LiveUpdated 2026-09-22 21:33 UTC

Now the next experiment cooking in the lab 👇

Name: Now the next experiment cooking in the lab 👇
Uploaded: 2026-09-22T20:40:05.000Z
Channel: Javier • priv/acc
Description: This was so much fun. Now the next experiment cooking in the lab 👇 A lean model trained hard to think from first principles and maximize tool usage. If you teach that well I believe the model could do anything, no need to memorize the whole internet.

This is a AI post classified by Jev as AI infra & evals (a tutorial), kept by the AI Radar because it carries real work, not commentary.

This was so much fun. Now the next experiment cooking in the lab 👇 A lean model trained hard to think from first principles and maximize tool usage. If you teach that well I believe the model could do anything, no need to memorize the whole internet.

Posted by Javier • priv/acc (4.4k followers) 1 h ago · 4 likes · 229 views · view the original post on X. Kept by the AI Radar as AI infra & evals.

More AI work like this

We’ve improved prompt caching in the API for GPT-6, helping agents run faster and cost… — @OpenAIDevs
What makes an AI factory energy efficient? — @NVIDIAAIInfra
$QCOM UNVEILS NEW 2NM SNAPDRAGON CHIPS WITH BIG ON-DEVICE AI PUSH — @wallstengine
GPT-6 Sol and GPT-6 Luna from OpenAI (@OpenAI) are now available on Merge Gateway. — @merge_api
LangSmith now supports decision models including Jev and SemIf, giving you visibility… — @LangChain
What the DPU Is in the Agentic Era ? we give the… — @zartbotF
We just pushed a big update to Ramp AI Index. — @arakharazian
simultaneous live detection of: — @yoheinakajima

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 43.2k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 21:33 UTC. Full method.