正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

I built the LLM interface I wished existed. interface0 is for power users: cross-provider memory & chat, multi-model synthesis, sharing & team features, granular context engineering, template prompts, forking, prompt enhancing, & more Here's a demo—see 🧵 for the rest

Andy Bromberg

15,005 subscribers

24,917 次观看 • 11 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

I just created a demo website for a super advanced cross-framework library for smooth LLM text streaming effects & also text-staggers.

I just created a demo website for a super advanced cross-framework library for smooth LLM text streaming effects & also text-staggers.

Sam Denty

31,798 次观看 • 1 年前

CONTEXT ENGINEERING > PROMPT ENGINEERING Everyone is obsessed with writing better prompts. The next generation of AI builders is focused on context engineering instead. • Prompt engineering shapes the question. Context engineering shapes everything the AI sees. • Great prompts can't save an agent missing critical context, memory, or tools. • AI failures often come from missing information, not weak models. • Context engineering combines prompts, memory, RAG, state management, and tool access into one system. What powers effective AI agents? → Memory: Remembers preferences, past interactions, and ongoing tasks. → State Management: Tracks progress across multi-step workflows. → RAG: Retrieves only the most relevant information when needed. → Tools: Connects AI to APIs, databases, code execution, and real-world actions. → Dynamic Prompts: Enriches instructions with live context at runtime. The key insight: Prompt Engineering = Better Questions Context Engineering = Better Systems The future of AI isn't building smarter prompts. It's building smarter environments for AI to think, remember, retrieve, and act.

CONTEXT ENGINEERING > PROMPT ENGINEERING Everyone is obsessed with writing better prompts. The next generation of AI builders is focused on context engineering instead. • Prompt engineering shapes the question. Context engineering shapes everything the AI sees. • Great prompts can't save an agent missing critical context, memory, or tools. • AI failures often come from missing information, not weak models. • Context engineering combines prompts, memory, RAG, state management, and tool access into one system. What powers effective AI agents? → Memory: Remembers preferences, past interactions, and ongoing tasks. → State Management: Tracks progress across multi-step workflows. → RAG: Retrieves only the most relevant information when needed. → Tools: Connects AI to APIs, databases, code execution, and real-world actions. → Dynamic Prompts: Enriches instructions with live context at runtime. The key insight: Prompt Engineering = Better Questions Context Engineering = Better Systems The future of AI isn't building smarter prompts. It's building smarter environments for AI to think, remember, retrieve, and act.

Dami-Defi

10,107 次观看 • 17 天前

Cross-chain execution is broken by bridging, RPC & interface inconsistencies! Console's Multi-Chain View is here to improve it⛓️ 🔗 One address across chains 📊 A unified dashboard for asset & position overviews 🔒 Siloed risk management & more! Release 1 Overview below🧵

Cross-chain execution is broken by bridging, RPC & interface inconsistencies! Console's Multi-Chain View is here to improve it⛓️ 🔗 One address across chains 📊 A unified dashboard for asset & position overviews 🔒 Siloed risk management & more! Release 1 Overview below🧵

Brahma

20,770 次观看 • 2 年前

NEW: Universal PDF support!⚡️📄 OpenRouter now supports PDF processing for every LLM, including PDFs with images. Multi-model demo & details below:

NEW: Universal PDF support!⚡️📄 OpenRouter now supports PDF processing for every LLM, including PDFs with images. Multi-model demo & details below:

OpenRouter

98,647 次观看 • 1 年前

Introducing the most advanced open-source chat template built on top of AI SDK. → Agents (Orchestration, handoffs & context guardrails) → Artifacts (Canvas, Charts) → Rate limits (Messages, tool permissions) Link ⬇️🧵

Introducing the most advanced open-source chat template built on top of AI SDK. → Agents (Orchestration, handoffs & context guardrails) → Artifacts (Canvas, Charts) → Rate limits (Messages, tool permissions) Link ⬇️🧵

Pontus Abrahamsson — oss/acc

70,823 次观看 • 8 个月前

I had a great time chatting with three of Anthropic's top prompt engineers: Amanda Askell, Zack Witten, and David Hershey. We covered a few topics like: - what makes a good prompt engineer - practical tips for writing better prompts - what's happening inside an LLM - jailbreaks - the future of prompt engineering - and more If you want to understand how we think about prompt engineering, this may be the best resource out there. Here's the entire one hour and sixteen minutes of our conversation. Enjoy!

