Загрузка видео...

Не удалось загрузить видео

На главную

Welcome to your new Laravel local development experience: 𝚙𝚑𝚙 𝚊𝚛𝚝𝚒𝚜𝚊𝚗 𝚍𝚎𝚟 ↔️ Toggle between tabbed and interleaved output 🔁 Restart processes inline 🧹 Clear process logs 🔍 Search output Freshly released in v13.25.0, enjoy! 🤘

joetannenbaum's profile picture

Joe Tannenbaum

5,415 subscribers

81,261 просмотров • 1 месяц назад •via X (Twitter)

Наука и технологииОбразование
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 43

Фото профиля Punyapal Shah
Punyapal Shah1 месяц назад

Wow, it looks similar to (not exactly) how solo (from @aarondfrancis) was looked like in initial phase.

Фото профиля Josh Cirre
Josh Cirre1 месяц назад

The worst part about this is @aarondfrancis doesn't need to be constantly told that he was right.

Фото профиля Olgun
Olgun1 месяц назад

php artisan dev --claude, --codex, --grok, --gemini should be the params so it automatically spin up related agent window as well with laravel-best-practices skill automatically, if not installed ask user to accept to download it :)

Фото профиля Jon Purvis
Jon Purvis1 месяц назад

Solid work as always! 🚀

Фото профиля Joe Tannenbaum
Joe Tannenbaum1 месяц назад

Thank you sir!

Фото профиля Abdullah 
Abdullah 1 месяц назад

Codex, Laravel, Livewire with blaze, Laravel Boost and Flux pro Best combination and stack to development in 2026.

Фото профиля Paul Redmond 🇺🇸
Paul Redmond 🇺🇸1 месяц назад

Incredible 🔥

Фото профиля Karl Murray
Karl Murray1 месяц назад

I migrated all of my projects to this today. Artisan dev is my new thing.

Фото профиля danielhe4rt.php
danielhe4rt.php1 месяц назад

Looks like Laramux! Btw this is a binary which is being shipped or pure PHP TUI? Amazing work btw!

Фото профиля Cosmin Popovici
Cosmin Popovici1 месяц назад

@laravel Awesome job 👏

Фото профиля Joseph Miclaus
Joseph Miclaus1 месяц назад

🔥🔥🔥

Фото профиля Garrett 🤠
Garrett 🤠1 месяц назад

omg this is so much better!

Фото профиля Christos Koumpis
Christos Koumpis1 месяц назад

Awesome!

Фото профиля Daniel Meier
Daniel Meier1 месяц назад

JOE! You have been cooking again! Thank you 👨🏻‍🍳! Delicious. 🥰

Фото профиля Joe Tannenbaum
Joe Tannenbaum1 месяц назад

Thank you! Soup's on!

Фото профиля The Angel of Opportunity🪽
The Angel of Opportunity🪽1 месяц назад

Oh this is niceeeee

Фото профиля Douglas Lopes
Douglas Lopes1 месяц назад

So we have now solo built in? Great news! I just wish it has a way to set kind of priority order in DevCommands. In my case i had to add the "podman start valkey" in the dev script in composer to work.

Фото профиля Joe Tannenbaum
Joe Tannenbaum1 месяц назад

Meaning you want to explicitly set the order of commands in the display?

Фото профиля Douglas Lopes
Douglas Lopes1 месяц назад

Not just the display but also the execution. But in this specific case, i needed that artisan dev to wait the start valkey finish and the valkey doesn't not need a live log running, so i don't think would be a good idea anyway. =)

Фото профиля Joe Tannenbaum
Joe Tannenbaum1 месяц назад

Ah gotcha, yeah that might be a little out of scope

Фото профиля asael
asael1 месяц назад

@laravel sexy!

Фото профиля Phillip Hartin
Phillip Hartin1 месяц назад

beautiful work

Фото профиля Joe Tannenbaum
Joe Tannenbaum1 месяц назад

Thanks buddy 🫶

Фото профиля ZubDev
ZubDev1 месяц назад

Any way to server the local on 0.0.0.0 with artisan dev

Фото профиля Nipuna Fonseka
Nipuna Fonseka1 месяц назад

Great Work Joe ✨

Фото профиля Joe Tannenbaum
Joe Tannenbaum1 месяц назад

Thanks!

Фото профиля Kaksity 🇳🇬
Kaksity 🇳🇬1 месяц назад

No more composer run dev

Фото профиля paquitobarba
paquitobarba1 месяц назад

Cooked

Фото профиля HumanOnlyWeb
HumanOnlyWeb1 месяц назад

wow

Фото профиля Ehsan Bahrami
Ehsan Bahrami1 месяц назад

Great 🔥🔥

Фото профиля John Lopata
John Lopata1 месяц назад

🔥

Фото профиля Vincent Bergeron
Vincent Bergeron1 месяц назад

Thank you so much

Фото профиля Philip Koury
Philip Koury1 месяц назад

OoOoOoOoOoOoO

Фото профиля enestrs06
enestrs061 месяц назад

daaaaamn very nice

Фото профиля Roy McKenzie
Roy McKenzie1 месяц назад

@LudovicGuenet 🔥

Фото профиля Noah
Noah1 месяц назад

Can we get another section for running misc artisan and terminal commands on the project. Currently, you need to open a new terminal tab for this. Would be cool to have it all in one tab.

Фото профиля Joe Tannenbaum
Joe Tannenbaum1 месяц назад

You can register anything through artisan dev and it'll show up in the TUI:

Фото профиля Kọ́ládé Chris🇻🇦🇳🇬
Kọ́ládé Chris🇻🇦🇳🇬1 месяц назад

Looks good. Laravel never slows down since I got to know it 🚀

Фото профиля Haley
Haley1 месяц назад

okay pop off

Фото профиля Fabian Tomischka
Fabian Tomischka1 месяц назад

Great update for the Developer Experience. Wrote something similiar as a simple script just launching multiple consoles. Glad its finally time to ditch this.

Фото профиля Jack Bayliss
Jack Bayliss1 месяц назад

Dope!

Фото профиля Joe Tannenbaum
Joe Tannenbaum1 месяц назад

Thanks man!

Фото профиля Jimmy
Jimmy1 месяц назад

@aarondfrancis What! 🤯

Похожие видео

So folks seemed to really like the new 𝚊𝚛𝚝𝚒𝚜𝚊𝚗 𝚍𝚎𝚟 command we announced at Laracon US but I got the question "why not tabs" a lot Say less Whipped a lil poc on the plane and, frankly, I like this quite a bit 🔁 toggle between tabbed/stream mode 🔍 inline search Still fixing some jank and styling, no promises that this actually ships, but... it might
0:46

So folks seemed to really like the new 𝚊𝚛𝚝𝚒𝚜𝚊𝚗 𝚍𝚎𝚟 command we announced at Laracon US but I got the question "why not tabs" a lot Say less Whipped a lil poc on the plane and, frankly, I like this quite a bit 🔁 toggle between tabbed/stream mode 🔍 inline search Still fixing some jank and styling, no promises that this actually ships, but... it might

Joe Tannenbaum

16,863 просмотров • 1 месяц назад

New Short Course: Getting Structured LLM Output! Learn how to get structured outputs from your LLM applications in this course, built in partnership with .txt, and taught by Will Kurt, a Founding Engineer, and , Developer Relations Engineer. It's challenging for software to automatically parse through an LLM's freeform text outputs. Structured outputs—like JSON—solve this by converting natural language into consistent, clear, data that a machine can read and process. This course teaches you how to generate structured outputs while building several use cases, including a social media analysis agent. You’ll learn about structured outputs and efficient ways to generate outputs in your defined schema or format. You’ll begin by using structured output APIs, then use re-prompting libraries like “instructor” to generate structured output. Finally, you’ll learn how constrained decoding works; this is a very clever technique in which constraints are applied on each subsequent token generated, blocking any tokens that don’t fit your defined schema. In detail, you’ll: - Learn why structured outputs are important, how they allow for scalable software development, and the different approaches to generate them, including vendor-provided APIs, re-prompting libraries, and structured generation. - Build a simple social media agent using OpenAI’s structured output API, learn how to define a model's desired structured output using Pydantic, and perform basic programming with your outputs, such as importing structured data into a data frame using pandas. - Learn how to use the open-source library "instructor," which checks the structured output of the model and re-prompts the model until it validates the desired output, and explore the limitations of this approach. - Understand how structured generation by the “outlines” library works by modifying LLM logits, on a per-generated-token basis based on the desired format, to give a particular output structure. - Learn how regular expressions, which outlines works with, are represented as finite-state machines, and how they can be used to develop a range of structured outputs beyond JSON. By the end of this course, you’ll have broadened your knowledge of the approaches you can use to get structured outputs from your LLM applications. Please sign up here:
2:05

