Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

I post-trained Qwen3-Coder to fix bugs using an actual debugger. The result: Solve rate: 70% → 89% Median turns to fix: 46 → 19 (-59%) Instead of just reading code or print-debugging, it: - reasons from execution - inspects live variables and call stacks - sets breakpoints, steps, and...

moofeez's profile picture

mufeez

1,766 subscribers

125,706 görüntüleme • 3 ay önce •via X (Twitter)

EğitimSağlık & İyilikBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

here's me using debug mode to fix a small bug in an swift app i just built issue was the initial characters were cut off when typing it out, so i had cursor 1. instrument the code 2. ask me to reproduce the issue 3. read the debug logs 4. implement the fix 5. ask me to reproduce to verify the fix using runtime context, cursor managed to fix it first try! team is using this very frequently, and highly recommend /debug mode for gnarly bugs
0:57

here's me using debug mode to fix a small bug in an swift app i just built issue was the initial characters were cut off when typing it out, so i had cursor 1. instrument the code 2. ask me to reproduce the issue 3. read the debug logs 4. implement the fix 5. ask me to reproduce to verify the fix using runtime context, cursor managed to fix it first try! team is using this very frequently, and highly recommend /debug mode for gnarly bugs

eric zakariasson

15,224 görüntüleme • 2 ay önce

I built an open source data analyst agent! Upload any CSV, ask a question, and get it answered with statistics or a nice chart. Launching in 24 hours. 100% free & open source. Under the hood, here's how it works: 1. User uploads a CSV and asks a question. 2. The app uses Together Code Interpreter to spin up a VM and uploads the CSV onto it. 3. I have an LLM (Qwen 3 Coder) write code to interpret the CSV using `pandas`, then solve the question the user asked. 4. Together Code Interpreter runs the code in a secure environment & returns a result. These results can be text (some kind of stats analysis) or a chart.
0:34

I built an open source data analyst agent! Upload any CSV, ask a question, and get it answered with statistics or a nice chart. Launching in 24 hours. 100% free & open source. Under the hood, here's how it works: 1. User uploads a CSV and asks a question. 2. The app uses Together Code Interpreter to spin up a VM and uploads the CSV onto it. 3. I have an LLM (Qwen 3 Coder) write code to interpret the CSV using `pandas`, then solve the question the user asked. 4. Together Code Interpreter runs the code in a secure environment & returns a result. These results can be text (some kind of stats analysis) or a chart.

Hassan

27,086 görüntüleme • 10 ay önce

Between myself and a lazy WhatsApp hacker. Guys beware of WhatsApp hackers, they always pick up your numbers from WhatsApp groups, call you while they’re registering your number on another device. All they need is the authentication code sent to you, They’ll call you and ask for it while relating an old format of meeting fix up. Do Not give them Numbers from your Authenticator App or SMS !!!
0:30

Between myself and a lazy WhatsApp hacker. Guys beware of WhatsApp hackers, they always pick up your numbers from WhatsApp groups, call you while they’re registering your number on another device. All they need is the authentication code sent to you, They’ll call you and ask for it while relating an old format of meeting fix up. Do Not give them Numbers from your Authenticator App or SMS !!!

Engr Yasir MNSE 🏗

315,501 görüntüleme • 2 yıl önce

Turn any paper into running code. Just swap arxiv → autoarxiv in the paper url. That hands the paper to an AI agent from alphaXiv. It reads the abstract, the claims, and the linked GitHub repo, then clones the codebase and works through the usual setup pain like dependencies, broken paths, environment config, and hardware assumptions. From there it designs a minimal reproduction. That means a smaller model, fewer steps, and a single GPU instead of a cluster, scaled down just enough to test whether the headline claim holds. The whole run is live and fully logged. Loss curves, metrics, and training progress are all observable as it happens. What comes back is a clean signal on whether the minimal run matches the paper's reported result, plus an estimate of what a full replication would cost in compute and time. A lot of research code dies in setup before anyone verifies a single number. This moves reproduction from a weekend of debugging to a url change. Pick a paper and try it now. video credits: alphaXiv
0:44

Turn any paper into running code. Just swap arxiv → autoarxiv in the paper url. That hands the paper to an AI agent from alphaXiv. It reads the abstract, the claims, and the linked GitHub repo, then clones the codebase and works through the usual setup pain like dependencies, broken paths, environment config, and hardware assumptions. From there it designs a minimal reproduction. That means a smaller model, fewer steps, and a single GPU instead of a cluster, scaled down just enough to test whether the headline claim holds. The whole run is live and fully logged. Loss curves, metrics, and training progress are all observable as it happens. What comes back is a clean signal on whether the minimal run matches the paper's reported result, plus an estimate of what a full replication would cost in compute and time. A lot of research code dies in setup before anyone verifies a single number. This moves reproduction from a weekend of debugging to a url change. Pick a paper and try it now. video credits: alphaXiv

