Ayan

@thsottiaux :D

I think GPT 5.6 is pretty good

@BojackBujin @notch I think it is unnecessary if you dont read the code after agent

@notch The only purpose is to make the code more "machine readable" for better catching errors before runtime. It's pretty much unnecessary today, specially with AI code assistants.

TypeScript is an insane quagmire for absolutely no benefit beyond documentation.

@giosullutrone99 @thsottiaux you are using 5.5 in screenshot

@thsottiaux Is it just my repo or did gpt-5.6 became much more prone to blocking requests?

Today, the OpenAI product and engineering team is humming, there is so much to coordinate and keep running across the release of GPT 5.6 Sol/Terra/Luna, ChatGPT Work, the new ChatGPT desktop app, hosted sites and a million other things... together with the new ChatGPT Voice just launched yesterday. We will not get it all right, give us feedback and we will iterate quickly. Thank you for being an amazing community.

@thsottiaux @thsottiaux In gpt live there is one issue. After talking 20 min voice start to lag. 200usd plan.

@thsottiaux @thsottiaux san, When is 5.6 ?? Waiting all day today

Good morning ☀️

@ibatulanand @OpenAI @TokyoAI_JP @OpenAIDevs You are the beast !

Won 🥇 1st place at the @OpenAI Hackathon in Tokyo and +$25k OpenAI credits 👀 built "Sabi" within 2 hrs, which solves the rental deposit over-charging issues for renters in Japan 150 min: vision + structured outputs, file search over the MLIT PDF, Codex, live on Vercel

@BenjDicken i think use tmux claude code + nvim in diff panels and in next window use the lazygit should be useful

What's the best ai-assisted coding setup in neovim? Need to seamlessly mix writing code by hand, agentic work, diff review, and file browsing.

Actually use the medium effort

Will test today 4.6 and 5.2 and let you know the difference

New Engineering blog: We tasked Opus 4.6 using agent teams to build a C compiler. Then we (mostly) walked away. Two weeks later, it worked on the Linux kernel. Here's what it taught us about the future of autonomous software development. Read more: anthropic.com/engineering/bu…

Google AI released Illuminate - research paper to short podcast You may be in the waiting list for couple of days.

Reflection 70B just dropped, beating GPT-4o and Claude Sonnet on key benchmarks while being much smaller. This is huge, but the real story is how it happened: Matt Shumer isn't your typical AI researcher. He's a prompt engineer who's been in the trenches since early GPT-3 days, building for millions of users. That experience led to a key insight: LLMs suck at admitting mistakes when reflecting. They'll make errors just to have something to correct. The solution? Fine-tuning for genuine self-correction without new errors. So simple it's brilliant, and the big labs missed it. The result is a model that thinks only when necessary. And with reflection built in, you can very easily hide it from the user. Built in 3 weeks by 2 guys who get how LLMs actually behave in the wild. No billions or years of research needed. It's open-source. 405B version next week, maybe dataset release too. Innovation flood incoming. Big Tech is likely scrambling. Their models, often built by researchers without real-world experience, look outdated now. Grok's system prompt is embarrassingly bad. Claude already does this with prompting (ask it to think carefully, you'll see inference slows down, because the UI doesn't show text in between tags), but fine-tuning it in could be an easy upgrade. Let's be very clear: models are going to get much better in the next month or two. What Matt did is simplistic, and there are a lot more easy gains to be had. For example, if you prompt a model with "I'll tip you $20 if you get this right, or "My job depends on this," you get better outputs. With better training, that might not be as necessary. Chain-of-Thought and Self-Reflection are also very simple, and this was built with a SYNTHETIC dataset. Can you imagine if we used people to carefully curate a much better dataset? If we experimented with other forms of CoT, self-reflection, multi-agent reasoning, etc? There are so many things to try, and you don't have to be at OpenAI to try them! Long-term, models might not need to fine-tune CoT/Reflection, this kind of thought process might be deeply baked into them. For now, it's an easy win. Yes, it's slower – it adds a reasoning step. But with Groq/Cerebras hitting 1800+ tokens/sec, does it matter? Every IQ point for a model is crucial. I'll happily wait 100ms for better results. The future of AI isn't just bigger models. It's smarter training, real human-like thinking. And it might come from engineers, not PhDs. Reflection is just the beginning. Watch this space.

Mark Zuckerberg tries to buy Instagram March 20, 2012

KEEPING LINUX UP TO DATE ISNT HARS ACTUALLY JUST DONT UPDATE IT YOU DONT EBEN NEED TO UPDATE IT

@dogs_minigame UQAlo0oeENBXkDCWvr9jK_-qd3vEgTxeXD3s-3z3JYJKN8Nk

@airdrop_ware UQAlo0oeENBXkDCWvr9jK_-qd3vEgTxeXD3s-3z3JYJKN8Nk

did you guys know that you can just like, decide to not spend any money at all? like you could literally just not spend any money other than costco and network/heat bills for a whole month and you'll be fine. you don't need to spend money ever

I’m pretty sure if I share this video the British Stasi will try to extradite me… please don’t retweet, for your own safety…