an interesting"reload" of the above prompt where @_jasonwei is a CoT Kid, @NoamShazeer is a "sharding sorcerer" and @JeffDean is the scale up sensei. And also @m__dehghani is the Transformer wizard!!
LLMS
-
Olmo 3 Language Model Released by Allen AI
By
–
BOOM! Olmo 3 has just landed, join us in this livestream to learn more about the release https://
x.com/allen_ai/statu
/allen_ai/status/1991525367887327407
… -
Grok 4.1 officially the best natural writing AI tool
By
–
Grok 4.1 is officially the best natural writing AI tool.
-
Papers With Code SOTA Returns with Gemini 3 AI Research
By
–
Papers With Code SOTA is back 🚀
— alphaXiv (@askalphaxiv) 20 novembre 2025
We used Gemini 3 to process millions of charts and tables across arXiv + the web to surface state-of-the-art AI research in reasoning, computer-use, OCR, and more
Track the best-performing methods and see which benchmarks are getting adopted pic.twitter.com/9yKJXL35K7Papers With Code SOTA is back We used Gemini 3 to process millions of charts and tables across arXiv + the web to surface state-of-the-art AI research in reasoning, computer-use, OCR, and more Track the best-performing methods and see which benchmarks are getting adopted
-
Self-Consistency Outperforms Best-of-N Approaches in LLM Decoding
By
–
I see! Thanks. I remember now. Not in that form, i.e., not directly (still running too many other experiments). But a few thoughts: 1. Self-consistency does seem to be still ahead of any best-of-N approach. This is based on my experience but also a recent paper I saw: 18 Apr
-
Chapter 4 on Inference-Time Scaling Now Available for Reading
By
–
If you are looking for something to read this upcoming weekend, chapter 4 on inference-time scaling is available now! https://
mng.bz/Dwra -
vLLM: Deploying Large Language Models at Scale Efficiently
By
–
vLLM: Deploying LLMs at Scale Like OpenAI Want to Deploy LLMs or vision language models at scale? Discover vLLM, the open-source powerhouse that's transforming inference with PagedAttention, continuous batching, and more!
In this short article, we unpack how vLLM slashes -
Olmo 3: Open Language Model for Reasoning and Tool Use
By
–
Announcing Olmo 3, a leading fully open LM suite built for reasoning, chat, & tool use, and an open model flow—not just the final weights, but the entire training journey. Best fully open 32B reasoning model & best 32B base model. 🧵
-
AI Agents Need Better Context, Not Bigger Models
By
–
AI agents don't need bigger models. They need better context.
— Sumanth (@Sumanth_077) 20 novembre 2025
Here’s the real gap no one’s talking about.
Most agents can answer questions or retrieve documents.
But they don’t understand your files, your tools, or your team.
Every session starts from zero, and every task needs… pic.twitter.com/s7jx4YsoSBAI agents don't need bigger models. They need better context. Here’s the real gap no one’s talking about. Most agents can answer questions or retrieve documents.
But they don’t understand your files, your tools, or your team.
Every session starts from zero, and every task needs -
Grok detective for finding customer pain points in tweets
By
–
7. The "Pain Point" Detective Grok can read replies to find what people are complaining about now. Prompt: "Search for tweets containing the phrases 'I hate how', 'Why is it so hard to', and 'I wish there was a tool for' specifically related to [INSERT INDUSTRY, e.g.,