Akshay 🚀

45,720 görüntüleme • 1 ay önce

Day 7: OpenClaw 🦞 The ultimate lean way to handle OpenClaw I just fired Claude, Cursor, Gemini, and every other “Pro” AI tool today. Instead, I paid $50 for MiniMax M2.5 and routed it directly into OpenClaw and Claude Code. The result? My company now has a 24/7 autonomous workforce that never sleeps and costs less than my old setup. I used to optimize for tokens a day ago. Now I optimize for execution. I’m 25. This isn’t a hobby anymore. Things are getting real. It’s an actual company now!
0:49

Day 7: OpenClaw 🦞 The ultimate lean way to handle OpenClaw I just fired Claude, Cursor, Gemini, and every other “Pro” AI tool today. Instead, I paid $50 for MiniMax M2.5 and routed it directly into OpenClaw and Claude Code. The result? My company now has a 24/7 autonomous workforce that never sleeps and costs less than my old setup. I used to optimize for tokens a day ago. Now I optimize for execution. I’m 25. This isn’t a hobby anymore. Things are getting real. It’s an actual company now!

Ziwen

44,532 görüntüleme • 5 ay önce

Think of it as the Shopify of Claude Code, but for agents, commands, and MCPs 🚀 Pick what you need, “add to cart,” and… it’s 100% FREE. Just copy the command, paste it in your terminal, and instantly get the perfect Claude Code stack for your project. Built as an open-source project so the community can spin up, share, and install Claude Code stacks in seconds, no setup headaches, no paywalls. Here’s the video showing how I built this post… and yes, if you share the command, anyone can clone the exact same stack you’re using. Enjoy, share, and help others build faster with Claude Code ✨
0:59

Think of it as the Shopify of Claude Code, but for agents, commands, and MCPs 🚀 Pick what you need, “add to cart,” and… it’s 100% FREE. Just copy the command, paste it in your terminal, and instantly get the perfect Claude Code stack for your project. Built as an open-source project so the community can spin up, share, and install Claude Code stacks in seconds, no setup headaches, no paywalls. Here’s the video showing how I built this post… and yes, if you share the command, anyone can clone the exact same stack you’re using. Enjoy, share, and help others build faster with Claude Code ✨

Daniel San

124,913 görüntüleme • 11 ay önce

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next
1:30

✨ A dream I had finally came true: I can now chat directly with my sites to build any feature or fix any bug just via Telegram I've been playing with OpenClaw for 3 weeks now and it's great but I was always too scared to run it on any production server And I was right a bit as Marc Köhlbrugge was able to hack it by social engineering and acting as if it was me, and with enough tries it believed him, and was able to modify the server, change SSH keys etc. of course I had it isolated properly on its own VPS and it didn't touch anything sensitive (as it should!) Marc then reported that bug to Peter Steinberger 🦞 who patched it fast But I wanted to try something more basic and simple, and I think maybe more secure: to just connect Claude Code on my server to Telegram which would be hard locked to only messages from me So I installed claude-code-telegram by Richard Atkinson on the server and run it as a system daemon and it works really well The cool thing is that I was already using Telegram for server errors like this: > Photo AI - ❌ Random credits giveaway failed (Attempt 30/30) with an exception: SQLSTATE[HY000]: General error: 5 database is locked So now I can just reply, "Ok fix this", and Claude Code on the server in production will try (and probably succeed) in fixing it In the video below I asked it to make show [🌳 Parks ] on the map by default on load, it did that, then I reloaded the page and it instantly worked One thing it still needs is sending actual messages while it's doing stuff which OpenClaw does really well, it's annoying to just wait while it says "Working..." but that's probably next

@levelsio

642,033 görüntüleme • 5 ay önce

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.
1:15

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.