I had a great time chatting with three of Anthropic's top prompt engineers: Amanda Askell, Zack Witten, and David Hershey. We covered a few topics like: - what makes a good prompt engineer - practical tips for writing better prompts - what's happening inside an LLM - jailbreaks - the future of prompt engineering - and more If you want to understand how we think about prompt engineering, this may be the best resource out there. Here's the entire one hour and sixteen minutes of our conversation. Enjoy!

Alex Albert

333,662 次观看 • 1 年前

Prompt engineering is hard. That's why we've been adding tons of features to the Anthropic Console to make the entire process easier for devs. Our goal is to cut the time you spend working on prompts by >90%. Here's a quick walkthrough:

Prompt engineering is hard. That's why we've been adding tons of features to the Anthropic Console to make the entire process easier for devs. Our goal is to cut the time you spend working on prompts by >90%. Here's a quick walkthrough:

Alex Albert

122,223 次观看 • 1 年前

🔄 Introducing #MiniFreak Update 3.0: unlock the full potential of granular synthesis with 8 new engines, granular-focused samples and an expanded factory bank. Available for #FREE for MiniFreak hardware and software users. Learn More →

🔄 Introducing #MiniFreak Update 3.0: unlock the full potential of granular synthesis with 8 new engines, granular-focused samples and an expanded factory bank. Available for #FREE for MiniFreak hardware and software users. Learn More →

Arturia

11,789 次观看 • 1 年前

Today we’re launching Synth LLM for Traders on Polymarket Limitless Hyperliquid Deribit and more This is the first ever LLM-native interface for turning live Monte Carlo forecasts into custom statistics, charts & example trades QT for a chance to win Pro access

Today we’re launching Synth LLM for Traders on Polymarket Limitless Hyperliquid Deribit and more This is the first ever LLM-native interface for turning live Monte Carlo forecasts into custom statistics, charts & example trades QT for a chance to win Pro access

Synthdata

49,026 次观看 • 1 个月前

Here's the anim bible I made for the Dragon Ball sequence in The Synthesis. It was so fun collecting prod art & references to analyse. The animators did a great job staying true to that early DB style and working with the amazing char sheets & poses from the design team. #twwwog

Here's the anim bible I made for the Dragon Ball sequence in The Synthesis. It was so fun collecting prod art & references to analyse. The animators did a great job staying true to that early DB style and working with the amazing char sheets & poses from the design team. #twwwog

Freddie

264,806 次观看 • 6 个月前

Crunched (Crunched) is the first Excel AI built by and for Excel power users - tailored for consulting and finance workflows. The team has 10k+ hrs in Excel. Crunched is live with firms across Europe & US, with users report being >2x faster on modeling tasks.

Crunched (Crunched) is the first Excel AI built by and for Excel power users - tailored for consulting and finance workflows. The team has 10k+ hrs in Excel. Crunched is live with firms across Europe & US, with users report being >2x faster on modeling tasks.

Y Combinator

2,038,527 次观看 • 8 个月前

Flux.2 Max is out NOW 💥 UNLIMITED for 1 month for Premium+ and Pro users The highest-quality and most consistent FLUX.2 model Built for maximum prompt adherence, multi-reference consistency, and production-ready editing at blazing speed Available for all users

Flux.2 Max is out NOW 💥 UNLIMITED for 1 month for Premium+ and Pro users The highest-quality and most consistent FLUX.2 model Built for maximum prompt adherence, multi-reference consistency, and production-ready editing at blazing speed Available for all users

Magnific

24,177 次观看 • 6 个月前

I dropped 2 more prompting guides for animation and typography This has a prompt builder that is insanely useful. Lots of types of animations, timing, techniques, examples & recommended prompts. My first guide was shockingly popular drawing 3k users in 24h. So thank you!

