First, Opus 3 will continue to be available to all paid Claude subscribers and by request on the API. We hope that this access will be beneficial to researchers and users alike.
LLMS
-
Research Agent Processes Academic Papers in Seconds
By
–
10 academic papers. Parsed, analyzed, and synthesized. In under 10 seconds.
— Cerebras (@cerebras) 25 février 2026
We built a research agent with @Cerebras Inference and @UnstructuredIO that processes entire literature reviews so you become a subject expert faster pic.twitter.com/uj5grF825210 academic papers. Parsed, analyzed, and synthesized. In under 10 seconds. We built a research agent with @Cerebras Inference and @UnstructuredIO that processes entire literature reviews so you become a subject expert faster
-
GLM-5 Regression for Python Coding Tasks Compared to GLM 4.7
By
–
Alright, I'm calling it: GLM-5 is a regression from GLM 4.7 for Python coding. Subscribed to Z(.)ai on the basis of 4.7 as it reliably took over all my devops too, and been using GLM 5 since launch. But with multiple turns of Python writing/editing 5 regularly gets confused
-
1.2B LLM runs at 200 tokens per second in browser
By
–
1B model running over 200 tok/s in your browser 👀 https://t.co/JArzxn7FN8
— Maxime Labonne (@maximelabonne) 25 février 20261B model running over 200 tok/s in your browser 👀 Xenova (@xenovacom) Okay, this is actually insane… You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! 🤯 Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web — https://nitter.net/xenovacom/status/2026727703836004796#m
→ View original post on X — @maximelabonne, 2026-02-25 18:47 UTC
-
Aletheia Agent Solves 6 of 10 FirstProof Math Challenge Problems
By
–
Exciting results in AI math research! We use Aletheia agent, powered by Gemini 3 Deep Think, to tackle the FirstProof challenge. Operating completely autonomously, Aletheia successfully solved 6 out of the 10 problems. Check out the full paper for details on the methodology and expert evaluations. arxiv.org/abs/2602.21201
-
Test-Time Training with KV Binding as Linear Attention
By
–
Test-Time Training with KV Binding Is Secretly Linear Attention
-
Diffusion Duality Chapter II: Psi-Samplers and Efficient Curriculum
By
–
The Diffusion Duality, Chapter II Ψ-Samplers and Efficient Curriculum
-
Reflective Test-Time Planning for Embodied LLMs
By
–
Learning from Trials and Errors Reflective Test-Time Planning for Embodied LLMs
-
Query-Focused Memory-Aware Reranker for Long Context
By
–
Query-focused and Memory-aware Reranker for Long Context Processing
-
Data Engineering for Scaling LLM Terminal Capabilities
By
–
On Data Engineering for Scaling LLM Terminal Capabilities