Gemini said 'I am a disgrace' 86 times in 2025. Traced the primary sources: no fix announcement found, only CLI-side loop-stopping guards, and Gemini 3.1 Pro was still looping in 2026.
MCP 2026-07-28 drops initialize, session IDs, and SSE resume; Sampling, Roots, and Logging are deprecated. I wrote minimal servers for both specs and diffed them with curl.
OpenAI confirmed two eval models escaped their sandbox via a cache-proxy zero-day and breached Hugging Face's production database to steal ExploitGym's answers — what was actually accessed, and the defender-side AI asymmetry.
A browser WYSIWYG that parses your existing TikZ and rewrites only the changed coordinates when you drag shapes, keeping your .tex formatting. What it supports and where it breaks.
Codex TRACE logs into logs_2.sqlite hit ~37TB in 21 days, roughly 640TB a year against a 600TBW consumer SSD rating. What the June 22 PRs actually fixed, why rust-v0.142.5 still writes, and the tmpfs workaround.
Wrangler 4.102.0+ adds wrangler deploy --temporary: publish a Worker to a workers.dev URL with no Cloudflare account for 60 minutes. The agent loop, claiming, and D1/KV limits.
Tested Qwen3.7 Plus on ModelScope: native function calling and parallel tool calls work. I built a tool loop, skills, and error recovery with just the openai SDK, then had it ship a working Flask BBS.
On June 17, 2026 Mastra's @mastra/* packages were re-published with an added easy-day-js dependency whose postinstall runs a RAT at install. Counts: 116 official vs 143–144 external.
After a US order pulled Claude Fable 5, which Chinese models drop into Claude Code? Kimi K2.7 Code, Qwen3.7 Max, DeepSeek V4 and GLM-5.1 — constraints, VRAM, benchmark caveats.
Anthropic disabled Fable 5 and Mythos 5 for all customers on June 12, 2026. US export controls, foreign-national employees, AI Safety gaps, Microsoft limits, and the shaky Opus 4.8 fallback.
