Fetching from the wire…
Tools2026-09-24 · source-backed
Unity scenes and prefabs link to code through GUIDs in .meta and YAML files, which shell search and code-only indexes can't follow. A persistent index exposed as typed query tools, in production in Tuanjie Codely since July 28, halved tokens and time on 28 paired questions (p<0.004) (arXiv). Generalizes to any repo where serialized config carries the links between parts. Index the links instead of hoping grep finds them.
Each link below shares sources, entities, or timing with this story.
TechCrunch: Greenoaks led on July 30, five months after Index led a $100M Series A. Founded by Stanford PhD Joon Sung Park, author of the "Smallville" generative-agents work. Revenue up 5x since a February 2026 launch, headcount past 50, tens of millions of simulations run for...
arXiv 2607.26791 benchmarks post-compromise incident response and reports agents struggle to proactively investigate silent intrusions. They respond to what they're pointed at. Read alongside the July intrusion post-mortem, that argues against putting an agent on the detection...
This one annoyed me, because I've been running the losing pattern. SWE-QA (arXiv 2608.01507) compares the sub-agent grep pattern that Claude Code, Codex and Antigravity all ship by default against a pre-built semantic index over the same repository. Semantic search answered 65...
Microsoft's July 23 release targets a genuine gap: harness-based agents like Claude Code and Codex drive multi-turn reasoning, tool use, and external system access but were hard to train end-to-end with standard open RL infrastructure. The trick is decoupling training from inf...
Data that contradicts the vibe. That's rare enough to lead with. Dipongkor, Baral, Lam and Moran analyzed 4,882 pull requests from five coding agents in the AIDev dataset (532 Java, 4,350 Python), accepted to ICSME 2026. The findings, in order of how much they should change yo...
Announced September 17, the policy is pretrained on Figure's Index dataset of human behavior and evaluated in 30 Bay Area homes with no data collected in any of them, no fine-tuning, no adaptation to the objects manipulated. In a controlled comparison against an identical poli...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.