I dropped 2 more prompting guides for animation and typography This has a prompt builder that is insanely useful. Lots of types of animations, timing, techniques, examples & recommended prompts. My first guide was shockingly popular drawing 3k users in 24h. So thank you!

Meng To

30,695 次观看 • 1 年前

Is this a 3D model? 2 minutes, one shot prompt after 5 prior prompts for context. Look it's learning and evolving...

Is this a 3D model? 2 minutes, one shot prompt after 5 prior prompts for context. Look it's learning and evolving...

Andrew Rulnick

27,916 次观看 • 6 个月前

🎨 Introducing Prompt Canvas — a novel UX for prompt engineering Building LLM applications requires new and dedicated tools for prompt engineering. With Prompt Canvas in LangSmith, you can: • Collaborate with an AI agent to draft, refine, and edit your prompts • Define custom quick actions to standardize prompting strategies used across the org ✍️ Learn more: ➡️ Try it out:

🎨 Introducing Prompt Canvas — a novel UX for prompt engineering Building LLM applications requires new and dedicated tools for prompt engineering. With Prompt Canvas in LangSmith, you can: • Collaborate with an AI agent to draft, refine, and edit your prompts • Define custom quick actions to standardize prompting strategies used across the org ✍️ Learn more: ➡️ Try it out:

LangChain

43,733 次观看 • 1 年前

Ara is the self-driving IDE. Instead of waiting for your next prompt, it ships features for you. Ara maintains self-improving memory across the app, Claude, and Codex. Congrats on the launch, Adi & Sven Myhre!

Ara is the self-driving IDE. Instead of waiting for your next prompt, it ships features for you. Ara maintains self-improving memory across the app, Claude, and Codex. Congrats on the launch, Adi & Sven Myhre!

Y Combinator

38,750 次观看 • 1 个月前

A 10x workflow for technical PMs & EMs: Linear inbox 🤝 code agents (Codegen ) The "inbox" is a natural queueing interface for reviewing agent outputs. Here's how to use the inbox to multi-task and effectively manage teams of agents 👇

A 10x workflow for technical PMs & EMs: Linear inbox 🤝 code agents (Codegen ) The "inbox" is a natural queueing interface for reviewing agent outputs. Here's how to use the inbox to multi-task and effectively manage teams of agents 👇

Jay Hack

46,159 次观看 • 1 年前

I built a tool to create, animate & export pixel art using Figma & now it’s on a billboard in Singapore 🫨 It all started out as a joke & after 384 prompts in Figma Make….I DID IT Thanks Figma for all the love & for featuring it. It’s been my highlight of this year.

I built a tool to create, animate & export pixel art using Figma & now it’s on a billboard in Singapore 🫨 It all started out as a joke & after 384 prompts in Figma Make….I DID IT Thanks Figma for all the love & for featuring it. It’s been my highlight of this year.

Ayaneshu

23,195 次观看 • 8 个月前

Since it got a bit of attention, I'm sharing the Seedance 2.0 prompts. It's not really the kind of prompt system I want yet, I'm working on a better method that performs more consistently. I'll share that with details soon. Also the previs prompt with gpt image 2 isn't ready yet. The one here was just loosely put together in chat with rough directions. Also working on a proper template for that. You can find the Seedance 2.0 prompts in the replies.

Since it got a bit of attention, I'm sharing the Seedance 2.0 prompts. It's not really the kind of prompt system I want yet, I'm working on a better method that performs more consistently. I'll share that with details soon. Also the previs prompt with gpt image 2 isn't ready yet. The one here was just loosely put together in chat with rough directions. Also working on a proper template for that. You can find the Seedance 2.0 prompts in the replies.

Kōda

44,640 次观看 • 2 个月前

Game on! 😎 Dropped a new demo, #SuperDash, a side scrolling multiplatform game built with Flutter & Flame using the new Endless Runner template. Can you make it on the leaderboard? Download the app for iOS or Android & play on desktop browsers here →

Game on! 😎 Dropped a new demo, #SuperDash, a side scrolling multiplatform game built with Flutter & Flame using the new Endless Runner template. Can you make it on the leaderboard? Download the app for iOS or Android & play on desktop browsers here →

Flutter

96,134 次观看 • 2 年前