Rohan Paul

33,431 görüntüleme • 5 ay önce

Anybody who knows me knows how passionate I am about education. My dad was a pediatrician and I was on track to become an early childhood educator. We have a national education crisis in America. Both parties have gotten sidetracked on the education metrics that matter by engaging in culture wars – whether it be bathroom access or what topics we can teach in schools. We need to nationalize the 'Mississippi Miracle' and 'Alabama on Math' models to improve our kids’ reading and math scores. I refer to this as TART: ✅Technology (to make kids ready for AI disruptions) ✅Attendance (to tackle the significant absentee rate post-COVID) ✅Reading (using the Mississippi Miracle doctrine) ✅Truth (to ensure parents know their kids' progress based on national standards) I spoke with Megyn Kelly about where we have gone wrong in education and what we can do to fix it.
2:19

Anybody who knows me knows how passionate I am about education. My dad was a pediatrician and I was on track to become an early childhood educator. We have a national education crisis in America. Both parties have gotten sidetracked on the education metrics that matter by engaging in culture wars – whether it be bathroom access or what topics we can teach in schools. We need to nationalize the 'Mississippi Miracle' and 'Alabama on Math' models to improve our kids’ reading and math scores. I refer to this as TART: ✅Technology (to make kids ready for AI disruptions) ✅Attendance (to tackle the significant absentee rate post-COVID) ✅Reading (using the Mississippi Miracle doctrine) ✅Truth (to ensure parents know their kids' progress based on national standards) I spoke with Megyn Kelly about where we have gone wrong in education and what we can do to fix it.

Rahm Emanuel

34,227 görüntüleme • 10 ay önce

Roy Lee got kicked out of Columbia University for posting a video of himself cheating an Amazon interview using his software and raised $5,000,000 in 24 hours “I record myself using interview coder to cheat on literally the entire process I record it I post it online and it starts going viral” “an Amazon executive sees the video they’re pissed and they send Columbia a letter saying your kid just cheated on our entire interview process posted online now he’s selling this software you need to expel him or we’re never gonna hire from Columbia anymore” “by the time I do that I’m posting everything on Twitter and there’s so many VCs in the valley that I raised like $5 million in like 24 hours”
0:46

Roy Lee got kicked out of Columbia University for posting a video of himself cheating an Amazon interview using his software and raised $5,000,000 in 24 hours “I record myself using interview coder to cheat on literally the entire process I record it I post it online and it starts going viral” “an Amazon executive sees the video they’re pissed and they send Columbia a letter saying your kid just cheated on our entire interview process posted online now he’s selling this software you need to expel him or we’re never gonna hire from Columbia anymore” “by the time I do that I’m posting everything on Twitter and there’s so many VCs in the valley that I raised like $5 million in like 24 hours”

Third

1,394,136 görüntüleme • 3 ay önce

8 rules to improve your AI coding agent. All of these rules work with Claude Code, Cursor, VS Code, and with most programming languages. Automating these rules will 10x the code quality and security produced by your AI coding agents. 1. Dependency checks - Prevent your agent from suggesting insecure libraries based on outdated training data. 2. Secret exposure - Auto-fix the use of hardcoded credentials introduced by your coding agent. 3. File and function size - Automatically refactor any files or functions that exceed a reasonable length. 4. Complexity and parameter limits - Simplify overly complex code written by the agent. 5. SQL Injection - Auto-fix all database interactions with unsanitized user input. 6. Unused variables and imports - Detect and remove dead code. 7. Detect invisible unicode characters in AI rules files - Remove zero-width spaces, direction overrides, and other invisible characters that can hide malicious behavior. 8. Insecure OpenAI API usage - Enforce use of secure OpenAI endpoints, proper authentication, and context isolation Here is how you can automate this: Install the Codacy extension. This will give you access to a CLI for local scanning and an MCP server for agent communication. From here on out, every time you need to generate some code: 1. Your agent will write the code 2. It will then call Codacy's CLI to check it 3. It will find any issues in real time 4. Your coding agent will fix the issues 5. When the code passes all checks, you are done Level of effort on your side: literally zero! Code quality and security because of this: 100x better! Here is the link to download the extension for your IDE: Thanks to the Codacy team for collaborating with me on this post.
3:50

