Hacker News: seaurchinzee

New comment by seaurchinzee in "Claude Fable 5.1 and Claude Mythos 5.1"

seaurchinzee — Tue, 01 Sep 2026 20:04:56 +0000

That website seems to suggest that Opus 5 spends ~57 cents per task, while GPT 5.6 Sol spends ~49 cents per task? That ratio doesn't feel quite right to me. Artificial Analysis says Opus 5 High costs nearly ~3x as much as GPT 5.6 Sol High for a given task: https://artificialanalysis.ai/models/comparisons/claude-opus...

New comment by seaurchinzee in "Claude Fable 5.1 and Claude Mythos 5.1"

seaurchinzee — Tue, 01 Sep 2026 18:53:03 +0000

According to the FrontierCode Extended benchmarks in the system "card" (page 169-170), Fable 5.1 apparently does best on the medium effort level for this benchmark: "[...] at higher efforts, Fable 5.1 occasionally adds more small, unrequested changes [...]" Though Fable 5.1's medium is also lower than Fable 5's best score on the same benchmark, which uses xhigh.

New comment by seaurchinzee in "Claude Fable 5.1 and Claude Mythos 5.1"

seaurchinzee — Tue, 01 Sep 2026 18:30:27 +0000

Oh dang, that's really unfortunate, nice catch. At least Claude subscription users got a usage reset. But yeah, I can't help but feel Codex is far more generous with their subscription quota at the moment. I've been using Fable to orchestrate GPT Sol Max and Sol Ultra agents all day, and I've barely made a dent.

New comment by seaurchinzee in "Claude Fable 5.1 and Claude Mythos 5.1"

seaurchinzee — Tue, 01 Sep 2026 18:17:52 +0000

"Cache reads now cost 75% less, or $0.25 per million tokens." For me, at a typical 95% cache hit rate, I think my optimal context window size before autocompaction goes from ~200K to ~400K tokens. Great for longer horizon tasks.