Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed

blog.can.ac

Post reply on HN
Print view View original

91–100 of 318 posts

Re: Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed

#92

Post by mycall »

logicprog wrote: post #65

I really enjoyed this article. I think the author is precisely right and I've been saying this for a long time. There's a ton of extremely interesting low hanging fruit that can vastly improve the effectiveness of even currently existing models hiding in how we design our agent harnesses; enough to — at least until we hit diminishing returns — make as much or more of a difference than training new models! I think one…

If I remember, both Claude Code and OpenAI Codex "harnesses" improved themselves now.

OpenAI used early versions of GPT-5.3-Codex to: debug its own training process, manage its deployment and scaling and diagnose test results and evaluation data.

Claude Code have shipped 22 PRs in a single day and 27 the day before, with 100% of the code in each PR generated entirely by Claude Code.

Re: Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed

#93

Post by barrenko »

logicprog wrote: post #65

I really enjoyed this article. I think the author is precisely right and I've been saying this for a long time. There's a ton of extremely interesting low hanging fruit that can vastly improve the effectiveness of even currently existing models hiding in how we design our agent harnesses; enough to — at least until we hit diminishing returns — make as much or more of a difference than training new models! I think one…

2026 is the year of the harness.

Re: Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed

#94

Post by TZubiri »

fcanesin wrote: post #90

The harness is the model "body", it's weight the cognition. Like in nature they develop together and the iteration of natural selection works at both. If smaller labs (Zai, Moonshot, deepseek, mistral..) get together and embrace a harness, like opencode for example, as a consortium just by the power of "evolution across different environments" they might hit jackpot earlier than bigger labs.

But they rely on distilling the output of american leader models. Which will probably train against their own harness.

Someone has to do the baseline training, development, and innovation. it can't be clones all the way down

Re: Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed

#95

Post by bitwize »

fazgha wrote: post #71
logicprog wrote: post #65

I really enjoyed this article. I think the author is precisely right and I've been saying this for a long time. There's a ton of extremely interesting low hanging fruit that can vastly improve the effectiveness of even currently existing models hiding in how we design our agent harnesses; enough to — at least until we hit diminishing returns — make as much or more of a difference than training new models! I think one…

[flagged]

I use Compose - - - on Linux and my cellphone (Unexpected Keyboard). Mac is Alt-_.

Re: Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed

#96

Post by giancarlostoro »

One of the first things I add to my claude instructions file is to stop using grep, its awfully slow, just use ripgrep instead, you can just type the word of what you're looking for from the project root and find it all in one shot. Claude likes to go folder by folder with grep and it drives me crazy.

"You're absolutely right!"

At this point I'd take a contract with Anthropic to have Claude code pick better tooling.

Re: Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed

#97

Post by throwup238 »

fazgha wrote: post #71
logicprog wrote: post #65

I really enjoyed this article. I think the author is precisely right and I've been saying this for a long time. There's a ton of extremely interesting low hanging fruit that can vastly improve the effectiveness of even currently existing models hiding in how we design our agent harnesses; enough to — at least until we hit diminishing returns — make as much or more of a difference than training new models! I think one…

[flagged]

Does your friend have an iPhone? The default iOS keyboard has automatically converted double dashes into an emdash for at least seven years now.

Re: Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed

#98

Post by kachapopopow »

logicprog wrote: post #86
kachapopopow wrote: post #73

Earlier quoted context omitted.

why the long -'s

Because I like them?

reminds me of that one guy complaining that everyone is calling them an AI when AI was trained on their grammar style.
Post reply on HN