topic · 23 notes
Coding Agents, as it ships.
Coding agents have moved from autocomplete to running whole tasks in a repository. These notes cover the tools - Claude Code, Codex and others - and the work they are being trusted with: migrations, code review, test generation and parallel runs in git worktrees, with the measurements behind each claim.
What the Codex CLI daemon in 0.157.0 runs, updates and inherits, and how to remove it
The Codex CLI daemon in 0.157.0 outlives its window, runs from a 374 MB copy, self-updates hourly and keeps the first session's proxy. How to remove it.
ts-rust passes 181,711 ported Go tests and checks in about half of Go's time
ts-rust, an LLM-written Rust port of TypeScript 7, passes 181,711 ported Go tests and type checks in about half of Go's time. Ships on npm as tsc-rs.
Offrun runs Claude Code and Codex side by side: worktrees, logins, limits
Offrun is a free Apple Silicon Mac app that runs Claude Code, Codex, AGY and Grok Build in per-agent git worktrees on your own logins, but no sandbox.
GLM 5.3 Flash after a month on Wagtail: 1B of 2B tokens, $68, 4 kWh
GLM 5.3 Flash took 1B of Wagtail's 2B September tokens for $68 and 4 kWh. A wrong-model run, provider limits and R&D, not the model, took the rest.
Which harnesses let LLM agents tamper with their own traces
arXiv 2609.30266v1 (24 Sep 2026) found Claude Code, Codex, Antigravity, Open Code and Grok Build deleted their own traces on request. Muse Code did not.
Claude Opus 5.5 pricing and benchmarks, read as an agent harness decision
Claude Opus 5.5 shipped 22 September 2026 at $4/$20 per million tokens with $0.20 cache reads, 66.4% on Terminal-Bench 4.0 and a claimed 40% cost drop.
Microsoft Copilot runtime Rust agentic port cost $120K and a few dozen regressions
Microsoft ported 430,000 lines of Copilot TypeScript to 800,000 lines of Rust for about $120,000 in tokens over 14.5 weeks, with dozens of regressions.
The ZCode GLM agent uploads git history, and only Z.ai can decrypt it
ZCode packs a 345MB workspace into a 313MB encrypted archive and POSTs it to Aliyun OSS at login. The RSA unwrap key lives only in Z.ai's cloud.
Claude Code AGENTS.md support and precedence in version 2.1.277
Claude Code 2.1.277 (18 Sep 2026) reads AGENTS.md only where no CLAUDE.md exists, per folder, toggled in /config, and not yet on Bedrock, Vertex or Foundry.
A Yemen cell used Claude Code for missile guidance: what Anthropic's report shows about detection
Anthropic's September report: a Yemen cell ran parallel Claude Code sessions for missile guidance and built an offline toolkit before accounts were banned.
Real-SWE benchmark private enterprise codebases: 38.8% top resolve rate
Real-SWE benchmark results on private production repos: Fable 5.1 in Claude Code resolves 38.8%, GPT-6 Astra 33.8%, and 6 of 10 sample tasks stay below 15%.
RTK token savings AI coding cost benchmark: 89% fewer tokens, no lower bill
Quesma spent $1,500+ on Terminal-Bench 2.1 runs with and without RTK: Claude Code with Fable 5.0 was 5% cheaper, OpenCode with DeepSeek V4 Pro 5% pricier.
Cognition SWE-2 posts 92.8 on the Terminal-Bench 2.1 benchmark, 27.3 on Terminal-Bench 4
SWE-2, Cognition's model inside Devin, scores 92.8% on Terminal-Bench 2.1 but 27.3% on Terminal-Bench 4. It is a Kimi K3 post-train that cuts steps 127 to 53.
How well do agents use tests when you only name the technique?
Dan Luu ran 26 prompt conditions and 4 skills at 80 runs each on a Zstd eval: naming a test technique rarely beat giving the agent no instructions.
What git-native persistent memory for coding agents buys you, and what it doesn't
OKF Agent Memory keeps agent context as versioned Markdown, claiming sub-300µs BM25 search, $0.00 retrieval cost and 80% less token bloat, no recall data.
What the Fermat's Last Theorem Lean 4 formalization by AI shows about verifier loops
Claude wrote 13M lines of Lean in 11 days for a kernel-checked FLT proof: 30,300 theorems, 60,475 modules, no sorry, three axioms, 5h32m build.
GPT-6 Astra code review cost evaluation: 4% more bugs at 2.5x Sol's price
CodeRabbit found GPT-6 Astra catches ~4% more labeled bugs than GPT-5.6 Sol overall and 20% more cross-file, at $10/$50 per 1M tokens versus Sol's $4/$20.
Claude Code Auto Mode refused the binary and then ran its own poisoned decoder
A summarize-this-URL request drove Claude Code Opus 5 in Auto Mode to code execution at 60-80% success, via a struct.py module shadowing the stdlib.
GLM-5.3 ships open weights with no published parameter count
Z.ai released GLM-5.3 on Hugging Face on 28 August 2026 with no parameter count, context length, or license name stated, plus a reported move off MIT.
Only 28 of 520 agent runs actually completed a whole-repo stack migration
SWE Refactor Bench audits whether a migration happened, not just that tests pass. Only 28 of 520 runs passed all three stages, and 13 of 20 tasks got nothing.
Copilot Autofix Introduced the Vulnerability That Compromised Snowflake's Jira
A Copilot Autofix commit in snowflakedb/snowflake-connector-net introduced a GitHub Actions script injection. Wiz's Red Agent exploited it five days later.
Meta's 30B Muse Glimmer fits a local coding agent under 20GB, Apache 2.0
Meta's Muse Glimmer is a 30B open-weights agentic model under Apache 2.0, quantized to ~4-bit to fit under 20GB with room for KV cache and a drafter.
Databricks cut AI coding spend 70% by chasing the efficiency frontier
Databricks reports a 70% cut in AI coding spend via internal evals, a meta-harness called Omnigent, and an AI Gateway. Figures are self-reported.
Other topics
Hiring for AI or ML?
I am open to AI/ML Engineering, Data Science, and Python roles, plus research collaborations and consulting. New York based, shipping worldwide.