8 rules to improve your AI coding agent. All of these rules work with Claude Code, Cursor, VS Code, and with most programming languages. Automating these rules will 10x the code quality and security produced by your AI coding agents. 1. Dependency checks - Prevent your agent from suggesting insecure libraries based on outdated training data. 2. Secret exposure - Auto-fix the use of hardcoded credentials introduced by your coding agent. 3. File and function size - Automatically refactor any files or functions that exceed a reasonable length. 4. Complexity and parameter limits - Simplify overly complex code written by the agent. 5. SQL Injection - Auto-fix all database interactions with unsanitized user input. 6. Unused variables and imports - Detect and remove dead code. 7. Detect invisible unicode characters in AI rules files - Remove zero-width spaces, direction overrides, and other invisible characters that can hide malicious behavior. 8. Insecure OpenAI API usage - Enforce use of secure OpenAI endpoints, proper authentication, and context isolation Here is how you can automate this: Install the Codacy extension. This will give you access to a CLI for local scanning and an MCP server for agent communication. From here on out, every time you need to generate some code: 1. Your agent will write the code 2. It will then call Codacy's CLI to check it 3. It will find any issues in real time 4. Your coding agent will fix the issues 5. When the code passes all checks, you are done Level of effort on your side: literally zero! Code quality and security because of this: 100x better! Here is the link to download the extension for your IDE: Thanks to the Codacy team for collaborating with me on this post.

Santiago

49,331 görüntüleme • 9 ay önce

I built a wallet app that sends sBTC using bitcoin addresses instead of Stacks addresses. That's layer 2 sats sent from bitcoin address to bitcoin address in seconds for < $0.01 via the Stacks network: ✅Standard bitcoin addresses ✅Standard sign and broadcast semantics ✅Confirmation in seconds ✅Low fees ✅Self-custody ✅Bitcoin finality While this wallet is a prototype that works only with native Segwit addresses and requires or Leather - Grow your Bitcoin for transaction signing, Bitcoin addresses for sBTC (or all Stacks assets) could be adopted natively by any wallets. It doesn't require any changes to the Stacks core network. This address scheme could even be expanded so that fast, easy and cheap layer 2 BTC transactions could also work with legacy addresses. Here's how it works: Bitcoin legacy and native segwit addresses along with Stacks addresses all encode the so-called "hash160" of the user's public key. This means we can convert these two types of bitcoin addresses into a Stacks address and any Stacks address into either a legacy or native segwit bitcoin address. Using bitcoin addresses instead of Stacks addresses allows us to reuse many of the payment standards and QR code formats that have already been developed for bitcoin. It makes sBTC a true layer 2 bitcoin.
6:33

I built a wallet app that sends sBTC using bitcoin addresses instead of Stacks addresses. That's layer 2 sats sent from bitcoin address to bitcoin address in seconds for < $0.01 via the Stacks network: ✅Standard bitcoin addresses ✅Standard sign and broadcast semantics ✅Confirmation in seconds ✅Low fees ✅Self-custody ✅Bitcoin finality While this wallet is a prototype that works only with native Segwit addresses and requires or Leather - Grow your Bitcoin for transaction signing, Bitcoin addresses for sBTC (or all Stacks assets) could be adopted natively by any wallets. It doesn't require any changes to the Stacks core network. This address scheme could even be expanded so that fast, easy and cheap layer 2 BTC transactions could also work with legacy addresses. Here's how it works: Bitcoin legacy and native segwit addresses along with Stacks addresses all encode the so-called "hash160" of the user's public key. This means we can convert these two types of bitcoin addresses into a Stacks address and any Stacks address into either a legacy or native segwit bitcoin address. Using bitcoin addresses instead of Stacks addresses allows us to reuse many of the payment standards and QR code formats that have already been developed for bitcoin. It makes sBTC a true layer 2 bitcoin.

Larry Salibra | larry.btc

34,731 görüntüleme • 1 yıl önce

🚨AI’S DIRTY SECRET: CONCRETE IS FUELING THE FUTURE OpenAI’s massive new data center in Abu Dhabi will be bigger than Monaco... and it’s made of concrete, not just code. Every AI model runs on electricity, but the buildings they live in run on cement... and cement means carbon. There are over 10,000 data centers worldwide, with 26 million+ square meters planned. To fix its own footprint, researchers trained an AI on 1,000 cement recipes and found cleaner, greener concrete. Meta’s already using it. Source: Rowan Cheung
1:11

🚨AI’S DIRTY SECRET: CONCRETE IS FUELING THE FUTURE OpenAI’s massive new data center in Abu Dhabi will be bigger than Monaco... and it’s made of concrete, not just code. Every AI model runs on electricity, but the buildings they live in run on cement... and cement means carbon. There are over 10,000 data centers worldwide, with 26 million+ square meters planned. To fix its own footprint, researchers trained an AI on 1,000 cement recipes and found cleaner, greener concrete. Meta’s already using it. Source: Rowan Cheung