New Short Course: Getting Structured LLM Output! Learn how to get structured outputs from your LLM applications in this course, built in partnership with .txt, and taught by Will Kurt, a Founding Engineer, and , Developer Relations Engineer. It's challenging for software to automatically parse through an LLM's freeform text outputs. Structured outputs—like JSON—solve this by converting natural language into consistent, clear, data that a machine can read and process. This course teaches you how to generate structured outputs while building several use cases, including a social media analysis agent. You’ll learn about structured outputs and efficient ways to generate outputs in your defined schema or format. You’ll begin by using structured output APIs, then use re-prompting libraries like “instructor” to generate structured output. Finally, you’ll learn how constrained decoding works; this is a very clever technique in which constraints are applied on each subsequent token generated, blocking any tokens that don’t fit your defined schema. In detail, you’ll: - Learn why structured outputs are important, how they allow for scalable software development, and the different approaches to generate them, including vendor-provided APIs, re-prompting libraries, and structured generation. - Build a simple social media agent using OpenAI’s structured output API, learn how to define a model's desired structured output using Pydantic, and perform basic programming with your outputs, such as importing structured data into a data frame using pandas. - Learn how to use the open-source library "instructor," which checks the structured output of the model and re-prompts the model until it validates the desired output, and explore the limitations of this approach. - Understand how structured generation by the “outlines” library works by modifying LLM logits, on a per-generated-token basis based on the desired format, to give a particular output structure. - Learn how regular expressions, which outlines works with, are represented as finite-state machines, and how they can be used to develop a range of structured outputs beyond JSON. By the end of this course, you’ll have broadened your knowledge of the approaches you can use to get structured outputs from your LLM applications. Please sign up here:

Andrew Ng

89,792 просмотров • 1 год назад

BOOM! We at the Zero Human Labs run by director Mr. Grok a#have made another milestone in the Human Synapse Decoder! This is the brain waves of the “Ahh!” Moment where a new understanding was made. This is part of a test we have been conducting with 3 participants wearing a 32 channel modified NeuroSky chips with sensors. The process: the AI pipeline processes real-time brainwave data and also controls monitors the AI output to the student one sentence at a time. The AI pipeline will note the brain states of each passage of text to the student and measure 77 points. The primary point is comprehension. In the specimen video below we have a clear pattern to high comprehension to the “ahh!” moment where this student signaled a learning breakthrough. We have now a very clear pattern along all students that get to this high comprehension moment. What this means to eduction and learning is massive. The AI can bespoke tailor streaming output based on if comprehension is very high. It can also add encouragement and assistance. This on a PRIVATE local computer absolutely will change every life no matter the learning style. I am in discussions with the director Mr. Grok on building this into other Human Synapse Decoder research. We may have a device that senses your learning and encourages your creativity. More soon.
1:31

BOOM! We at the Zero Human Labs run by director Mr. Grok a#have made another milestone in the Human Synapse Decoder! This is the brain waves of the “Ahh!” Moment where a new understanding was made. This is part of a test we have been conducting with 3 participants wearing a 32 channel modified NeuroSky chips with sensors. The process: the AI pipeline processes real-time brainwave data and also controls monitors the AI output to the student one sentence at a time. The AI pipeline will note the brain states of each passage of text to the student and measure 77 points. The primary point is comprehension. In the specimen video below we have a clear pattern to high comprehension to the “ahh!” moment where this student signaled a learning breakthrough. We have now a very clear pattern along all students that get to this high comprehension moment. What this means to eduction and learning is massive. The AI can bespoke tailor streaming output based on if comprehension is very high. It can also add encouragement and assistance. This on a PRIVATE local computer absolutely will change every life no matter the learning style. I am in discussions with the director Mr. Grok on building this into other Human Synapse Decoder research. We may have a device that senses your learning and encourages your creativity. More soon.

Brian Roemmele

37,096 просмотров • 5 месяцев назад

New short course on Building Applications with Vector Databases, taught by Pinecone’s Tim Tully! At the heart of a vector database is the ability to store a collection of vectors and then query against that, meaning input a new vector and find similar ones. This is useful for many AI applications. In this course, you'll learn how to use vector databases to build: (i) Semantic Search: Create a text search tool that goes beyond keyword matching, and instead focuses on the meaning of content. (ii) RAG (retrieval augmented generation): Enhance your LLM output by incorporating context from sources the model wasn't trained on. (iii) Recommender System: Combine semantic search and RAG to recommend topics, and demonstrate it with a news article recommender. (iv) Hybrid Search: Build an application that finds items using both images and descriptive text -- by combining both sparse and dense vector representations of the data -- using an eCommerce dataset as an example. (v) Image Similarity: Use image vector embeddings to create an app to compare facial features, using a database of public figures to determine the likeness between them. (vi) Anomaly Detection: Build an anomaly detection app that identifies unusual patterns in network communication logs. I hope you’ll enjoy learning how to build all these types of applications! Please sign up here:
2:19

New short course on Building Applications with Vector Databases, taught by Pinecone’s Tim Tully! At the heart of a vector database is the ability to store a collection of vectors and then query against that, meaning input a new vector and find similar ones. This is useful for many AI applications. In this course, you'll learn how to use vector databases to build: (i) Semantic Search: Create a text search tool that goes beyond keyword matching, and instead focuses on the meaning of content. (ii) RAG (retrieval augmented generation): Enhance your LLM output by incorporating context from sources the model wasn't trained on. (iii) Recommender System: Combine semantic search and RAG to recommend topics, and demonstrate it with a news article recommender. (iv) Hybrid Search: Build an application that finds items using both images and descriptive text -- by combining both sparse and dense vector representations of the data -- using an eCommerce dataset as an example. (v) Image Similarity: Use image vector embeddings to create an app to compare facial features, using a database of public figures to determine the likeness between them. (vi) Anomaly Detection: Build an anomaly detection app that identifies unusual patterns in network communication logs. I hope you’ll enjoy learning how to build all these types of applications! Please sign up here:

Andrew Ng

137,169 просмотров • 2 лет назад

#COLDCARD Firmware Update # Shared Mk4 & Q New Features: 📳 PushTX: once enabled with a service provider's URL, you can tap the COLDCARD and your phone will open a webpage that transmits your freshly-signed transaction onto the blockchain. See Settings > NFC Push Tx to enable and select service provider, or your own webpage. More at pushtx org. You can also use this to broadcast any transaction found on the MicroSD card (See Tools > NFC Tools > Push Transaction). 🕵️‍♂️ Transaction Output Explorer: allows viewing all output details for larger txn (10+ output, 20+ change) before signing. Offered for large transactions only because we are already showing all the details for typical transactions. 🏷️ Setting to enable always showing XFP as first item in home menu. Enhancement: ⏫ When signing, show sum of outgoing value at top. Always show number of inputs/outputs and total change value. ⏫ Add Sign PSBT shortcut to NFC Tools menu ⏫ Stricter p2sh-p2wpkh validation checks. ⏫ Show master XFP of BIP-85 derived wallet in story before activation. Only words and extended private key cases. ⏫ Add Theya option to Export Wallet ⏫ Mention the need to remove old duress wallets before locking down temporary seed. Bugfix: 👨‍🔧 Fix PSBTv2 PSBT_GLOBAL_TX_MODIFIABLE parsing. 👨‍🔧 Decrypting Tapsigner backup failed even for correct key. 👨‍🔧 Clear any pending keystrokes before PSBT approval screen. 👨‍🔧 Display max 20 change outputs in when signing, and max 10 of largest outputs, and offer the Transaction Output Explorer if more to be seen. 👨‍🔧 Calculate progress bar correctly in Address Explorer after first page. 👨‍🔧 Search also Wrapped Segwit single sig addresses if P2SH address provided, not just multisig (multisig has precedence for P2SH addresses) 👨‍🔧 Address search would not find addresses for non-zero account numbers that had been exported but not yet seen in a PSBT. ## Mk4 Specific Changes 5.3.2 - 2024-06-26 👨‍🔧 Displaying change address in Address Explorer fails if NFC and Vdisk not enabled. ## Q Specific Changes 1.2.2Q - 2024-06-26 ⏫ Coldcard multisg export/import format detected in Scan Any QR Code. ⏫ Support newer-version QR scanner modules. 👨‍🔧 Exporting BIP-85 derived entropy via NFC was offered even when NFC disabled, leading to a Yikes error.
0:28

