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

101–110 of 765 posts

Re: Promising results from DeepSeek R1 for code

#101

Post by JKCalhoun »

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.…

> When companies claim that AI will replace developers, it isn't entirely bluster.

I'm not so sure there isn't a bit of bluster in there. Imagine when you hand-coded in either machine code or assembly and then high level languages became a thing. I assume there was some handwringing then as well.

Re: Promising results from DeepSeek R1 for code

#102

Post by WhitneyLand »

20k wrote: post #74
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.…

Eh it performed a 1:1 conversion of ARM NEON to wasm SIMD, which with the greatest will in the world is pretty trivial work. Its something that ML is good at, because its the same problem area as "translate this from english to french", but more mechanistic This is a task that would likely have taken as long to write by hand as the AI took to do it, given how long the actual task took to execute. 98% of the work is f…

Every time AI achieves something new/productive/interesting, cue the apologists who chime in to say “well yeah but that really just decomposes into this stuff so it doesn’t mean much”.

I don’t get why people don’t understand that everything decomposes into other things.

You can draw the line for when AI will truly blow your mind anywhere you want, the point is the dominoes keep falling relentlessly and there’s no end in sight.

Re: Promising results from DeepSeek R1 for code

#103

Post by jvanderbot »

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.…

This is great. Really! Buuut...

How do you get these tools to not fall over completely when relying on an existing non-public codebase that isn't visible in just the current file?

Or, how do you get them to use a recent API that doesn't dominate their training data?

Combining the both, I just cannot for the life of me get them to be useful beyond the most basic boilerplate.

Arguably, SIMD intrinsics are a one-to-one translation boilerplate, and in the case of this PR, is a leetcode style, well-defined problem with a correct answer, and an extremely well-known api to use.

This is not a dig on LLMs for coding. I'm an adopter - I want them to take my work away. But this is maybe 5% of my use case for an LLM. The other 95% is "Crawl this existing codebase and use my APIs that are not in this file to build a feature that does X". This has never materialized for me -- what tool should I be using?

Re: Promising results from DeepSeek R1 for code

#104

Post by lenerdenator »

simonw wrote: post #57
lenerdenator wrote: post #53

Earlier quoted context omitted.

My greatest problem is duplicating the secret sauce of GHCP: it has access to your project and can use it as context. Admittedly, I haven't looked too hard, but how could I do that with a model from, say, Ollama and run exclusively on my machine?

There are a bunch of tools that might be able to do that. I'd start by exploring https://aider.chat/

I'll take a look, thank you!

Re: Promising results from DeepSeek R1 for code

#105

Post by thefourthchime »

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.…

There is a near-infinite demand for more applications. They simply become more specific and more niche. You can think to a point where everyone has their own set of applications custom for the exact workflow that they like.

Just look at the options dialogue for Microsoft Word at least back in the day. It was pretty much everyone's pet feature over the last 10 years.

Re: Promising results from DeepSeek R1 for code

#106

Post by joshstrange »

anotherpaulg wrote: post #61

> 99% of the code in this PR [for llama.cpp] is written by DeekSeek-R1 It's definitely possible for AI to do a large fraction of your coding, and for it to contribute significantly to "improving itself". As an example, aider currently writes about 70% of the new code in each of its releases. I automatically track and share this stat as graph [0] with aider's release notes. Before Sonnet, most releases were less than…

First off I want to thank you for Aider. I’ve had so much fun playing with it and using it for real work. It’s an amazing tool.

How do you determine how much was written by you vs the LLM? I assume it consists of parsing the git log and getting LoC from that or similar?

If the scripts are public could you point me at them? I’d love to run it on a recent project I did using aider.

Re: Promising results from DeepSeek R1 for code

#107

Post by onetimeusename »

jeswin wrote: post #86
simonw wrote: post #52

Earlier quoted context omitted.

"Jobs are going to be lost unless there's somehow a demand for more applications." That's why I'm not worried. There is already SO MUCH more demand for code than we're able to keep up with. Show me a company that doesn't have a backlog a mile long where most of the internal conversations are about how to prioritize what to build next. I think LLM assistance makes programmers significantly more productive, which makes…

> That's why I'm not worried. There is already SO MUCH more demand for code than we're able to keep up with. Show me a company that doesn't have a backlog a mile long where most of the internal conversations are about how to prioritize what to build next. I worry about junior developers. It will be a while before vocational programming courses retool to teach this new way of writing code, and these are going to be te…

Just as a side note, at my university about half the CS people are in the AI track. I would guess that number will keep increasing. There is also a separate major that kind of focuses on AI/psychology that is pretty popular but I am not sure how many people are in it. A good number of the students have some kind of "AI startup". Also, although it violates the honor code, I would be willing to bet many students use AI in some way for doing programming assignments.

This isn't to say you are wrong but just to put some perspective on how things are changing. Maybe most new programmers will be hired into AI roles or data science.

Re: Promising results from DeepSeek R1 for code

#108

Post by simonw »

dluan wrote: post #93
simonw wrote: post #24

Earlier quoted context omitted.

There are a bunch of theories floating round. Personally this looks to me like an ego thing: the DeepSeek team are really, really good and their CEO is enjoying the enormous attention they are getting, plus the pride of proving that Chinese AI labs can take the lead in a field that everyone thought the USA was unassailable in. Maybe they are true believers in building and sharing "AGI" with the world? Lots of people…

> Chinese government backed conspiracy Do you understand how ginormous China is and how ridiculous this kind of made up boogeyman statement sounds?

Yes.

Re: Promising results from DeepSeek R1 for code

#109

Post by lukan »

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 hope we can put to rest the argument that LLMs are only marginally useful in coding"

I more often heard the argument, they are not useful for them. I agree. If a LLM would be trained on my codebase and the exact libaries and APIs I use - I would use them daily I guess. But currently they still make too many misstake and mess up different APIs for example, so not useful to me, except for small experiments.

But if I could train deepseek on my codebase for a reasonable amount(and they seemed to have improved on the training?), running it locally on my workstation: then I am likely in as well.

Re: Promising results from DeepSeek R1 for code

#110

Post by nkozyra »

lenerdenator wrote: post #53
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.…

My greatest problem is duplicating the secret sauce of GHCP: it has access to your project and can use it as context. Admittedly, I haven't looked too hard, but how could I do that with a model from, say, Ollama and run exclusively on my machine?

Couldn't you load the whole thing into a database or memory and use it as a RAG source? Not sure if that would fully scratch the itch.
Post reply on HN