1
Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed
Across 16 coding models, hashline’s content-hash line anchors beat patch for 14 models; the weakest models gained the most.
Can.ac
Reverse-engineering and whatnot
- Popular posts
- 2
- Total points
- 1,040
- HN comments
- 364
- Rank
- #2,052 personal
Visit blog.can.ac → RSS feedOn Hacker News Mar 2021 – Feb 2026
Software Engineering 2Systems & Performance 1AI & Machine Learning 1
2
Speculating the entire x86-64 instruction set in seconds with one weird trick
As cheesy as the title sounds, I promise it cannot beat the cheesiness of the technique I’ll be telling you about in this post. The morning I saw Mark …