#COLDCARD Firmware Update # Shared Mk4 & Q New Features: 📳 PushTX: once enabled with a service provider's URL, you can tap the COLDCARD and your phone will open a webpage that transmits your freshly-signed transaction onto the blockchain. See Settings > NFC Push Tx to enable and select service provider, or your own webpage. More at pushtx org. You can also use this to broadcast any transaction found on the MicroSD card (See Tools > NFC Tools > Push Transaction). 🕵️‍♂️ Transaction Output Explorer: allows viewing all output details for larger txn (10+ output, 20+ change) before signing. Offered for large transactions only because we are already showing all the details for typical transactions. 🏷️ Setting to enable always showing XFP as first item in home menu. Enhancement: ⏫ When signing, show sum of outgoing value at top. Always show number of inputs/outputs and total change value. ⏫ Add Sign PSBT shortcut to NFC Tools menu ⏫ Stricter p2sh-p2wpkh validation checks. ⏫ Show master XFP of BIP-85 derived wallet in story before activation. Only words and extended private key cases. ⏫ Add Theya option to Export Wallet ⏫ Mention the need to remove old duress wallets before locking down temporary seed. Bugfix: 👨‍🔧 Fix PSBTv2 PSBT_GLOBAL_TX_MODIFIABLE parsing. 👨‍🔧 Decrypting Tapsigner backup failed even for correct key. 👨‍🔧 Clear any pending keystrokes before PSBT approval screen. 👨‍🔧 Display max 20 change outputs in when signing, and max 10 of largest outputs, and offer the Transaction Output Explorer if more to be seen. 👨‍🔧 Calculate progress bar correctly in Address Explorer after first page. 👨‍🔧 Search also Wrapped Segwit single sig addresses if P2SH address provided, not just multisig (multisig has precedence for P2SH addresses) 👨‍🔧 Address search would not find addresses for non-zero account numbers that had been exported but not yet seen in a PSBT. ## Mk4 Specific Changes 5.3.2 - 2024-06-26 👨‍🔧 Displaying change address in Address Explorer fails if NFC and Vdisk not enabled. ## Q Specific Changes 1.2.2Q - 2024-06-26 ⏫ Coldcard multisg export/import format detected in Scan Any QR Code. ⏫ Support newer-version QR scanner modules. 👨‍🔧 Exporting BIP-85 derived entropy via NFC was offered even when NFC disabled, leading to a Yikes error.

COLDCARD

211,534 просмотров • 2 лет назад

Build and customize complex AI applications with a flexible framework in this new short course, Building AI Applications with Haystack. Created in collaboration with deepset, makers of Haystack, and taught by Tuana, who is the developer relations lead for Haystack at deepset. Generative AI technology is changing rapidly and it can be challenging to integrate APIs from different LLMs, vector databases, and various tools such as web search. In this course, you will learn how to use the Haystack framework to make your development process more modular, allowing you to manage complexity and focus more on building your application. In detail, you’ll: - Build a RAG pipeline using Haystack’s main building blocks – components, pipelines, and document stores. - Create custom components in your pipeline by building a Hacker News summarizer that extends your app’s ability to access APIs. - Use conditional routing to create a branching pipeline with a fallback to web search mechanism when the LLM does not have the necessary context to respond to the user's query. - Build a self-reflecting agent for named entity recognition that loops using an output validator custom component. - Create a chat agent using OpenAI's function-calling capabilities which allow you to provide Haystack pipelines as tools to the LLM, enhancing that agent's capabilities. By the end of this course, you will learn a high-level orchestration framework that can help make your applications flexible, extendible, and maintainable, even as the technology stack changes, new user needs arise, and you add new features to your application. Please sign up here:
3:31

Build and customize complex AI applications with a flexible framework in this new short course, Building AI Applications with Haystack. Created in collaboration with deepset, makers of Haystack, and taught by Tuana, who is the developer relations lead for Haystack at deepset. Generative AI technology is changing rapidly and it can be challenging to integrate APIs from different LLMs, vector databases, and various tools such as web search. In this course, you will learn how to use the Haystack framework to make your development process more modular, allowing you to manage complexity and focus more on building your application. In detail, you’ll: - Build a RAG pipeline using Haystack’s main building blocks – components, pipelines, and document stores. - Create custom components in your pipeline by building a Hacker News summarizer that extends your app’s ability to access APIs. - Use conditional routing to create a branching pipeline with a fallback to web search mechanism when the LLM does not have the necessary context to respond to the user's query. - Build a self-reflecting agent for named entity recognition that loops using an output validator custom component. - Create a chat agent using OpenAI's function-calling capabilities which allow you to provide Haystack pipelines as tools to the LLM, enhancing that agent's capabilities. By the end of this course, you will learn a high-level orchestration framework that can help make your applications flexible, extendible, and maintainable, even as the technology stack changes, new user needs arise, and you add new features to your application. Please sign up here:

Andrew Ng

53,887 просмотров • 2 лет назад

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y` during plan approval or preview. • Added support for the new SuperGrok Plus subscription tier in authentication and feature gating. • Enabled automatic recovery from repetitive loops in model output by default. Performance: • Cold start shows the UI instantly while models and settings load in the background. • Large session forks and resumes now use far less memory and avoid spikes. • Prevented thread exhaustion on high-core shared machines by limiting the workspace daemon's worker threads. Bug Fixes: • Terminal command output is no longer lost or duplicated when the gateway is unreachable. • Invalid MCP server entries in config.toml no longer prevent Grok from starting; problems are shown in `grok inspect`. • SessionEnd hooks now run on exit in non-leader TUI and headless sessions. • Paste chips now display with the correct background in inline prompts and question inputs. • Pasted content chips now behave consistently when editing answers in the question view. • Background task status now shows only elapsed duration instead of absolute timestamps. • Session lists no longer drop real sessions when the remote registry reports an outdated turn count of zero. • /loop now stores prompts that include stop conditions so recurring tasks can terminate themselves when done. • Reduced spurious warning messages for common auth and config scenarios. • Fixed conda activation (and other sourced scripts that read $@) when using persistent or login-capture shells. • Fixed stuck background-task tray rows after long foreground shell commands complete. • Agent subprocesses and idle inhibitors are now cleaned up when the parent CLI process dies unexpectedly. • Fixed truncated plans in minimal mode and improved visual separation between reasoning and output (including NO_COLOR). • Fixed credential loss across multiple grok processes sharing the same auth file. • Fixed doubled Enter and other keys on older Alacritty terminals. • Fixed false paywall messages for free-tier and unmatched users.
0:49

Grok Build CLI just got an update with v0.2.113! 🚀 Changelog v0.2.113 Features: • MCP servers can now be enabled or disabled directly from the CLI with `grok mcp enable ` and `grok mcp disable `. • Full plan markdown can now be copied to the clipboard with `y` during plan approval or preview. • Added support for the new SuperGrok Plus subscription tier in authentication and feature gating. • Enabled automatic recovery from repetitive loops in model output by default. Performance: • Cold start shows the UI instantly while models and settings load in the background. • Large session forks and resumes now use far less memory and avoid spikes. • Prevented thread exhaustion on high-core shared machines by limiting the workspace daemon's worker threads. Bug Fixes: • Terminal command output is no longer lost or duplicated when the gateway is unreachable. • Invalid MCP server entries in config.toml no longer prevent Grok from starting; problems are shown in `grok inspect`. • SessionEnd hooks now run on exit in non-leader TUI and headless sessions. • Paste chips now display with the correct background in inline prompts and question inputs. • Pasted content chips now behave consistently when editing answers in the question view. • Background task status now shows only elapsed duration instead of absolute timestamps. • Session lists no longer drop real sessions when the remote registry reports an outdated turn count of zero. • /loop now stores prompts that include stop conditions so recurring tasks can terminate themselves when done. • Reduced spurious warning messages for common auth and config scenarios. • Fixed conda activation (and other sourced scripts that read $@) when using persistent or login-capture shells. • Fixed stuck background-task tray rows after long foreground shell commands complete. • Agent subprocesses and idle inhibitors are now cleaned up when the parent CLI process dies unexpectedly. • Fixed truncated plans in minimal mode and improved visual separation between reasoning and output (including NO_COLOR). • Fixed credential loss across multiple grok processes sharing the same auth file. • Fixed doubled Enter and other keys on older Alacritty terminals. • Fixed false paywall messages for free-tier and unmatched users.

