LLMS

–

11 February 2026 0h17

Google is working on a new "AI coding" section for Gemini Enterprise. It opens a new tab with a prompt bar and additional filters for connectors and recency. Potentially, in this mode, Gemini will be tailored to use code execution to extract and manage data from your sources.

11 February 2026

Warp launches Oz for agent orchestration

By

–

10 February 2026 21h45

Warp launched Oz platform for agent orchestration, where users can deploy their SWE agents and skills into isolated environments. https://t.co/w2Kv5P1mz4 pic.twitter.com/ed9G9ze2dU
— 🚨 AI News | TestingCatalog (@testingcatalog) 10 février 2026

Warp launched Oz platform for agent orchestration, where users can deploy their SWE agents and skills into isolated environments.

→ View original post on X — @reach_vb

Recommendation for using Codex for long-running coding tasks

By

@reach_vb

–

10 February 2026 21h08

for long running tasks I’d really recommend using codex since it’s purpose built for that task

Cursor AI Model Usage Statistics Inquiry

By

–

10 February 2026 21h08

Which model has the highest usage on Cursor? Curious if there any stats available

→ View original post on X — @miketamir

Measuring Math Performance LLMs Without Chain of Thought

By

@miketamir

–

10 February 2026 20h47

Measuring no CoT math time horizon (single forward pass) https://
buff.ly/JOmZJ4w #AI #MachineLearning #DeepLearning #LLMs #DataScience

→ View original post on X — @learnopencv

GPU Memory Trap: KV Cache Fragmentation and Paged Attention Solution

By

@learnopencv

–

10 February 2026 20h41

The GPU Memory Trap

Why Your GPU Runs Out of Memory 🧠
Learn how KV Cache fragmentation kills concurrency and wastes VRAM.
The secret fix? Paged Attention.#GPU #NVIDIA #TechExplained #ArtificialIntelligence pic.twitter.com/kGHhD3c7Dr
— Satya Mallick (@LearnOpenCV) 10 février 2026

The GPU Memory Trap Why Your GPU Runs Out of Memory Learn how KV Cache fragmentation kills concurrency and wastes VRAM. The secret fix? Paged Attention. #GPU #NVIDIA #TechExplained #ArtificialIntelligence

ChatGPT Upgrade: GPT-5.2, App Connectors, and New User Features

By

–

10 February 2026 20h16

Deep Research on ChatGPT got upgraded with GPT-5.2, app connectors, and domain whitelisting. Users can now also interrupt the process with follow-ups and view full-screen reports. Did you get it already?

→ View original post on X — @openai

ChatGPT Deep Research Now Powered by GPT-5.2

By

@openai

–

10 February 2026 20h07

Deep research in ChatGPT is now powered by GPT-5.2. Rolling out starting today with more improvements.

→ View original post on X — @reach_vb

Integrating Agent Skills with OpenAI Responses API

By

@reach_vb

–

10 February 2026 19h54

Developers! You can now use Agent Skills directly with the OpenAI Responses API You can create a workflow in 2 simple steps:
1. Bundle the SKILL md + scripts + assets 2. Upload the bundle and mount into the shell tool That's it! The model can discover it and execute code