Why Are Coding Agents So Dumb?
Lynch started with coding agents in February 2025 and expected agents to catch up with the models within six months; he says they did not.
10subtasks OpenCode created for a 1.5k-line feature, then ran one by one
Coding agents
Week 41 · 5-11 Oct
8 sources filed · EN 7 · RU 1
B A ts-rust (aka tsc-rs): Rust port of the TypeScript compiler, written by LLMs
OpenAI run: GPT-5.6 Sol and GPT 6 Astra, over $400,000 in API-priced tokens, over 1.3 million lines of Rust over several months of goal loops, about 84% compatibility at best.
$400,000+API-priced tokens spent on GPT-5.6 Sol and GPT 6 Astra, which never got past about 84% compatibility
A Comprehension Audits to Mitigate Risks from Automated AI Research
Anthropic, OpenAI and Google report AI writing 75% or more of their new code; Anthropic reported that as of August 2026 Claude "leads" 26% of its R&D work.
183%median increase in code submitted by regular contributors to open-source AI repos, Q1 2024 to Q2 2026
A When Sub-Agents Work in Parallel: Promises and Pitfalls of Dynamic Concurrency in Long-Horizon Coding
Agents and models (July 2026 configurations): Codex with GPT-5.4, Claude Code with Claude Opus 5, Kimi Code with Kimi K3.
1.41-3.31xtoken usage of concurrent versus sequential execution across agents
A How we launched an AI reviewer on 4,000 PRs a day
About 4,000 PRs a day pass through NeuroReview, roughly 40% of PRs created in Arcadia; use is voluntary and internal only.
~4,000pull requests a day reviewed by NeuroReview, about 40% of all PRs in Yandex's Arcadia monorepo
B Coding-agent use at OpenAI is doubling roughly every month
Median researcher daily spend: $0.17 (week ending 18 January), $10.45 (8 March), $136.68 (31 May), $601.25 (15 August).
$601.25median OpenAI researcher's daily coding-agent use at API prices, week ending 15 Aug 2026
A Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale
In a 30-day September 2025 sample, the time from a test-failure notice to the developer's next edit was 2.37 minutes at p10, 6.72 at p25 and 27.48 at p50; this is the window the agent targets.
67.18%correct fixes in expert review of 195 real test failures
A What Does a Harness Buy? Tokens, Mostly
On 447 tasks, Claude Code and mini-SWE-agent differ by -1.8 points (Qwen3.6-35B-A3B) and -1.4 points (Qwen3.8-27B), equivalent within a 5-point margin.
13%median share of hard tasks whose outcome flips, both when swapping the harness and when rerunning the same one
August 2026
1 source filed · EN 1
A Agentic Coding in the Wild
87% of LLM calls are agent-initiated; model calls and tool calls run at a near 1:1 ratio (760.5M LLM calls vs 774.7M tool calls).
87%LLM calls initiated by the agent rather than the user