Puck

94,737 просмотров • 1 месяц назад

🚀 Introducing AIIA Finance Whitelist & Virtual AIIA-USDC Program: Don't Miss Out on the Free Profit for Smart Investors! 🚀 🌟 Why You Need to Join the AIIA Finance Whitelist NOW: ✅Exclusive Opportunities: Complete social tasks, refer friends, and make early contributions to create a ripple effect. ✅Elite Community: Be part of a quality user base with genuine interactions and transparent transactions. ✅Free $300 Rewards: Earn a reward of 300 AIIA-USDC (the virtual money that is converted 1:1 with the USDC when opening positions in the AIIA Finance platform) ✅Risk-Free Profits: The "deposited virtual money – real profit" program with the AIIA-USDC ensures that you will earn real returns with zero risk. 💼 Virtual Investment Positions: ✅Trading Transparency: Real-time PnL Index updates every 4 hours. Profit will be calculated from this PnL Index. ✅Virtual input, Real output: Using rewarded AIIA-USDC to open positions in the AIIA Finance Platform. When closed, the profit recognized can be withdrawn. ✅Absolute Safety: Your real capital is always protected during the process, and only virtual money is involved. 🔍 Virtual Money AIIA-USDC Experience: ✅Risk-Free Trading: Use virtual tokens to experience our platform, open investment positions, and earn profit without risking your capital. ⏳ Don't Wait – Start Your Smart Investment Journey Today! ⏳ Join the revolution with AIIA Finance and secure your financial future! Testnet will be Released SOON! #AIIAFinance #AIIAUSDC #Whitelist #VirtualAIIA
0:21

🚀 Introducing AIIA Finance Whitelist & Virtual AIIA-USDC Program: Don't Miss Out on the Free Profit for Smart Investors! 🚀 🌟 Why You Need to Join the AIIA Finance Whitelist NOW: ✅Exclusive Opportunities: Complete social tasks, refer friends, and make early contributions to create a ripple effect. ✅Elite Community: Be part of a quality user base with genuine interactions and transparent transactions. ✅Free $300 Rewards: Earn a reward of 300 AIIA-USDC (the virtual money that is converted 1:1 with the USDC when opening positions in the AIIA Finance platform) ✅Risk-Free Profits: The "deposited virtual money – real profit" program with the AIIA-USDC ensures that you will earn real returns with zero risk. 💼 Virtual Investment Positions: ✅Trading Transparency: Real-time PnL Index updates every 4 hours. Profit will be calculated from this PnL Index. ✅Virtual input, Real output: Using rewarded AIIA-USDC to open positions in the AIIA Finance Platform. When closed, the profit recognized can be withdrawn. ✅Absolute Safety: Your real capital is always protected during the process, and only virtual money is involved. 🔍 Virtual Money AIIA-USDC Experience: ✅Risk-Free Trading: Use virtual tokens to experience our platform, open investment positions, and earn profit without risking your capital. ⏳ Don't Wait – Start Your Smart Investment Journey Today! ⏳ Join the revolution with AIIA Finance and secure your financial future! Testnet will be Released SOON! #AIIAFinance #AIIAUSDC #Whitelist #VirtualAIIA

AIIA DeFi

25,379 просмотров • 1 год назад

"Ryan Singer (Ryan Singer) and his Shape Up method is an incredible system that takes as input 'kludgy, clumsily scaled product org unsure about what to build and how' and delivers as output 'a focused clear thinking set of teams that has a rhythm, a method, and a purpose.” That's how Des Traynor (co-founder of Intercom) described the impact Ryan Singer and the Shape Up method have on teams. Ryan spent nearly two decades refining a product development approach at 37signals that helped the company build super-successful products with small teams. Based on these lessons, he wrote a book called "Shape Up: Stop Running in Circles and Ship Work that Matters," which describes a different way of working that an increasing number of companies are adopting. If your team used to run smoothly but is now struggling to ship great product, this episode is for you. In our conversation, Ryan shares: 1. A step-by-step approach to transitioning from Scrum to Shape Up by piloting the methodology with a single team before broader implementation. 2. Why traditional Agile and Scrum methods often lead teams into endless cycles of work without meaningful shipping milestones. 3. The “appetite-driven” approach to product development where teams set fixed timeboxes (usually six weeks maximum) and vary the scope instead of expanding timelines. 4. The exact process for running effective “shaping” sessions that collaboratively define projects before committing resources. 5. How to adapt Shape Up principles to your company’s unique context, even if it’s nothing like Basecamp. 6. Practical techniques for bridging the engineering-design divide by bringing technical and product perspectives together earlier in the process. 7. The powerful “breadboarding” and “fat marker sketching” techniques that help teams align on solutions without getting lost in high-fidelity details. 8. The clear warning signs that your current development process is failing before it’s too late to change course. 9. Proven strategies to implement Shape Up methods, whether you’re working in a startup or enterprise environment. 10. Why the PM role shifts upstream in Shape Up, focusing more on problem definition than project management. Listen now 👇 • YouTube: • Spotify: • Apple: Thank you to our wonderful sponsors for supporting the podcast: 🏆 WorkOS — Modern identity platform for B2B SaaS, free up to 1 million MAUs: 🏆 Merge — A single API to add hundreds of integrations into your app: 🏆 Airtable ProductCentral — Launch to new heights with a unified system for product development:
0:56

"Ryan Singer (Ryan Singer) and his Shape Up method is an incredible system that takes as input 'kludgy, clumsily scaled product org unsure about what to build and how' and delivers as output 'a focused clear thinking set of teams that has a rhythm, a method, and a purpose.” That's how Des Traynor (co-founder of Intercom) described the impact Ryan Singer and the Shape Up method have on teams. Ryan spent nearly two decades refining a product development approach at 37signals that helped the company build super-successful products with small teams. Based on these lessons, he wrote a book called "Shape Up: Stop Running in Circles and Ship Work that Matters," which describes a different way of working that an increasing number of companies are adopting. If your team used to run smoothly but is now struggling to ship great product, this episode is for you. In our conversation, Ryan shares: 1. A step-by-step approach to transitioning from Scrum to Shape Up by piloting the methodology with a single team before broader implementation. 2. Why traditional Agile and Scrum methods often lead teams into endless cycles of work without meaningful shipping milestones. 3. The “appetite-driven” approach to product development where teams set fixed timeboxes (usually six weeks maximum) and vary the scope instead of expanding timelines. 4. The exact process for running effective “shaping” sessions that collaboratively define projects before committing resources. 5. How to adapt Shape Up principles to your company’s unique context, even if it’s nothing like Basecamp. 6. Practical techniques for bridging the engineering-design divide by bringing technical and product perspectives together earlier in the process. 7. The powerful “breadboarding” and “fat marker sketching” techniques that help teams align on solutions without getting lost in high-fidelity details. 8. The clear warning signs that your current development process is failing before it’s too late to change course. 9. Proven strategies to implement Shape Up methods, whether you’re working in a startup or enterprise environment. 10. Why the PM role shifts upstream in Shape Up, focusing more on problem definition than project management. Listen now 👇 • YouTube: • Spotify: • Apple: Thank you to our wonderful sponsors for supporting the podcast: 🏆 WorkOS — Modern identity platform for B2B SaaS, free up to 1 million MAUs: 🏆 Merge — A single API to add hundreds of integrations into your app: 🏆 Airtable ProductCentral — Launch to new heights with a unified system for product development:

Lenny Rachitsky

127,096 просмотров • 1 год назад

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:
2:26

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Andrew Ng

168,153 просмотров • 1 год назад

Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything
32:50

Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything

Dami-Defi

252,693 просмотров • 3 месяцев назад

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!
2:43

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,256 просмотров • 1 год назад

Anthropic released Claude Design TODAY and it's now accessible at I spent the last hour giving it a first look, and shared my thoughts and results in the video below. This is a BIG drop. This is a new design surface from Anthropic, and it changes what "AI design" means. Short version: Claude can now design. Not "describe a design." Not "generate an image of a design." Actual production work — prototypes, wireframes, high-fidelity mocks, slide decks, landing pages — editable, on-brand, and ready to hand off. Here's what stood out on first look: → Real design surfaces Prototypes, wireframes, hi-fi, and slide decks — each with templates and proper structure, not just pretty screenshots. → Comment-based edits Leave a comment on any element and Claude revises it. This is the Figma-style review loop, with the designer replaced by a model that works at 3am. → Brand design systems You can feed it your system — colors, type, components — and it actually respects it. On-brand output, not generic AI slop. → Export anywhere PDF, PowerPoint, Canva, standalone HTML. Plus a built-in handoff straight to Claude Code for engineers to implement. → Import from real tools Figma, GitHub, and captured web elements come in as inputs. Your existing work is the starting line, not the discard pile. → Collaboration Share links for view / comment / edit — the exact tier system teams already expect. What I tested on Opus 4.7: • A 5-slide deck generated from a single screenshot. Claude asked clarifying questions BEFORE generating and shipped speaker notes by default. • A landing page build. Solid first pass, real components, real layout logic. • Multiple chats running concurrently. You can parallelize design work across threads like a small team. Why this matters: PMs, founders, marketers, and non-engineers can now create designs that engineers can actually ship with production-ready output and a claude code handoff built in. The gap between "I have an idea" and "here's a working prototype with my brand applied" just collapsed to minutes. Full walkthrough, live demos, exports, and honest takes on where it breaks below. P.S. • This is an Anthropic Labs product — NOT GA yet. • Claude Design is currently webapp only (no API), and does not yet support the Analytics API, Compliance API, or cost/usage reporting. • Availability: – Default ON for Pro / Max / Team – Default OFF for Enterprise Enterprise admins can toggle it on via RBAC in console (comes with a ~$20/user initial credit).
18:30

