The Gut Benchmark - Field Notes
Loading...
This site is best viewed in a modern browser with JavaScript enabled.
Something went wrong while trying to load the full version of this site. Try hard-refreshing this page to fix the error.
All Discussions
Welcome to The Gut Benchmark forum
What got you into tracking how models feel?
Is the max x20 sub actually worth $200/mo? Let us do the math
The 3-message warmup that makes any model feel smarter
Same prompt, worse output than a month ago — collecting evidence
Did they quietly quantize the flagship last week?
Anyone else notice the flagship getting lazy on long context today?
Claude felt razor-sharp this morning, foggy by mid-afternoon?