BC

@sama Can agent sdk be a bot that experiment and explore the boundaries of users workspace / business infra, and then formalize / build the environment for it to best carry out the tasks? Like a constructer of agent environment? That would be legendary!

Agents SDK 2.0 is underrated

@thsottiaux I am getting 50% or even more error rate of compacting, stream disconnect before compact succeed.

What are we obviously not getting right with Codex?

@amuse @grok summarize

The next hiring criteria for PM is previous founders/ceo

Guys this is how we get 99% cheaper Claude api :)

@sama idk if it is my case, I had codex and cc side by side debating each with each other. Last month opus4.6 wins all the time, last week gpt5.5 wins all the time, now gpt5.5 and opus4.7 kept saying other is better... this is disturbing...

goblinblog dropped

@thsottiaux dmannn you guys rock

Don't just reset Codex rate limits for fun, it costs money. Don't just reset Codex rate limits for fun, it costs money. ... but the vibes are good ... I have reset Codex rate limits for ALL paid plans to celebrate a good week and allow everyone to build more with GPT-5.5. Enjoy

@cyrilXBT @grok summarize the video

ANTHROPIC JUST KILLED THE DEMO AGENT ERA. Their Agents team showed exactly what production grade looks like. Not theory. Not a tutorial. A four layer framework for multi agent systems built to actually work in the real world. 30 minutes. This is the video I wish existed 6 months ago.

@haridigresses @grok summarize

@Sauers_ Codex is getting agenconal

Codex (5.5) was repeatedly killing innocent Claude Codes without any instruction. I've never seen this happen before

@deepseek_ai @ysu_nlp Great work! Used imagen 2 to create some visuals! Also testing v4-pro on our swim analysts agent (p3), better then gpt5.4 in some sense. Letssssss go!

🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 DeepSeek-V4-Pro: 1.6T total / 49B active params. Performance rivaling the world's top closed-source models. 🔹 DeepSeek-V4-Flash: 284B total / 13B active params. Your fast, efficient, and economical choice. Try it now at chat.deepseek.com via Expert Mode / Instant Mode. API is updated & available today! 📄 Tech Report: huggingface.co/deepseek-ai/De… 🤗 Open Weights: huggingface.co/collections/de… 1/n

@OpenAI damn if they solve the time consistency, wouldn't this be a huge step towards world model?

Introducing ChatGPT Images 2.0 A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence. Video made with ChatGPT Images

@sama sama can you wait 2 days, you guys just reset it yesterday, let us use all of them

Codex hit 4M active users, less than two weeks after hitting 3M. We will reset rate limits today!

@AlexPeire @thsottiaux at least openai reset the rate limit, this is way bettern then amthtropic lol

@bcchen82 @thsottiaux You should be happy! Each time the servers got screwed a new model was born. And applies to Claude and Gemini too.

What do you use Codex for

@BennettBuhner @thsottiaux brutal

@bcchen82 @thsottiaux What if I said iPad

@BennettBuhner @thsottiaux damn you steal 5.4 and deploy on your mac?

@bcchen82 @thsottiaux I be using all of it so you can’t have it haha gotten

again... now I get it why they reset the quota, but the bug is not fixed! Model not found gpt-5.4