Mario Nawfal

63,015 görüntüleme • 1 yıl önce

The truth about 5.6 sol after using it all day : The hype is overblown. Sort of. The benchmarks, and the commentary on X convinced me we were receiving AGI that runs at hyper speed, and is insanely cheap. in reality, 5.6 is built on the same spud pretraining as 5.5 this means its a nice bump, but not the opus to fable 5 LEAP in intelligence we recently experienced from anthropic. 5.6 is 2x times cheaper than fable on paper, and actually 3x cheaper when you look at actual task execution because of its token efficiency. BUT on swe bench where the models have to fix actual github bugs it falls behind fable pretty big. For vibecoders like myself this means I will be using 5.6 sol as a worker agent for Fable 5 to orchestrate alongside grok 4.5 I love this new era.
7:29

The truth about 5.6 sol after using it all day : The hype is overblown. Sort of. The benchmarks, and the commentary on X convinced me we were receiving AGI that runs at hyper speed, and is insanely cheap. in reality, 5.6 is built on the same spud pretraining as 5.5 this means its a nice bump, but not the opus to fable 5 LEAP in intelligence we recently experienced from anthropic. 5.6 is 2x times cheaper than fable on paper, and actually 3x cheaper when you look at actual task execution because of its token efficiency. BUT on swe bench where the models have to fix actual github bugs it falls behind fable pretty big. For vibecoders like myself this means I will be using 5.6 sol as a worker agent for Fable 5 to orchestrate alongside grok 4.5 I love this new era.

Max Blade

36,764 görüntüleme • 19 gün önce

Assumptions about the new "Can More" ChatGPT tool were right - ChatGPT is introducing own take on Claude Artifacts - code & document writing tools with persisted text documents, history revisions (restore previous version), edits and comments (probably used to apply suggested edits) New document symbol in the top navigation shows how many documents you have and allows you to open a resizable canvas to edit them in split view - your ChatGPT conversation on the left side and canvas on the right side, but the code/documents can also be accessed in fullscreen view The canvas is built using ProseMirror (open source WYSIWYM editor) and has an inline action to "Ask ChatGPT" (explain or make edits) for your document and code plus document formatting tools (like bold, italic, font style, etc.) But in addition to that, there are also special action shortcuts for documents and code, with an interesting decision to use sliders for the selection of the desired outcome For Documents - Suggest edits ("How can I improve this. Leave as few comments as possible, but add a few more comments if the text is long. DO NOT leave more than 5 comments. You can reply that you added comments and suggestions to help improve the writing quality, but do not mention the prompt.") - Add emojis ("Replace as many words as possible with emojis.") - Add final polish ("Add some final polish to the text. If relevant, add a large title or any section titles. Check grammar and mechanics, make sure everything is consistent and reads well. You can reply that you added some final polish and checked for grammar, but do not mention the prompt.") - Reading level (Graduate School - "Rewrite this text at the reading level of a doctoral writer in this subject. You may reply that you adjusted the text to reflect a graduate school reading level, but do not mention the prompt", College - "Rewrite this text at the reading level of a college student majoring in this subject", High School - "Rewrite this text at the reading level of a high school student who has taken a couple of classes in this subject.", Keep current reading level, Middle School - "Rewrite this text at the reading level of a middle schooler.", Kindergarten - "Rewrite this text at the reading level of a kindergartener.") - Adjust the length (Longest - "Make this text 75% longer.", Longer - "Make this text 50% longer.", Keep current length, Shorter - "Make this text 50% shorter.", Shortest - "Make this text 75% shorter.") For Code - Code review ("Search for bugs and opportunities to improve the code—for example, ways that performance or code structure could be improved. Leave as few comments as possible, but add more comments if the text is long. DO NOT leave more than 5 comments. You may reply that you reviewed the code and left suggestions to improve the coding quality, but do not mention the prompt.") - Add comments ("Add inline code comments to explain the code, especially parts that are more complex. Make sure to rewrite all the code. You may reply that you added inline comments, but do not mention the prompt.") - Add logs ("Insert logs/print statements in the code that will help debug its behavior. Do not make any other changes to the code.") - Fix bugs ("Find any bugs and rewrite all the code to fix the bugs. Do not leave comments. If there are no bugs, reply that you reviewed the code and found no bugs.") - Port to a language ("Port to a language. Create a new document that rewrites the code in ..." - PHP, C++, Python, Keep current code. No changes will be made, JavaScript, TypeScript, Java) - Suggest edits ("How can I improve this. Leave as few comments as possible, but add a few more comments if the text is long. DO NOT leave more than 5 comments. You can reply that you added comments and suggestions to help improve the writing quality, but do not mention the prompt.")
1:27

