In 27,280 coding agent runs, 64% of inference spend went to runs that failed
2 comments
- Points344
- Comments120
2 comments
Story details from Hacker News ↗ · linked article on runta.com.
In 27,280 coding agent runs, 64% of inference spend went to runs that failed was first seen on Hacker News · Front page on Nov 17, 2026. Since then it has appeared in 92 checks on 2 different days. Its best position was #1 of 30, reached on Nov 17, 16:43 UTC. It dropped off the list after Nov 18, 14:43 UTC.
Position on Hacker News · Front page at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hacker News.
A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.
The headline here is confusing. They ran a bunch of harness and agent combinations on terminal bench tasks, and 64% of the spending was on tasks that didn’t pass terminal bench verifiers. It’s unclear whether that’s supposed to be surprising against the selected models for the benchmark. I suspect it’s not and the…
There's no IP in a harness, and they don't matter that much. Harnesses simply make different choices around certain context engineering things, what they name tools, how they compact, their system prompt, etc. So it's not surprising that they work "better" for some models than others, but I'd bet that if you made…
I find myself pulled in two directions by the performance of coding agents: First, keeping them on a short leash seems sensible. I don't get failed results very often. When I first started using coding agents, this seemed not just sensible but required in order to not deal with a lot of hallucinated weirdness.…
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 18, 14:43 UTC, after 2 days of trending.
#1 on Hacker News · Front page, on Nov 17, 16:43 UTC. Trendoday checks this list every 15 minutes.
It was first seen on Nov 17, 2026 and has been on the list on 2 days (92 checks) since.
344 points and 120 comments; submitted by Edward40 on Nov 17, 2026.