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

Promising results from DeepSeek R1 for code

simonwillison.net

Post reply on HN
Print view View original

761–765 of 765 posts

Re: Promising results from DeepSeek R1 for code

#761

Post by fennecfoxy »

skeaker wrote: post #475
aithrowawaycomm wrote: post #296

Earlier quoted context omitted.

Reading through the PR makes me glad I got off GitHub - not for anything AI-related, but because it has become a social media platform, where what should be a focused and technical discussion gets derailed by strangers waging the same flame wars you can find anywhere else.

This depends pretty heavily on the repo.

And applies to any platform with a level of public interactions. Also, people can restrict opening issues/leaving comments etc to only collaborators on their repo if they want to.

Re: Promising results from DeepSeek R1 for code

#762

Post by fennecfoxy »

jeswin wrote: post #31

> 99% of the code in this PR [for llama.cpp] is written by DeekSeek-R1 I hope we can put to rest the argument that LLMs are only marginally useful in coding - which are often among the top comments on many threads. I suppose these arguments arise from (a) having used only GH copilot which is the worst tool, or (b) not having spent enough time with the tool/llm, or (c) apprehension. I've given up responding to these.…

I'm not entirely worried, yet. I don't think that LLMs produce code/architecture that is trustworthy enough for them to operate independently. Of course suits & ties will believe it and kill many dev jobs eventually, but as per usual wtf do they know about how things work on the ground. Executives thrive on NYT articles and hearsay from LinkedIn.

Re: Promising results from DeepSeek R1 for code

#763

Post by momo_O »

brianstrimp wrote: post #727
anotherpaulg wrote: post #712

Earlier quoted context omitted.

Every metric has limitations, but git blame line counts seem pretty uncontroversial. Typical aider changes are not like autocompleting braces or reformatting code. You tell aider what to do in natural language, like a pair programmer. It then modifies one or more files to accomplish that task. Here's a recent small aider commit, for flavor. -# load these from aider/resources/model-settings.yml -# use the proper packa…

Point is that not all lines are equal. The 30% that the tool didn't make are the hard stuff. Not just in line count. Once an approach or an architecture or a design are clear then implementing is merely manual labor. Progress is not linear. You shouldn't judge your sw eng employees by lines of code either. Those that think the hard stuff often don't have that many lines of code checked in. But it's those people that…

I don't think any reasonable person is using "lines of code" as a hard metric for anything -- as you've noted, the quality and impact of code isn't proportional to its length.

Lines of code serves as a directional heuristic at best, but that's ok.

Re: Promising results from DeepSeek R1 for code

#764

Post by ban-evader »

brianstrimp wrote: post #727
anotherpaulg wrote: post #712

Earlier quoted context omitted.

Every metric has limitations, but git blame line counts seem pretty uncontroversial. Typical aider changes are not like autocompleting braces or reformatting code. You tell aider what to do in natural language, like a pair programmer. It then modifies one or more files to accomplish that task. Here's a recent small aider commit, for flavor. -# load these from aider/resources/model-settings.yml -# use the proper packa…

Point is that not all lines are equal. The 30% that the tool didn't make are the hard stuff. Not just in line count. Once an approach or an architecture or a design are clear then implementing is merely manual labor. Progress is not linear. You shouldn't judge your sw eng employees by lines of code either. Those that think the hard stuff often don't have that many lines of code checked in. But it's those people that…

And you think this is news to any of us?

Re: Promising results from DeepSeek R1 for code

#765

Post by kragen »

Vegenoid wrote: post #744
kragen wrote: post #733

Earlier quoted context omitted.

People posting comments without caring whether they are true or false undermines the presumption of good faith that underlies rational discourse. Please stop posting such comments on this site. Instead, only post comments that you have some reason to believe are true.

It is not about not caring if the statement is true or false. The statement neither absolutely true nor absolutely false, because there is no absolute definition of when software engineering started, or what "a lifetime" is. It is about making a statement that communicates information. However, if I must prove that my statement can reasonably considered "true" in order to prove that it does communicate the short span…

Fair enough.
Post reply on HN