We have lots of teams, one of them is our web-team who is adding features to the website as requested by the community. This is unrelated to the research team which is working on new models, etc.
CODE
-
xAI Releases Grok 4.1 Fast Model
By
–
BREAKING 🚨: xAI released Grok 4.1 Fast model with 2M context window and better tool calling performance! xAI Agent Tools API has been announced as well.
— 🚨 AI News | TestingCatalog (@testingcatalog) 19 novembre 2025
The chance of getting Grok Code this weekend just got higher! https://t.co/Zq0OBZ2BQg pic.twitter.com/CL1gMukuSBBREAKING : xAI released Grok 4.1 Fast model with 2M context window and better tool calling performance! xAI Agent Tools API has been announced as well. The chance of getting Grok Code this weekend just got higher!
-
Off-by-One Errors in Long AI Model Conversations
By
–
Thanks! In longer chats I'm convinced models respond to messages 1 in the past, maybe due to timeout/revert earlier in the conversation. I have been sending them message codes they have to echo back, and sometimes comes back 1 delayed, response content is also off-by-one. Could
-
Software Complexity: The Case for Removing Features
By
–
Well the problem you have now is that there are too many features, they conflict together, files get mixed up with the various reviewing tools, options, now worktrees applying stuff back. I'd actually remove features, make only a core set of things that work reliably together.
-
LLM Performance Degradation at 100K Tokens Context
By
–
People working on basic code and reset their Agent chats every 4-5 replies I envy you. Having to work on deep context design work and at about 100k tokens, LLMs start to get lazy / confused. I resorted to giving them codes they have to echo back. They often seem to think
-
GPT-5.1-Codex-Max Model Achieves 24-Hour Autonomous Task Processing
By
–
The new GPT-5.1-Codex-Max model can work autonomously for more than 24h on a single task over millions of tokens!
-
Terminal Bench 2.0: Reliable Powerful Agents and Harbor Platform
By
–
We had a terrific interview with the creators of Terminal Bench 2.0. They unpack:
• why terminals → more reliable and powerful agents
• key design tradeoffs in TB 2.0
• Creating Harbor to enable eval, RL, and agent workflows at scale
• lessons from building a 100+ -
Semantic Caching for AI Agents Course Announcement
By
–
New course announcement: Semantic Caching for AI Agents, taught by @tchutch94 and @ilzhechev from @Redisinc.
— Andrew Ng (@AndrewYNg) 19 novembre 2025
Semantic caching can significantly reduce your AI application's inference costs and latency. If someone asks "How do I get a refund?" and another later asks "I want my… pic.twitter.com/4ZMLEFr0iqNew course announcement: Semantic Caching for AI Agents, taught by @tchutch94 and @ilzhechev from @Redisinc
. Semantic caching can significantly reduce your AI application's inference costs and latency. If someone asks "How do I get a refund?" and another later asks "I want my -
OpenAI Releases GPT-5.1-Codex-Max for Coding
By
–
BREAKING : OpenAI released GPT-5.1-Codex-Max on Codex with a better performance on coding tasks. “GPT-5.1-Codex-Max can work independently for hours”