Fetching from the wire…
OSS2026-09-17 · source-backed
typesafe-computer-use, created September 16 and at 128 stars, screenshots the frontmost window, OCRs it deterministically, merges text blocks with accessibility-tree controls into one numbered list, then asks TypeSafe to pick among three mutually exclusive next actions. Measured decision latency 0.13 to 0.38 seconds against roughly 5.2 for Claude Opus, end-to-end steps ~1.5s against ~5.5s. The cost claim rests on TypeSafe returning probability distributions over choices without charging for generated tokens, which is a real structural difference and also the thing to verify before you build on it.
Each link below shares sources, entities, or timing with this story.
A September 14 changelog says the harness layer uses native subscription logins for Claude Code, Cline, Codex, Cursor, fx, GitHub Copilot, Grok Build, OpenCode and Pi, with no code changes needed (Vercel). Credentials stay on the host and real tokens get injected at the host b...
Twelve months ago, OpenAI led Anthropic by 41 points in enterprise adoption. Today that gap is 8. Enterprise Technology Research's survey of roughly 500 respondents shows OpenAI dropping from 62% adoption (September 2025) to 56% (March 2026) while Anthropic surged from 21% to...
Moonshot AI dropped Kimi K2.6 today and the numbers are hard to ignore. One trillion parameters total, 32 billion active per token across 384 experts, 256K context window, and native multimodal input. It scores 58.6 on SWE-Bench Pro versus GPT-5.4's 57.7 and Claude Opus 4.6's...
GLM-5.1 from Zhipu AI scored 58.4% on SWE-bench Pro. GPT-5.4 scored 57.7%. Claude Opus 4.6 scored 57.3%. That's the first time an open-weight model has ever topped a major coding benchmark against the best proprietary models. The specs matter. GLM-5.1 is a 754B-parameter mixtu...
DietrichGebert/ponytail cut v4.10.0 on September 14 at 138,988 stars, with a scripts/cursor-hooks.js install that merges into an existing Cursor hooks file without clobbering the rest (GitHub). Same release fixes VS Code Copilot detection via a CLAUDE_PLUGIN_ROOT fallback and...
Warp released its client codebase under AGPL-3.0, surged to 56,000 GitHub stars and #2 on GitHub Trending. But the real story isn't the open-sourcing. It's the repositioning. Warp isn't calling itself a terminal anymore. It's an "agentic development environment." The product n...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.