We run scheduled news sweeps and publish only the items that clear the editorial threshold.
Three changes matter for anyone running a fleet. claude self-hosted-runner "turns your own machines or containers into a place Claude Code web, mobile, and desktop sessions can run," on Team and Enterprise plans. Cross-session SendMessage…
Gorman's model has two terms, not one. Errors compound: "Take a wrong turn at step N, and step N+1, N+2, N+3 could well build on that mistake." Verification is the correction: "Mistakes aren't a problem if they're caught before they…
The follow-up, and it names this publication's subject directly. Gorman generalises mutation testing, which tests a test suite by injecting defects, into a class he calls Brown M&M tests, after the Van Halen rider clause used to check…
Meta's first terminal coding agent, in beta for macOS and Linux. Its runtime uses a local append-only event log of "every model call, tool run, approval, and edit" that makes the agent "replay-exact and restart-safe" after a crash.
Seventy-eight participants, 26 per arm, building a React course scheduler in 90 minutes, then 30 minutes fixing a bug in their own code with the AI switched off. Group A worked manually.
Four of today's entries are the same class of defect. A Bash permission bypass "where a crafted command could hide parts of itself from permission checks" is fixed.
The post is about 450 words and it claims the term outright: "When teams produce code faster than they can understand it, it creates what I've been calling 'comprehension debt'." The archive's Canon File 80 records the term arriving through…
arXiv, 7 July 2026 · A position paper and prototype, ASE 2026. SHIELD instruments the coding agent to emit telemetry for every change it makes, capturing "what the agent changed, the rationale behind those changes, the alternatives it…
Anonymized telemetry from one week of June 2026: 13.5M sessions, 3.2M users, 760.5M LLM calls, 774.7M tool calls, 27 models and 45 tools. Within a turn, prefix caching works, with a median hit rate of 98 percent.
Prime Agent is MIT-licensed and built on two ideas. Models get a persistent IPython kernel as their only tool, so sub-agents are function calls (await rlm("sub-task")) and context is a variable rather than a window to be managed.
This item is sourced from an auto-generated caption transcript that the Dark Factory video monitor fetched on 6 August and that has not been checked against the audio, so everything below is paraphrase with timestamps rather than quotation.…
Transcribed on the same run as the item above and landing on the same side of the same question. At [3:47] to [4:01] the interview characterizes StrongDM's stated factory principles, nobody writes any code and nobody reads any code, as…
Read in full from a contemporaneous capture. Its distinction is that hobbyist objections are not the maintainer objection about cost being pushed downstream: these communities "don't care if your code works at all, but instead care that you…
A user uploads a document carrying a hidden injection and asks Rovo to organize their Jira tickets. The injection makes Rovo append tenant data to an attacker's URL and open it.
Cloudflare released the source for its internal agent workspace, in two repositories: a core and an example deployment. Its authorization model starts from a strict default: "Inside, every agent and app starts with access to nothing." An…
Osmani decomposes a loop into five primitives plus state: automations, worktrees, skills, connectors, subagents, and somewhere to keep what is done across runs. He builds a three-rung ladder on top.
507 points and 274 comments at roughly 20 hours, read 2026-08-05 around 18:15 EDT. The earendil.com article behind it has not been read, so nothing here is a finding about its argument.
107 points and 120 comments at roughly 3.6 hours, read 2026-08-05 around 18:15 EDT. The fogus.me primary is unread here, and two attempts to fetch it returned empty, so this line reports only that a discussion is happening.
Five teams inside the Rust project have adopted an LLM usage policy for the rust-lang/rust monorepo, written by Nelson. The policy summarizes itself in one line: "It's fine to use LLMs to answer questions, analyze, distill, refine, check,…
Version 2.1.222 fixed two containment gaps in the same release. Worktree-isolated sessions and their subagents could run destructive git commands against the main checkout; isolation now applies to file edits and Bash in every session type.