Live data from Hacker News

Interview with Boris Cherny [video]

youtube.com

81–87 of 87 posts

Re: Interview with Boris Cherny [video]

#81
post #3

The TL;DR of the fragment at around 6:57 in the video, for those who don't want to watch, is that Boris recommends to delete all the customizations, CLAUDE.md, skills, and other stuff you had for older models, and try using the new models without all that, because the new models can surprise you.

What if I don't use customizations at all, bare prompt per feature or function only? Do those customizations help?

Re: Interview with Boris Cherny [video]

#82
post #68
post #62

Earlier quoted context omitted.

Seems like something they should work on, not customers. Reinventing my workflow every six months because a company/product is lazy is not high on my list.

What I read from that is that there's a chance claude gets worse using a claude.md and that's a usability issue on their side.

I've seen this particular in the post and others from Anthropic make similar claims of "oh, just do this or that", and I've always been of the opinion: "isn't this what everyone is paying Anthropic to do?".

Re: Interview with Boris Cherny [video]

#83
post #10

I feel like the Big Insight with Claude Code was 'give the AI access to tools, in fact to your actual laptop'. And of course 1.5 years later 'a harness to enable an agent to use my computer' has turned into the flagship product we expect from frontier labs However. I don't think all the other 'Ideas' these harness-building guys have are all that universally applicable. Heck they are naysaying their own gearhead stack…

> And there is a lot missing in the actual harnesses frankly that isn't about more parallel agent ninjutsu. Like why isn't there a 'move this function from this file to this file' tool (copy/paste char range) and we have to see Claude/Codex/etc flail around rewriting huge chunks of code in token space

This is a very important point. There's so much missing in software development that we've gone from zero to one hundred without considering the in between. Same thing happened with electric cars and automated driving. Everyone decided that we should go from no driver assistance to full-self driving instead of incrementally building up driver assistance features. This is similar. We and these AI tools need better semantic tooling for dealing with software development. Otherwise, like you say, these AI tools are just going to flail about as much as we do. It's pretty ridiculous our version control systems still operate on objects that are just lines of text.

Re: Interview with Boris Cherny [video]

#84
post #23

Earlier quoted context omitted.

Come on what are we talking about. Ruff is a linter. Can you show me any LSP server that can move an arbitrary function from file1.ts to file2.ts based on calling it on the command line?

They're not command line applications, they use JSON-RPC inline, and it's an interactive flow, so you need the client to actually persist state. So what you'd see in the LLM traces, for example, is a couple back-and-forths using JSON-RPC. It absolutely works at the moment, and claude code will happily use it if everything is set up correctly, just tested it using https://github.com/typescript-language-server/typescri…

You're basically just agreeing with the original comment that these tools don't do what's stated.

And in my experience, Claude Code will often ignore LSPs, despite instructing Claude to use them and have them installed through Claude, and revert to using grep and sed.

Re: Interview with Boris Cherny [video]

#85
post #83
post #10

I feel like the Big Insight with Claude Code was 'give the AI access to tools, in fact to your actual laptop'. And of course 1.5 years later 'a harness to enable an agent to use my computer' has turned into the flagship product we expect from frontier labs However. I don't think all the other 'Ideas' these harness-building guys have are all that universally applicable. Heck they are naysaying their own gearhead stack…

> And there is a lot missing in the actual harnesses frankly that isn't about more parallel agent ninjutsu. Like why isn't there a 'move this function from this file to this file' tool (copy/paste char range) and we have to see Claude/Codex/etc flail around rewriting huge chunks of code in token space This is a very important point. There's so much missing in software development that we've gone from zero to one hund…

[flagged]

Re: Interview with Boris Cherny [video]

#86
post #41

Earlier quoted context omitted.

There’s really not much to specialize in and differentiate yourself. All this harness customization is fleeting. Remember prompt engineering?

To be fair prompts is just English language intent abstracted for code. It is still am very much a thing. Why do you feel that harness customization is fleeting, enterprises care about them a lot for many reasons from compliance to security.

From the point of view of a developer looking to differentiate themselves. The instinct is to look for generalizations, abstractions, composability, but as Boris says, these just get subsumed into the latest model RL. So what expertise is left for the developer to invest in?

Re: Interview with Boris Cherny [video]

#87
post #53

Earlier quoted context omitted.

That is the interesting part to me. Also, was anyone else familiar with the LLM-app terms "ablation" and "product overhang," prior to this? I was not. If you were, please share the knowledge with us. Where can I learn more?

Ablation is a medical term, he's just using it generically to describe removing existing config.

I only knew ablation from spaceflight re-entry. I should have been more clear. I had never heard those words in terms of software products.
Post reply on HN