vibehacker
News
X / @thsottiaux (Codex lead) ·

Codex Day 4: instant steering ships alongside GPT-6.1 Sol Ultrafast, up to 8x faster than Standard

Codex lead Tibo's Day 4 post (Oct 8) says mid-task steering now takes effect instantly, so the model reacts to your corrections right away instead of wasting effort on the old direction, while OpenAI Developers says Ultrafast for GPT-6.1 Sol is rolling out today in the API, Codex, and ChatGPT Work at up to 8x Sol Standard's speed. Astra's Ultrafast has been limited to Pro $500 and eligible Enterprise and Edu plans and bills above Standard, so check your plan and the API pricing page before switching it on.

Read at x.com
Codex
AI coding agent for features, refactors, reviews, and releases

More news

View all

Google Cloud announces Gemini agent, one enterprise agent that takes objectives and can route to Claude

Announced Oct 8 at Gemini at Work 2026, it handles knowledge work, media, and writing and running code from one prompt box, with @Gemini in Gmail and Docs, access from the command line, Slack, and Microsoft 365, plus an API to run it headless inside other apps. It can spin up sub agents and route to Gemini or Anthropic's Claude models, but it's in private preview for select Workspace Business and Enterprise plans with no firm rollout date…

9to5Google

JetBrains releases Mellum2.1, an Apache 2.0 12B MoE trained with RL to work as a local coding sub-agent

Released Oct 8 on Hugging Face with the same 2.5B active architecture as Mellum2, the model was post trained with reinforcement learning across millions of sandboxed runs so it can explore a codebase, edit files, and check its own changes, and JetBrains says it serves almost twice as many tokens as Qwen3.5 9B under heavy load. GGUF builds for llama.cpp, Ollama, and LM Studio, plus the multi token prediction head for vLLM, are listed as coming soon…

JetBrains Blog

Sierra and Meta propose Personal Agent Protocol, an OAuth-based standard for personal agents to sign in to businesses

Announced Oct 6 with Genesys, Instinct, Rocket, Shopify, Stripe, and Walmart, the open standard lets a personal agent start as a guest on a company's site, then sign in with read only or write access the user picks, and finish the job through the website, MCP or OpenAPI endpoints, or the company's own agent in one OAuth session. The v0.1 spec and a reference implementation are due later in October, so nothing is implementable yet…

Sierra Blog

GitHub Copilot will run Microsoft's MAI Code 1.1 Flash locally and auto-route between your PC and the cloud

Announced Oct 7 and due by end of October in Copilot CLI, the Copilot app, and VS Code, a 53GB quantized build of the 137B parameter (6.8B active) MoE scores 70.8% on SWE Bench Verified vs 72.6% for the cloud version, with Auto mode picking local or cloud per task or you selecting it via Windows ML or any OpenAI compatible local endpoint. Microsoft's reference machine is an RTX Spark Surface Laptop Ultra with 128GB unified memory (75.5GB peak at 256K context), and local inference alone doesn't make a session offline…

Microsoft Command Line Blog

Spotted something we missed? Start a thread.