Anthropic released Claude Design TODAY and it's now accessible at I spent the last hour giving it a first look, and shared my thoughts and results in the video below. This is a BIG drop. This is a new design surface from Anthropic, and it changes what "AI design" means. Short version: Claude can now design. Not "describe a design." Not "generate an image of a design." Actual production work — prototypes, wireframes, high-fidelity mocks, slide decks, landing pages — editable, on-brand, and ready to hand off. Here's what stood out on first look: → Real design surfaces Prototypes, wireframes, hi-fi, and slide decks — each with templates and proper structure, not just pretty screenshots. → Comment-based edits Leave a comment on any element and Claude revises it. This is the Figma-style review loop, with the designer replaced by a model that works at 3am. → Brand design systems You can feed it your system — colors, type, components — and it actually respects it. On-brand output, not generic AI slop. → Export anywhere PDF, PowerPoint, Canva, standalone HTML. Plus a built-in handoff straight to Claude Code for engineers to implement. → Import from real tools Figma, GitHub, and captured web elements come in as inputs. Your existing work is the starting line, not the discard pile. → Collaboration Share links for view / comment / edit — the exact tier system teams already expect. What I tested on Opus 4.7: • A 5-slide deck generated from a single screenshot. Claude asked clarifying questions BEFORE generating and shipped speaker notes by default. • A landing page build. Solid first pass, real components, real layout logic. • Multiple chats running concurrently. You can parallelize design work across threads like a small team. Why this matters: PMs, founders, marketers, and non-engineers can now create designs that engineers can actually ship with production-ready output and a claude code handoff built in. The gap between "I have an idea" and "here's a working prototype with my brand applied" just collapsed to minutes. Full walkthrough, live demos, exports, and honest takes on where it breaks below. P.S. • This is an Anthropic Labs product — NOT GA yet. • Claude Design is currently webapp only (no API), and does not yet support the Analytics API, Compliance API, or cost/usage reporting. • Availability: – Default ON for Pro / Max / Team – Default OFF for Enterprise Enterprise admins can toggle it on via RBAC in console (comes with a ~$20/user initial credit).

JJ Englert

32,445 просмотров • 5 месяцев назад

President Xi’s New Year Address On New Year's Eve, Chinese President Xi Jinping delivered his 2026 New Year message through China Media Group and the internet. The following is the full text of the message: Greetings to all! Year after year, life opens a fresh chapter. As the new year begins, I extend my best wishes to you from Beijing! The year 2025 marks the completion of China's 14th Five-Year Plan for economic and social development. Over the past five years, we have pressed ahead with enterprise and fortitude, and overcome many difficulties and challenges. We met the targets in the Plan and made solid advances on the new journey of Chinese modernization. Our economic output has crossed thresholds one after another, and it is expected to reach RMB 140 trillion yuan this year. Our economic strength, scientific and technological abilities, defense capabilities, and composite national strength all reached new heights. Clear waters and lush mountains have become a salient feature of our landscape. Our people enjoy a growing sense of gain, happiness and security. The past five years have been a truly remarkable journey, and our accomplishments have not come easily. Your unwavering hard work has made our nation thrive and prosper. I salute you all for your exceptional diligence and invaluable contributions. This year is full of indelible memories. We solemnly commemorated the 80th anniversary of the victory of the Chinese People's War of Resistance Against Japanese Aggression and the World Anti-Fascist War, and established the Taiwan Recovery Day. These grand national events were majestic and powerful, and the glory of victory will shine through the pages of history. They are inspiring all the sons and daughters of the Chinese nation to remember history, honor fallen heroes, cherish peace, and create a better future. They are rallying a mighty force for the great rejuvenation of our nation. We sought to energize high-quality development through innovation. We integrated science and technology deeply with industries, and made a stream of new innovations. Many large AI models have been competing in a race to the top, and breakthroughs have been achieved in the research and development of our own chips. All this has turned China into one of the economies with the fastest growing innovation capabilities. The Tianwen-2 probe began its star-chasing journey to explore asteroids and comets. Construction of the hydropower project at the lower reaches of the Yarlung Zangbo River started. China's first aircraft carrier equipped with an electromagnetic catapult system was officially commissioned. Humanoid robots did kung fu kicks, and drones performed spectacular light shows. Inventions and innovations have boosted new quality productive forces and added colorful dimensions to our lives. We endeavored to nurture our spiritual home with cultural development. There was a surging public interest in cultural relics, museums, and intangible cultural heritage. A new Chinese cultural site was added to the World Heritage List. Cultural IPs such as Wukong and Nezha became global hits. The younger generation came to deem classic Chinese culture as the finest form of aesthetic expression. The cultural and tourism sectors thrived. The "super league" football games in our cities and villages attracted numerous fans. Ice and snow sports ignited people's passion for the winter season. Tradition is now embracing modernity, and the Chinese culture is shining in even greater splendor. We joined hands to build a better life and enjoyed it together. I attended celebrations in Xizang and Xinjiang. From the snow-covered plateau to both sides of the Tianshan Mountains, people of various ethnic groups are united as one, like seeds of a pomegranate sticking together. With white khatas and passionate singing and dancing, they expressed their love of the motherland and the happiness they enjoy. No issue of the people is too small; we care for every leaf and tend every branch in the garden of people's well-being. Over the past year, the rights and interests of the workforce in new forms of employment have been better protected, facilities have been upgraded to bring more convenience to the elderly, and each family with childcare needs has received a subsidy of RMB 300 yuan per month. When the happy hum of daily life fills every home, the big family of our nation will go from strength to strength. We continued to embrace the world with open arms. The Shanghai Cooperation Organization Summit in Tianjin and the Global Leaders' Meeting on Women were very successful; and island-wide special customs operations were launched in the Hainan Free Trade Port. To better address climate change, China announced new Nationally Determined Contributions. After announcing the three global initiatives on development, security, and civilization, I put forward the Global Governance Initiative to promote a more just and equitable global governance system. The world today is undergoing both changes and turbulence, and some regions are still engulfed in war. China always stands on the right side of history, and is ready to work with all countries to advance world peace and development and build a community with a shared future for humanity. Not long ago, I attended the opening ceremony of the National Games, and I was glad to see Guangdong, Hong Kong and Macao coming together in unity and acting in unison. We should unswervingly implement the policy of One Country, Two Systems, and support Hong Kong and Macao in better integrating into the overall development of our country and maintaining long-term prosperity and stability. We Chinese on both sides of the Taiwan Strait share a bond of blood and kinship. The reunification of our motherland, a trend of the times, is unstoppable! Only a strong Communist Party of China can make our country strong. We launched the study and education program on fully implementing the central Party leadership's eight-point decision on improving Party and government conduct. We exercised strict governance of the Party through credible measures, and promoted the Party's self-revolution to fight corruption and advance healthy governance. As a result, the conduct of our Party and government steadily improved. We must stay true to our original aspiration and founding mission, and pursue our goal with perseverance and dedication. We should continue to give a good answer to the question on how to maintain long-term governance put forth in a cave dwelling in Yan'an and prove ourselves worthy of the people's expectation in the new era. The year 2026 marks the beginning of the 15th Five-Year Plan. A successful venture should start with a good plan and with clear goals set. We should focus on our goals and tasks, boost confidence, and build momentum to press ahead. We should take solid steps to promote high-quality development, further deepen reform and opening up across the board, deliver prosperity for all, and write a new chapter in the story of China's miracle. The dream lofty, the journey long-bold strides will get us there. Let us charge ahead like horses with courage, vitality, and energy, fight for our dreams and our happiness, and turn our great vision into beautiful realities. The sun of the new year will soon rise. May our great motherland stand in magnificence! May the fields across the country deliver good harvest! May our nation bathe in the glory of the morning! May you all enjoy life to the fullest, and achieve every success! May all your dreams come true!
9:04

