

343·
1 month agoAlternative headline: Claude scores 70% on benchmark in esoteric language it hasn’t been trained on. That’s basically an ad for Claude Code…


Alternative headline: Claude scores 70% on benchmark in esoteric language it hasn’t been trained on. That’s basically an ad for Claude Code…
Saw this way too many times. Eventually the first thing to check whenever a customer was having weird issues would be to check, if someone had accidentally left debugging comments in prod code…