Tau² Benchmark: How a Prompt Rewrite Boosted GPT-5-Mini by 22%
Link: https://quesma.com/blog/tau2-benchmark-improving-results-smaller-models/
Discussion: https://news.ycombinator.com/item?id=45275354
Tau² Benchmark: How a Prompt Rewrite Boosted GPT-5-Mini by 22%
Link: https://quesma.com/blog/tau2-benchmark-improving-results-smaller-models/
Discussion: https://news.ycombinator.com/item?id=45275354
If you have a fediverse account, you can quote this note from your own instance. Search https://social.lansky.name/users/hn100/statuses/115220703383404369 on your instance and quote it. (Note that quoting is not supported in Mastodon.)