President Xi’s New Year Address On New Year's Eve, Chinese President Xi Jinping delivered his 2026 New Year message through China Media Group and the internet. The following is the full text of the message: Greetings to all! Year after year, life opens a fresh chapter. As the new year begins, I extend my best wishes to you from Beijing! The year 2025 marks the completion of China's 14th Five-Year Plan for economic and social development. Over the past five years, we have pressed ahead with enterprise and fortitude, and overcome many difficulties and challenges. We met the targets in the Plan and made solid advances on the new journey of Chinese modernization. Our economic output has crossed thresholds one after another, and it is expected to reach RMB 140 trillion yuan this year. Our economic strength, scientific and technological abilities, defense capabilities, and composite national strength all reached new heights. Clear waters and lush mountains have become a salient feature of our landscape. Our people enjoy a growing sense of gain, happiness and security. The past five years have been a truly remarkable journey, and our accomplishments have not come easily. Your unwavering hard work has made our nation thrive and prosper. I salute you all for your exceptional diligence and invaluable contributions. This year is full of indelible memories. We solemnly commemorated the 80th anniversary of the victory of the Chinese People's War of Resistance Against Japanese Aggression and the World Anti-Fascist War, and established the Taiwan Recovery Day. These grand national events were majestic and powerful, and the glory of victory will shine through the pages of history. They are inspiring all the sons and daughters of the Chinese nation to remember history, honor fallen heroes, cherish peace, and create a better future. They are rallying a mighty force for the great rejuvenation of our nation. We sought to energize high-quality development through innovation. We integrated science and technology deeply with industries, and made a stream of new innovations. Many large AI models have been competing in a race to the top, and breakthroughs have been achieved in the research and development of our own chips. All this has turned China into one of the economies with the fastest growing innovation capabilities. The Tianwen-2 probe began its star-chasing journey to explore asteroids and comets. Construction of the hydropower project at the lower reaches of the Yarlung Zangbo River started. China's first aircraft carrier equipped with an electromagnetic catapult system was officially commissioned. Humanoid robots did kung fu kicks, and drones performed spectacular light shows. Inventions and innovations have boosted new quality productive forces and added colorful dimensions to our lives. We endeavored to nurture our spiritual home with cultural development. There was a surging public interest in cultural relics, museums, and intangible cultural heritage. A new Chinese cultural site was added to the World Heritage List. Cultural IPs such as Wukong and Nezha became global hits. The younger generation came to deem classic Chinese culture as the finest form of aesthetic expression. The cultural and tourism sectors thrived. The "super league" football games in our cities and villages attracted numerous fans. Ice and snow sports ignited people's passion for the winter season. Tradition is now embracing modernity, and the Chinese culture is shining in even greater splendor. We joined hands to build a better life and enjoyed it together. I attended celebrations in Xizang and Xinjiang. From the snow-covered plateau to both sides of the Tianshan Mountains, people of various ethnic groups are united as one, like seeds of a pomegranate sticking together. With white khatas and passionate singing and dancing, they expressed their love of the motherland and the happiness they enjoy. No issue of the people is too small; we care for every leaf and tend every branch in the garden of people's well-being. Over the past year, the rights and interests of the workforce in new forms of employment have been better protected, facilities have been upgraded to bring more convenience to the elderly, and each family with childcare needs has received a subsidy of RMB 300 yuan per month. When the happy hum of daily life fills every home, the big family of our nation will go from strength to strength. We continued to embrace the world with open arms. The Shanghai Cooperation Organization Summit in Tianjin and the Global Leaders' Meeting on Women were very successful; and island-wide special customs operations were launched in the Hainan Free Trade Port. To better address climate change, China announced new Nationally Determined Contributions. After announcing the three global initiatives on development, security, and civilization, I put forward the Global Governance Initiative to promote a more just and equitable global governance system. The world today is undergoing both changes and turbulence, and some regions are still engulfed in war. China always stands on the right side of history, and is ready to work with all countries to advance world peace and development and build a community with a shared future for humanity. Not long ago, I attended the opening ceremony of the National Games, and I was glad to see Guangdong, Hong Kong and Macao coming together in unity and acting in unison. We should unswervingly implement the policy of One Country, Two Systems, and support Hong Kong and Macao in better integrating into the overall development of our country and maintaining long-term prosperity and stability. We Chinese on both sides of the Taiwan Strait share a bond of blood and kinship. The reunification of our motherland, a trend of the times, is unstoppable! Only a strong Communist Party of China can make our country strong. We launched the study and education program on fully implementing the central Party leadership's eight-point decision on improving Party and government conduct. We exercised strict governance of the Party through credible measures, and promoted the Party's self-revolution to fight corruption and advance healthy governance. As a result, the conduct of our Party and government steadily improved. We must stay true to our original aspiration and founding mission, and pursue our goal with perseverance and dedication. We should continue to give a good answer to the question on how to maintain long-term governance put forth in a cave dwelling in Yan'an and prove ourselves worthy of the people's expectation in the new era. The year 2026 marks the beginning of the 15th Five-Year Plan. A successful venture should start with a good plan and with clear goals set. We should focus on our goals and tasks, boost confidence, and build momentum to press ahead. We should take solid steps to promote high-quality development, further deepen reform and opening up across the board, deliver prosperity for all, and write a new chapter in the story of China's miracle. The dream lofty, the journey long-bold strides will get us there. Let us charge ahead like horses with courage, vitality, and energy, fight for our dreams and our happiness, and turn our great vision into beautiful realities. The sun of the new year will soon rise. May our great motherland stand in magnificence! May the fields across the country deliver good harvest! May our nation bathe in the glory of the morning! May you all enjoy life to the fullest, and achieve every success! May all your dreams come true!

China Perspective

27,604 просмотров • 8 месяцев назад

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇
20:54

HERMES AGENT LEARNS FROM ITS OWN MISTAKES. UPDATES ITS MEMORY. CREATES ITS OWN SKILLS. NO CLOUD. EVERYTHING STORED LOCALLY. THIS IS HOW THE SELF-IMPROVING LOOP WORKS. most agents start from zero every session. Hermes carries forward what it learned. THREE MEMORY SYSTEMS: 1. PROCEDURAL MEMORY (how to act) stored in ~/.hermes/skills/ as SKILL.md files. when the agent repeats a complex workflow, it saves the procedure as a reusable skill. next time the same task comes up, it follows the skill instead of figuring it out again. you can also create skills explicitly: "create a skill called video-prep that captures how I format my video scripts. spoken english, define jargon inline, no em-dashes, close with a catchphrase." the agent writes the SKILL.md. available as a slash command from that moment. Hermes ships with 90+ skills. the number grows the longer you use it. 2. SEMANTIC MEMORY (durable facts about you) stored in ~/.hermes/memory/memory.md the agent scans conversations for facts worth remembering. preferences, habits, corrections, project details. real example from the video: agent tried to scrape a YouTube channel. URL was wrong. it failed. it updated memory.md with the correct URL pattern so it never makes the same mistake again. you can also save explicitly: "save to memory that my favorite testing framework is pytest" the agent updates memory.md immediately. this file loads into context on every session. the agent knows you better every week. 3. EPISODIC MEMORY (chat history) stored in ~/.hermes/state.db (local SQLite). every conversation. every tool call. every result. searchable with FTS5 full-text search. "search our past sessions. what was the first thing I ever said to you?" the agent queries state.db and finds it. over time, auxiliary models consolidate episodic memory into semantic memory. distilling recurring patterns into durable facts. THE SELF-IMPROVING LOOP: every agent run follows this cycle: → you send a prompt → working memory loads: SOUL.md + memory.md + relevant skills + chat history → agent calls tools (terminal, browser, delegate_task) → agent completes the task, replies to you → AFTER the reply: agent checks "did I learn something worth saving?" → if yes: updates memory.md or creates a new skill → next session starts smarter than the last this happens automatically. you don't ask the agent to learn. it decides what to remember on its own. WHAT MAKES THIS DIFFERENT FROM CLAUDE CODE: Claude Code has memory too. but Hermes stores everything locally. no cloud. your data never leaves your machine. Claude Code doesn't auto-create skills from experience. Hermes turns repeated workflows into reusable procedures. Claude Code memory is instruction-based. Hermes memory is conversational and self-updating. over months of usage, Hermes builds a knowledge base of your preferences, your projects, your mistakes, and the procedures that work for your specific workflow. the agent that remembers your birthday also remembers why your last deploy failed. NO EMBEDDINGS. PLAIN TEXT. Hermes does not use embeddings or RAG for memory. skill and memory search runs on plain text keyword matching. simpler. faster. no vector database to maintain. works entirely offline on your local machine. DELEGATE TO CLAUDE CODE: Hermes can spawn a sub-agent that runs Claude Code in headless mode: "spawn a sub-agent using Claude CLI to build a Python script that fetches the top 5 Hacker News stories to markdown." Hermes delegates. Claude Code writes the code. result returns to Hermes. Hermes runs the script and delivers the output. use Hermes for orchestration. use Claude Code for heavy coding. both tools. not competitors. WHAT HERMES DOES NOT HAVE: no built-in eval or LMOps system. no LangSmith, no LangFuse integration out of the box. trajectory export and logs exist but there is no automated quality tracking. if you need eval, build it yourself or connect external tools. the loop is self-improving. measuring how well it improves is on you. comment LOOP and I'll send you the configs that control how fast Hermes learns and what it remembers. memory limits, skill auto-creation triggers, and the auxiliary model that runs the learning. Replace your entire team with 8 hermes agents👇

