3/ Two of the most powerful features in Claude Code: /loop and /schedule Use these to schedule Claude to run automatically at a set interval, for up to a week at a time. I have a bunch of loops running locally: – /loop 5m /babysit, to auto-address code review, auto-rebase, and
LLMS
-
Top AI Research Papers of the Week (March 23-29)
By
–
Here are the top AI Papers of the week (March 23 – 29) 1. Meta AI's V-JEPA 2.1
2. LeWorldModel
3. TurboQuant
4. ARC-AGI-3
5. Claudini More details on each paper below. -
Introducing GPT-5.5: New Class of Intelligence for Real Work and Agents
By
–
Working on approving all members requests to our x/LocalLLaMA community https://
x.com/i/communities/
1958212555958022177
… -
Cache Deletion Degrades Model Performance and Reasoning
By
–
kills cache, kills thinking stream, will degrade performance on any model. Bad idea.
-
GPT 5.5: A New Class of Intelligence for Real Work and Agents
By
–
Happy to have you co-hosting this session with me bro!
-
OpenAI Announces Official Release of GPT 5.5 with Benchmark Performance Gains
By
–
Glad to hear you found it informative
-
Grok’s AI-powered translation and recommendation features improving
By
–
Grok automatically translating and recommending 𝕏 posts from other languages is starting to work
-
OpenAI and Google Models Solve 2025 International Mathematical Olympiad
By
–
I've come across an article from El País that surprised me because for a moment it seemed to suggest that the whole thing about OpenAI and Google's models solving problems from the 2025 International Mathematical Olympiad was a lie. Then you read the article and realize what
-
Supporting AI Researchers with Codex: India Growth
By
–
ayy, super cool! lets make this even more fun – would love to support the researchers w/ codex bullish on India!
