Show HN: 10x better performance from the Coding Harnesses with LLM-wiki
nvk
16 points
14 comments
June 18, 2026
Related Discussions
Found 5 related stories in 129.0ms across 10,996 title embeddings via pgvector HNSW
- Show HN: Browser Harness – Gives LLM freedom to complete any browser task gregpr07 · 96 pts · April 24, 2026 · 61% similar
- Show HN: Find the best local LLM for your hardware, ranked by benchmarks andyyyy64 · 279 pts · May 15, 2026 · 58% similar
- Show HN: A Karpathy-style LLM wiki your agents maintain (Markdown and Git) najmuzzaman · 229 pts · April 25, 2026 · 58% similar
- Show HN: Open-Source AI Racing Harness danAtElodin · 32 pts · May 27, 2026 · 57% similar
- Show HN: 1v1 coding game that LLMs struggle with levmiseri · 15 pts · March 06, 2026 · 56% similar
Discussion Highlights (7 comments)
jarbus
Where is this 10x number coming from?
esafak
How does this differ from https://context7.com/ ?
dolebirchwood
What if I only want 6x better performance? Is there a knob or slider to dial it down?
sppfly
This kind of llm bragging title and AI generated webpage makes me gross.
adithyassekhar
Edit: On closer look this looks useful without the coding harness pitch.
xnx
Some say text files work even better: https://cloud.google.com/blog/products/data-analytics/how-th...
superfrank
I've got a couple of LLM wikis running for different purposes. I just pointed Claude at Karpathy's Github Gist and said "do this" and it set up and has maintained them ever since. So far no issue with that. Can you explain why the version linked is better? Gist link: https://gist.github.com/karpathy/442a6bf555914893e9891c11519...