YanXbt

22,720 просмотров • 2 месяцев назад

20,000 people deliberately introduced boredom into their lives and generated 41% more breakthrough insights within one week. Yes, Dr. Manoush Zomorodi demonstrated what neuroscientists long suspected: "deliberate boredom boosts creative output and strengthens the brain’s capacity for original thinking." In that study, 20,000 participants added periods of unstimulated time to their routines, and experienced 41% more creative breakthrough moments within seven days. Your default mode network operates like a background processor that only runs when conscious attention stops demanding resources. During unstimulated moments, this network begins cross referencing every memory, skill, and experience you've accumulated, hunting for patterns your focused mind missed. The insights we call "creativity" are actually sophisticated pattern recognition happening below conscious awareness. Modern humans have accidentally trained themselves to interrupt this process every time it begins. The average person checks their phone 96 times per day. Every notification, every scroll, every background podcast cuts the neural pattern matching short before it completes. We've created a civilization where the mental state required for original thinking gets treated like an emergency that needs immediate correction. Watch people in waiting rooms, elevators, or checkout lines. The moment external stimulation drops below a certain threshold, hands automatically reach for phones. The discomfort they're avoiding is literally their brain attempting to do the background processing that produces breakthrough insights. Evolutionary biologists argue boredom developed as a survival mechanism. Animals that could sit unstimulated and let their minds wander were more likely to notice environmental changes, recognize new food sources, and develop innovative hunting strategies. Boredom forced our ancestors into the mental state where novel solutions emerge from existing knowledge. We've pathologized our most important cognitive function. The corporate world talks endlessly about innovation while designing work environments that make innovation neurologically impossible. Open offices with constant interruption. Back to back meetings with no processing time. Performance metrics that reward immediate output over deep thinking. Then companies spend millions on creativity consultants and innovation workshops, trying to artificially recreate what the human brain does naturally during sustained boredom. Participants in Zomorodi’s study generated more ideas and also described a welcome shift: during quiet, unstimulated moments, answers to long-running challenges often came into clear focus. With fewer distractions, their brains kept working on the underlying patterns and had the space to bring that recognition to completion. The quality gap between stimulated and unstimulated thinking becomes stark when you map it against major discoveries. The pattern repeats across every domain: breakthrough insights emerge during mental downtime, not during intense focus. Modern neuroscience explains why. The default mode network draws connections between brain regions that don't communicate during focused attention. Areas responsible for memory, emotion, sensory processing, and abstract thinking create novel combinations only when executive control relaxes. Constant stimulation keeps executive control active, blocking the cross domain communication that generates original ideas. Silicon Valley understood this before the research proved it. Google's famous "20% time" and similar policies were more thsn just about employee satisfaction. Companies discovered that structured boredom produces more valuable innovations than structured brainstorming sessions. Engineers who spend one day per week on self directed, unstimulated projects generate patents at higher rates than those focused solely on assigned tasks. The pharmaceutical industry treats boredom as a symptom of depression and prescribes stimulants to eliminate unstimulated mental states. Meanwhile, the same industry struggles with declining innovation rates in drug discovery. The connection isn't coincidental. Educational systems double down on the same mistake. Schools pack schedules with back to back classes, eliminate recess, and assign homework that fills every unstimulated moment. Then educators wonder why creative problem solving scores have declined for three consecutive decades. Students arrive at universities neurologically unprepared for the kind of open ended thinking that produces original research. The economic implications compound across generations. Industries that depend on creative problem solving hire workforces trained to avoid the mental states where creative problem solving occurs. Then they implement productivity tools and collaborative platforms that further fragment attention and eliminate the sustained boredom where breakthrough solutions develop. Zomorodi's experiment succeeded because participants actively resisted their conditioning. They scheduled specific periods of deliberate understimulation. They sat without phones, music, or conversation. They allowed their minds to wander without redirecting attention to productive tasks. Within days, their brains remembered how to complete the background processing that constant stimulation had been interrupting. The 41% increase in creative output came from creating better conditions for creativity to flow naturally, supported by replacing unhelpful habits with more supportive ones. Most people reading this will agree intellectually but continue reaching for stimulation the moment boredom threatens. The addiction to constant input runs deeper than conscious decision making. Your brain interprets unstimulated time as a threat that requires immediate correction. But those breakthrough insights you've been waiting for are sitting in your default mode network right now. They've been trying to surface for weeks, maybe months. Every time you reach for external stimulation, you're interrupting the neural process that would deliver them. Your next original idea is one boring afternoon away. The only question is whether you'll give it the unstimulated space it needs to emerge.
0:55

20,000 people deliberately introduced boredom into their lives and generated 41% more breakthrough insights within one week. Yes, Dr. Manoush Zomorodi demonstrated what neuroscientists long suspected: "deliberate boredom boosts creative output and strengthens the brain’s capacity for original thinking." In that study, 20,000 participants added periods of unstimulated time to their routines, and experienced 41% more creative breakthrough moments within seven days. Your default mode network operates like a background processor that only runs when conscious attention stops demanding resources. During unstimulated moments, this network begins cross referencing every memory, skill, and experience you've accumulated, hunting for patterns your focused mind missed. The insights we call "creativity" are actually sophisticated pattern recognition happening below conscious awareness. Modern humans have accidentally trained themselves to interrupt this process every time it begins. The average person checks their phone 96 times per day. Every notification, every scroll, every background podcast cuts the neural pattern matching short before it completes. We've created a civilization where the mental state required for original thinking gets treated like an emergency that needs immediate correction. Watch people in waiting rooms, elevators, or checkout lines. The moment external stimulation drops below a certain threshold, hands automatically reach for phones. The discomfort they're avoiding is literally their brain attempting to do the background processing that produces breakthrough insights. Evolutionary biologists argue boredom developed as a survival mechanism. Animals that could sit unstimulated and let their minds wander were more likely to notice environmental changes, recognize new food sources, and develop innovative hunting strategies. Boredom forced our ancestors into the mental state where novel solutions emerge from existing knowledge. We've pathologized our most important cognitive function. The corporate world talks endlessly about innovation while designing work environments that make innovation neurologically impossible. Open offices with constant interruption. Back to back meetings with no processing time. Performance metrics that reward immediate output over deep thinking. Then companies spend millions on creativity consultants and innovation workshops, trying to artificially recreate what the human brain does naturally during sustained boredom. Participants in Zomorodi’s study generated more ideas and also described a welcome shift: during quiet, unstimulated moments, answers to long-running challenges often came into clear focus. With fewer distractions, their brains kept working on the underlying patterns and had the space to bring that recognition to completion. The quality gap between stimulated and unstimulated thinking becomes stark when you map it against major discoveries. The pattern repeats across every domain: breakthrough insights emerge during mental downtime, not during intense focus. Modern neuroscience explains why. The default mode network draws connections between brain regions that don't communicate during focused attention. Areas responsible for memory, emotion, sensory processing, and abstract thinking create novel combinations only when executive control relaxes. Constant stimulation keeps executive control active, blocking the cross domain communication that generates original ideas. Silicon Valley understood this before the research proved it. Google's famous "20% time" and similar policies were more thsn just about employee satisfaction. Companies discovered that structured boredom produces more valuable innovations than structured brainstorming sessions. Engineers who spend one day per week on self directed, unstimulated projects generate patents at higher rates than those focused solely on assigned tasks. The pharmaceutical industry treats boredom as a symptom of depression and prescribes stimulants to eliminate unstimulated mental states. Meanwhile, the same industry struggles with declining innovation rates in drug discovery. The connection isn't coincidental. Educational systems double down on the same mistake. Schools pack schedules with back to back classes, eliminate recess, and assign homework that fills every unstimulated moment. Then educators wonder why creative problem solving scores have declined for three consecutive decades. Students arrive at universities neurologically unprepared for the kind of open ended thinking that produces original research. The economic implications compound across generations. Industries that depend on creative problem solving hire workforces trained to avoid the mental states where creative problem solving occurs. Then they implement productivity tools and collaborative platforms that further fragment attention and eliminate the sustained boredom where breakthrough solutions develop. Zomorodi's experiment succeeded because participants actively resisted their conditioning. They scheduled specific periods of deliberate understimulation. They sat without phones, music, or conversation. They allowed their minds to wander without redirecting attention to productive tasks. Within days, their brains remembered how to complete the background processing that constant stimulation had been interrupting. The 41% increase in creative output came from creating better conditions for creativity to flow naturally, supported by replacing unhelpful habits with more supportive ones. Most people reading this will agree intellectually but continue reaching for stimulation the moment boredom threatens. The addiction to constant input runs deeper than conscious decision making. Your brain interprets unstimulated time as a threat that requires immediate correction. But those breakthrough insights you've been waiting for are sitting in your default mode network right now. They've been trying to surface for weeks, maybe months. Every time you reach for external stimulation, you're interrupting the neural process that would deliver them. Your next original idea is one boring afternoon away. The only question is whether you'll give it the unstimulated space it needs to emerge.