Assumptions about the new "Can More" ChatGPT tool were right - ChatGPT is introducing own take on Claude Artifacts - code & document writing tools with persisted text documents, history revisions (restore previous version), edits and comments (probably used to apply suggested edits) New document symbol in the top navigation shows how many documents you have and allows you to open a resizable canvas to edit them in split view - your ChatGPT conversation on the left side and canvas on the right side, but the code/documents can also be accessed in fullscreen view The canvas is built using ProseMirror (open source WYSIWYM editor) and has an inline action to "Ask ChatGPT" (explain or make edits) for your document and code plus document formatting tools (like bold, italic, font style, etc.) But in addition to that, there are also special action shortcuts for documents and code, with an interesting decision to use sliders for the selection of the desired outcome For Documents - Suggest edits ("How can I improve this. Leave as few comments as possible, but add a few more comments if the text is long. DO NOT leave more than 5 comments. You can reply that you added comments and suggestions to help improve the writing quality, but do not mention the prompt.") - Add emojis ("Replace as many words as possible with emojis.") - Add final polish ("Add some final polish to the text. If relevant, add a large title or any section titles. Check grammar and mechanics, make sure everything is consistent and reads well. You can reply that you added some final polish and checked for grammar, but do not mention the prompt.") - Reading level (Graduate School - "Rewrite this text at the reading level of a doctoral writer in this subject. You may reply that you adjusted the text to reflect a graduate school reading level, but do not mention the prompt", College - "Rewrite this text at the reading level of a college student majoring in this subject", High School - "Rewrite this text at the reading level of a high school student who has taken a couple of classes in this subject.", Keep current reading level, Middle School - "Rewrite this text at the reading level of a middle schooler.", Kindergarten - "Rewrite this text at the reading level of a kindergartener.") - Adjust the length (Longest - "Make this text 75% longer.", Longer - "Make this text 50% longer.", Keep current length, Shorter - "Make this text 50% shorter.", Shortest - "Make this text 75% shorter.") For Code - Code review ("Search for bugs and opportunities to improve the code—for example, ways that performance or code structure could be improved. Leave as few comments as possible, but add more comments if the text is long. DO NOT leave more than 5 comments. You may reply that you reviewed the code and left suggestions to improve the coding quality, but do not mention the prompt.") - Add comments ("Add inline code comments to explain the code, especially parts that are more complex. Make sure to rewrite all the code. You may reply that you added inline comments, but do not mention the prompt.") - Add logs ("Insert logs/print statements in the code that will help debug its behavior. Do not make any other changes to the code.") - Fix bugs ("Find any bugs and rewrite all the code to fix the bugs. Do not leave comments. If there are no bugs, reply that you reviewed the code and found no bugs.") - Port to a language ("Port to a language. Create a new document that rewrites the code in ..." - PHP, C++, Python, Keep current code. No changes will be made, JavaScript, TypeScript, Java) - Suggest edits ("How can I improve this. Leave as few comments as possible, but add a few more comments if the text is long. DO NOT leave more than 5 comments. You can reply that you added comments and suggestions to help improve the writing quality, but do not mention the prompt.")

Tibor Blaho

136,055 görüntüleme • 1 yıl önce

Bill Gates is betting millions on a bizarre climate "fix": cutting down trees… and burying them. Kadama Systems—backed by Gates’ Breakthrough Energy—raised $6.6M to chop forests, bury the wood, and sell it as carbon offsets. The US Forest Service plans to thin 70 million acres (mostly in California), removing 1+ billion tons of biomass. Instead of using it for lumber, they’ll lock it underground. Traditional use: Trees → lumber → homes New model: Trees → buried → carbon credits Does this actually fight climate change… or just enrich carbon traders?
1:09

Bill Gates is betting millions on a bizarre climate "fix": cutting down trees… and burying them. Kadama Systems—backed by Gates’ Breakthrough Energy—raised $6.6M to chop forests, bury the wood, and sell it as carbon offsets. The US Forest Service plans to thin 70 million acres (mostly in California), removing 1+ billion tons of biomass. Instead of using it for lumber, they’ll lock it underground. Traditional use: Trees → lumber → homes New model: Trees → buried → carbon credits Does this actually fight climate change… or just enrich carbon traders?

