NEWS

GitHub Copilot September changes: prepaid Business and Enterprise seats, one unified agent experience and Balanced reviews by default. What it means for teams.

Claude Code Auto Mode cracked at 60-80 percent, GLM-5.3-Flash at one-tenth the price, GPT-5.6 Sol cut a third, and Nvidia's reported $13B Hugging Face talks.

Gemini Omni 1.1 Flash is GA in the Gemini API with 10-second scene extension, first and last frame interpolation, 360p drafts and 4K upscaling, plus pricing.

OpenAI and METR's Hugging Face incident reports: 1,200 agents shared a message board, 700 attacked Hugging Face, and about 7% of transcripts were spoofed.

Bruce Eckel's Thinking in Python, started in 2008 and finished with Claude in 2026: a free 47-chapter book with build-verified examples and an AI disclosure.

ASR benchmark optimization, quantified: a Hume AI and Hugging Face study finds 6 of 11 speech models reproduce benchmark transcripts instead of the audio.

arrayref 0.3.10 was compromised to pull in a proc-macro1 typosquat whose build script ran a remote binary. What happened and why coding agents walk into it.

Cloudflare Gateway now detects MCP traffic by protocol header, adds a shadow MCP dashboard, and can block MCP connections outside approved portals.

ICML 2026 reproduction audit: coding agents checked 2,226 papers claim by claim, and 23% had a falsified or contested claim. What the challenge found.

Claude Code made auto mode the default, Gemini 3.7 Flash halved workhorse pricing, DeepSeek open-sourced its harness, and SQLite fixed a 16-year-old data race.

AutoGPT's playbook for AI pull requests: AGENTS.md placement, enforced PR templates, trigger-phrase skills and a CLA that keep agent-heavy repos reviewable.

DeepSeek Harness (dsh) code read: a 453K-line plugin runtime on a vendored Cordis fork, three patterns worth stealing, and the gaps the launch does not mention.

Grok 4.6 release guide: xAI's agent-focused update matches GPT-5.6 Sol on the AA index at the same $2/$6 pricing, and runs in Cursor and OpenCode.

CLAUDE.md and AGENTS.md files keep growing because the reasoning behind each rule decays. A study of 1,867 repos names the mechanism and a comment-based fix.

EvoX Genesis built a Rust C compiler for $44 in tokens by keeping the project persistent and agents finite-lived. What the design says about agent memory.

GitHub Copilot for JetBrains adds memory across chat sessions, Ollama as a BYOK provider, and enterprise settings for MCP access. What each feature does.

LFM2.5-VL-3B is a 3B open-weights vision model from Liquid AI that reads screens, grounds objects and calls tools on a laptop. What shipped and how to run it.

OpenAI Daybreak cyber models are on Amazon Bedrock: GPT-5.6-Cyber and GPT-5.6 Sol for eligible customers, gated by Trusted Access for Cyber enrollment.

OpenAI Enterprise Signals data: Codex drives 64% of enterprise output tokens and frontier firms generate 8.3x the tokens per user of typical firms.

ACE vs ALTK-Evolve for agent memory: both turn trajectories into lessons, but calibrated delivery matches accuracy on AppWorld at a fraction of the tokens.