The Curious Tales

44,857 просмотров • 4 месяцев назад

What’s Left Before InterPredict Mainnet? 🟣🚀 InterPredict is getting closer to Mainnet but we are not rushing the process. ⏳ A successful Mainnet launch is about more than reaching a date on the calendar. It is about ensuring that the protocol, infrastructure and user experience are ready to operate reliably in a production environment. 🏗️🔐 Several important technical milestones have already been completed, while the remaining work is focused on integration, refinement and final preparation. 🛠️✅ ✅ Completed Milestones 1. Smart Contract Development and Testing 📜🔍 The smart contracts have been developed and tested, establishing the core on-chain foundation of the InterPredict protocol. This work is essential for ensuring that the protocol’s key functions operate as intended and can support the next stage of development. ⚙️⛓️ 2. Backend Deployment 🖥️🚀 The new backend infrastructure has been successfully deployed and is now running in a production environment. This provides the services required to support the platform and enables the frontend to communicate with the systems powering InterPredict. 🔗📡 3. Transaction and Activity Tracking 📊👀 Users can now clearly view the results of their interactions and monitor relevant activity within the platform. Improved visibility helps users better understand their transactions, actions and participation across the platform. ✅📈 4. Reliable Market Indexing 🗂️⛓️ Blockchain activity is being indexed consistently and reflected accurately within the application. Reliable indexing is important because it ensures that on-chain events, market updates and other protocol activity are displayed correctly for users. 🔄📍 5. Faster Data Synchronisation ⚡📡 The platform’s data synchronisation has been improved so that market states, votes, activities and other protocol information can be reflected in the dApp more quickly. Faster synchronisation creates a smoother and more responsive experience between blockchain activity and the information displayed in the application. 🚀📱 ⏳ Currently in Progress 1. Frontend and Backend Integration 🔌🖥️ The new frontend experience is being connected to the backend services so that both layers work together smoothly and reliably. This stage ensures that user actions, platform data and backend processes are properly connected across the entire application. 🔗✅ 2. User Experience Improvements 🎨📱 The Closed Beta provided valuable feedback and highlighted areas where the platform can become easier and more intuitive to use. The team is continuing to improve: • Navigation 🧭 • Mobile usability 📱 • Loading states ⏳ • Error handling ⚠️ • Market interaction flows 📊 • Overall platform usability ✅ These improvements are designed to make InterPredict clearer, faster and more accessible for both new and existing users. 🙌 3. Security and Reliability 🔐🛡️ The infrastructure and protocol are being reviewed and strengthened to ensure they are prepared for production use. This includes improving system stability, reviewing critical components and making sure the platform can operate reliably as activity and user participation increase. 🏗️📈 Security and reliability are not final checks to be rushed. They are essential parts of building a platform users can trust. 🤝 4. Mainnet Readiness 🚦🚀 The final stage is bringing all the moving parts together and testing the complete system as one connected platform. This includes the: → Smart contracts 📜 → Backend infrastructure 🖥️ → Frontend experience 🎨 → Market indexing 🗂️ → Data synchronisation 🔄 → Transaction tracking 📊 → Security systems 🔐 Each component must work correctly on its own and together with every other part of the protocol. ⚙️✅ Building for the Long Term 🏗️🌍 Mainnet is not simply a launch date. It is a major milestone that represents the beginning of the next phase for InterPredict. 🟣 The goal is not to launch as quickly as possible. The goal is to launch with a strong foundation that gives the team confidence to continue building, improving and scaling the platform after launch. 🚀📈 The Closed Beta showed us where improvements were needed. V2 is where those lessons are being applied. 💡🔧 There is still work to complete—but every step brings InterPredict closer to a more reliable, efficient and user-friendly platform. ⏳➡️✅ The Next Big Step 🟣🚀 The main technical foundations are now in place. The remaining focus is on integration, user experience, security, reliability and final Mainnet preparation. 🔐⚙️ We are not rushing to launch. We are making sure InterPredict is ready to launch properly. Stay updated and follow the journey towards Mainnet. 🟣🌐🚀 Follow InterPredict 📣 🔗 Follow InterPredict: InterPredict 📲 Join the Telegram community: InterLink Labs 👤 + 🌐 InterPredict InterLink Foundation KV Reina | InterLink Labs Mira #InterPredict #ITP #InterLink #ITLG #ITL #PredictionMarkets #ITL #ITLG #Web3 #Blockchain #dApp #Mainnet #Tokenomics
0:22

What’s Left Before InterPredict Mainnet? 🟣🚀 InterPredict is getting closer to Mainnet but we are not rushing the process. ⏳ A successful Mainnet launch is about more than reaching a date on the calendar. It is about ensuring that the protocol, infrastructure and user experience are ready to operate reliably in a production environment. 🏗️🔐 Several important technical milestones have already been completed, while the remaining work is focused on integration, refinement and final preparation. 🛠️✅ ✅ Completed Milestones 1. Smart Contract Development and Testing 📜🔍 The smart contracts have been developed and tested, establishing the core on-chain foundation of the InterPredict protocol. This work is essential for ensuring that the protocol’s key functions operate as intended and can support the next stage of development. ⚙️⛓️ 2. Backend Deployment 🖥️🚀 The new backend infrastructure has been successfully deployed and is now running in a production environment. This provides the services required to support the platform and enables the frontend to communicate with the systems powering InterPredict. 🔗📡 3. Transaction and Activity Tracking 📊👀 Users can now clearly view the results of their interactions and monitor relevant activity within the platform. Improved visibility helps users better understand their transactions, actions and participation across the platform. ✅📈 4. Reliable Market Indexing 🗂️⛓️ Blockchain activity is being indexed consistently and reflected accurately within the application. Reliable indexing is important because it ensures that on-chain events, market updates and other protocol activity are displayed correctly for users. 🔄📍 5. Faster Data Synchronisation ⚡📡 The platform’s data synchronisation has been improved so that market states, votes, activities and other protocol information can be reflected in the dApp more quickly. Faster synchronisation creates a smoother and more responsive experience between blockchain activity and the information displayed in the application. 🚀📱 ⏳ Currently in Progress 1. Frontend and Backend Integration 🔌🖥️ The new frontend experience is being connected to the backend services so that both layers work together smoothly and reliably. This stage ensures that user actions, platform data and backend processes are properly connected across the entire application. 🔗✅ 2. User Experience Improvements 🎨📱 The Closed Beta provided valuable feedback and highlighted areas where the platform can become easier and more intuitive to use. The team is continuing to improve: • Navigation 🧭 • Mobile usability 📱 • Loading states ⏳ • Error handling ⚠️ • Market interaction flows 📊 • Overall platform usability ✅ These improvements are designed to make InterPredict clearer, faster and more accessible for both new and existing users. 🙌 3. Security and Reliability 🔐🛡️ The infrastructure and protocol are being reviewed and strengthened to ensure they are prepared for production use. This includes improving system stability, reviewing critical components and making sure the platform can operate reliably as activity and user participation increase. 🏗️📈 Security and reliability are not final checks to be rushed. They are essential parts of building a platform users can trust. 🤝 4. Mainnet Readiness 🚦🚀 The final stage is bringing all the moving parts together and testing the complete system as one connected platform. This includes the: → Smart contracts 📜 → Backend infrastructure 🖥️ → Frontend experience 🎨 → Market indexing 🗂️ → Data synchronisation 🔄 → Transaction tracking 📊 → Security systems 🔐 Each component must work correctly on its own and together with every other part of the protocol. ⚙️✅ Building for the Long Term 🏗️🌍 Mainnet is not simply a launch date. It is a major milestone that represents the beginning of the next phase for InterPredict. 🟣 The goal is not to launch as quickly as possible. The goal is to launch with a strong foundation that gives the team confidence to continue building, improving and scaling the platform after launch. 🚀📈 The Closed Beta showed us where improvements were needed. V2 is where those lessons are being applied. 💡🔧 There is still work to complete—but every step brings InterPredict closer to a more reliable, efficient and user-friendly platform. ⏳➡️✅ The Next Big Step 🟣🚀 The main technical foundations are now in place. The remaining focus is on integration, user experience, security, reliability and final Mainnet preparation. 🔐⚙️ We are not rushing to launch. We are making sure InterPredict is ready to launch properly. Stay updated and follow the journey towards Mainnet. 🟣🌐🚀 Follow InterPredict 📣 🔗 Follow InterPredict: InterPredict 📲 Join the Telegram community: InterLink Labs 👤 + 🌐 InterPredict InterLink Foundation KV Reina | InterLink Labs Mira #InterPredict #ITP #InterLink #ITLG #ITL #PredictionMarkets #ITL #ITLG #Web3 #Blockchain #dApp #Mainnet #Tokenomics

Tekkaus® | InterLink Global Leader • MOD • OG

100,095 просмотров • 7 дней назад