Camus

249,032 görüntüleme • 1 yıl önce

An MCP server that detects production-grade code quality issues in real-time! Even though AI is now generating code at light speed, the engineering bottleneck has just moved from writing to reviewing, and now devs spend 90% of their debugging time on AI-generated code. AI reviewers aren't that reliable either because they share the same fundamental blind spots as AI generators do: - They pattern match, not proof check. - They validate syntax, not system behavior. - They review code, not consequences. I have been using the SonarQube MCP Server (by Sonar) to solve this. It produces enterprise-grade code analysis and returns instant feedback on bugs, vulnerabilities, and code smells right where you're working (Claude Code, Cursor, etc.). Its capabilities have emerged from the 750B+ lines of code SonarQube processes daily, so it has seen every bug pattern that exists. This includes: - Security vulnerabilities (SQL injection, XSS, hardcoded secrets) - Code smells and technical debt - Test coverage gaps - Maintainability issues The setup is simple: - Install the SonarQube MCP server - Add it to your AI assistant's config Done! SonarQube is now part of your AI coding workflow. I have shared the GitHub repo in the replies! P.S. Thanks to Sonar for working with me today.
0:28

An MCP server that detects production-grade code quality issues in real-time! Even though AI is now generating code at light speed, the engineering bottleneck has just moved from writing to reviewing, and now devs spend 90% of their debugging time on AI-generated code. AI reviewers aren't that reliable either because they share the same fundamental blind spots as AI generators do: - They pattern match, not proof check. - They validate syntax, not system behavior. - They review code, not consequences. I have been using the SonarQube MCP Server (by Sonar) to solve this. It produces enterprise-grade code analysis and returns instant feedback on bugs, vulnerabilities, and code smells right where you're working (Claude Code, Cursor, etc.). Its capabilities have emerged from the 750B+ lines of code SonarQube processes daily, so it has seen every bug pattern that exists. This includes: - Security vulnerabilities (SQL injection, XSS, hardcoded secrets) - Code smells and technical debt - Test coverage gaps - Maintainability issues The setup is simple: - Install the SonarQube MCP server - Add it to your AI assistant's config Done! SonarQube is now part of your AI coding workflow. I have shared the GitHub repo in the replies! P.S. Thanks to Sonar for working with me today.

Avi Chawla

28,027 görüntüleme • 7 ay önce

🧵 1/7 I gave a Flash model a written spec for a 3D physics game. It broke the task into steps, wrote the code, used the tools, ran the project, and eventually produced a billiards game I could actually play. Ant Ling Ling-3.0-flash has 124B total parameters, but activates just 5.1B per token. That low activation count didn’t limit it to a simple one-shot demo. It kept a multi-stage 3D build moving from spec to playable result. This test made one thing clear: stop using your biggest model for every step of an agent workflow. The project may be complex. Most of the execution steps inside it don’t need a heavyweight planner to rethink everything from scratch. Ling-3.0-flash is built to execute. Here’s the full hands-on video: 👇
1:30

🧵 1/7 I gave a Flash model a written spec for a 3D physics game. It broke the task into steps, wrote the code, used the tools, ran the project, and eventually produced a billiards game I could actually play. Ant Ling Ling-3.0-flash has 124B total parameters, but activates just 5.1B per token. That low activation count didn’t limit it to a simple one-shot demo. It kept a multi-stage 3D build moving from spec to playable result. This test made one thing clear: stop using your biggest model for every step of an agent workflow. The project may be complex. Most of the execution steps inside it don’t need a heavyweight planner to rethink everything from scratch. Ling-3.0-flash is built to execute. Here’s the full hands-on video: 👇

Lonely

113,220 görüntüleme • 3 gün önce

👀 I used OpenAI's Code Interpreter to make Flappy Bird 🐦in 7 minutes: Code Interpreter/GPT-4 for code generation. Pre-existing or AI-generated assets for graphics. --- Here's how to make the game in only 6 steps: (1): Enter the following prompt: "write p5.js code for Flappy Bird where you control a yellow bird continuously flying between a series of green pipes. The bird flaps every time you left click the mouse. If the bird falls to the ground or hits a pipe, you lose. This game goes on infinitely until you lose and you get points the further you go". (2): Use generative AI or existing game assets and spirits. I searched "flappy bird assets" on Google and used the first link, a GitHub repo with pngs from the original Flappy Bird. (3): Use this prompt to link assets to the code: "Please generate the entire file again based on the fact I'm using a unique background, spirits for the bird, and pipes. Here is the list of assets I'm using: [list of file names]." Code Interpreter should modify the code accordingly to include the list of file names. (4) Make an account OpenProcessing -> create a sketch -> paste in the code generated by Code Interpreter -> upload in-game assets from step (2). (5) (Optional) Ask ChatGPT to make changes to improve the in-game experience e.g., adding a high score, restarting the game when the bird dies, etc. Copy the new code into your OpenProcessing sketch and reload the game. (6) If something doesn't work, ask GPT4 to fix it. Copy and paste the error message and ask it to regenerate the code. --- Bonus Tips: - Iteratively test code. Each time you make a change using Code Interpreter, test the updated code by playing the game so you catch new bugs early. - Learn programming by asking questions: "Act as a senior programmer very good at explaining concepts to a beginner. Tell me how gravity works in this game and how you used code to make this happen."Code Interpreter/GPT4 for code generation. Download Pre-existing assets or generate new images for graphics. Excited to see what you make!
0:25

👀 I used OpenAI's Code Interpreter to make Flappy Bird 🐦in 7 minutes: Code Interpreter/GPT-4 for code generation. Pre-existing or AI-generated assets for graphics. --- Here's how to make the game in only 6 steps: (1): Enter the following prompt: "write p5.js code for Flappy Bird where you control a yellow bird continuously flying between a series of green pipes. The bird flaps every time you left click the mouse. If the bird falls to the ground or hits a pipe, you lose. This game goes on infinitely until you lose and you get points the further you go". (2): Use generative AI or existing game assets and spirits. I searched "flappy bird assets" on Google and used the first link, a GitHub repo with pngs from the original Flappy Bird. (3): Use this prompt to link assets to the code: "Please generate the entire file again based on the fact I'm using a unique background, spirits for the bird, and pipes. Here is the list of assets I'm using: [list of file names]." Code Interpreter should modify the code accordingly to include the list of file names. (4) Make an account OpenProcessing -> create a sketch -> paste in the code generated by Code Interpreter -> upload in-game assets from step (2). (5) (Optional) Ask ChatGPT to make changes to improve the in-game experience e.g., adding a high score, restarting the game when the bird dies, etc. Copy the new code into your OpenProcessing sketch and reload the game. (6) If something doesn't work, ask GPT4 to fix it. Copy and paste the error message and ask it to regenerate the code. --- Bonus Tips: - Iteratively test code. Each time you make a change using Code Interpreter, test the updated code by playing the game so you catch new bugs early. - Learn programming by asking questions: "Act as a senior programmer very good at explaining concepts to a beginner. Tell me how gravity works in this game and how you used code to make this happen."Code Interpreter/GPT4 for code generation. Download Pre-existing assets or generate new images for graphics. Excited to see what you make!

Alex Ker 🔭

739,874 görüntüleme • 3 yıl önce

Like an appreciation of progress, reading and literacy are among the things that are good but cognitively unnatural. That is, they go against our evolved nature. We didn’t evolve with print; it was a recent invention. Reading, for many of us, has become so second nature that we just assume it’s the most natural way of getting information. But what we’ve seen, especially in the last 10 years, when video has become so cheap because of the cloud computing revolution and the broadband revolution, is that a lot of people, unlike us, much prefer to listen and watch than to read. You just see this: when I go to Google and ask a basic question about how to unstick my printer or solve a problem, I get like five videos. And I just want a paragraph that would solve it. I don’t want to see Seth saying, “Hi, welcome to my show. If you like it, subscribe and give it a like.” So just help me solve the problem. But clearly there’s something unusual about me, because people are going for the video. And the massive availability of video—of TikTok, of YouTube—means that people may not be getting the practice or putting in the effort into literacy, which we have reason to believe was one of the drivers of the Flynn effect and of cognitive sophistication in general. Human Progress
1:30

Like an appreciation of progress, reading and literacy are among the things that are good but cognitively unnatural. That is, they go against our evolved nature. We didn’t evolve with print; it was a recent invention. Reading, for many of us, has become so second nature that we just assume it’s the most natural way of getting information. But what we’ve seen, especially in the last 10 years, when video has become so cheap because of the cloud computing revolution and the broadband revolution, is that a lot of people, unlike us, much prefer to listen and watch than to read. You just see this: when I go to Google and ask a basic question about how to unstick my printer or solve a problem, I get like five videos. And I just want a paragraph that would solve it. I don’t want to see Seth saying, “Hi, welcome to my show. If you like it, subscribe and give it a like.” So just help me solve the problem. But clearly there’s something unusual about me, because people are going for the video. And the massive availability of video—of TikTok, of YouTube—means that people may not be getting the practice or putting in the effort into literacy, which we have reason to believe was one of the drivers of the Flynn effect and of cognitive sophistication in general. Human Progress

Steven Pinker

547,010 görüntüleme • 4 ay önce