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

31–40 of 765 posts

Re: Promising results from DeepSeek R1 for code

#31

Post by jeswin »

> 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.

Our trade has changed forever, and there's no going back. When companies claim that AI will replace developers, it isn't entirely bluster. Jobs are going to be lost unless there's somehow a demand for more applications.

Re: Promising results from DeepSeek R1 for code

#32

Post by belter »

miohtama wrote: post #5
simonw wrote: post #3

Given these initial results, I'm now experimenting with running DeepSeek-R1-Distill-Qwen-32B for some coding tasks on my laptop via Ollama - their version of that needs about 20GB of RAM on my M2. https://www.ollama.com/library/deepseek-r1:32b It's impressive! I'm finding myself running it against a few hundred lines of code mainly to read its chain of thought - it's good for things like refactoring where it will thi…

Also even if the answer is incorrect, you can still cook the eggs on the laptop :)

The eggs cost more than the laptop...

Re: Promising results from DeepSeek R1 for code

#33

Post by mohsen1 »

simonw wrote: post #26
tantalor wrote: post #25

> it can optimize its own code This is an overstatement. There are still humans in the loop to do the prompt, apply the patch, verify, write tests, and commit. We're not even at intern-level autonomy here.

Plugging DeepSeek R1 into a harness that can apply the changes, compile them, run the tests and loop to solve any bugs isn't hard. People are already plugging it into existing systems like Aider that can run those kinds of operations.

Yes! I've done something like this here in my repo. This was nice while lasted (Deepseek is practically useless through the API since yesterday)

https://github.com/bodo-run/yek/blob/main/.github/workflows/...

https://github.com/bodo-run/yek/blob/main/scripts/ai-loop.sh

Using askds https://github.com/bodo-run/askds

Re: Promising results from DeepSeek R1 for code

#34

Post by amarcheschi »

For what i can understand, he asked deepseek to convert arm simd code to wasm code.

in the github issue he links he gives an example of a prompt: Your task is to convert a given C++ ARM NEON SIMD to WASM SIMD. Here is an example of another function: (follows a block example and a block with the instructions to convert)

https://gist.github.com/ngxson/307140d24d80748bd683b396ba13b...

I might be wrong of course, but asking to optimize code is something that quite helped me when i first started learning pytorch. I feel like "99% of this code blabla" is useful as in it lets you understand that it was ai written, but it shouldn't be a brag. then again i know nothing about simd instructions but i don't see why it should be different for a capable llm to do simd instructions or optimized high level code (which is much harder than just working high level code, i'm glad i can do the latter lol)

Re: Promising results from DeepSeek R1 for code

#35

Post by Rzor »

netdevphoenix wrote: post #16
simonw wrote: post #7

Earlier quoted context omitted.

Yeah, it is definitely a big deal. I expect it will be a net positive: they proved that you can both train and run inference against powerful models for way less compute than people had previously expected - and they published enough details that other AI labs are already starting to replicate their results. I think this will mean cheaper, faster, and better models. This FAQ about it is very good: https://stratechery…

Why did DeepSeek not kept this for themselves? Is this a Meta style scorched earth strategy?

>An Yong: But DeepSeek is a business, not a nonprofit research lab. If you innovate and open-source your breakthroughs—like the MLA architecture innovation releasing in May—won’t competitors quickly copy them? Where’s your moat?

>Liang Wenfeng: In disruptive tech, closed-source moats are fleeting. Even OpenAI’s closed-source model can’t prevent others from catching up.

>Therefore, our real moat lies in our team’s growth—accumulating know-how, fostering an innovative culture. Open-sourcing and publishing papers don’t result in significant losses. For technologists, being followed is rewarding. Open-source is cultural, not just commercial. Giving back is an honor, and it attracts talent.

https://thechinaacademy.org/interview-with-deepseek-founder-...

Re: Promising results from DeepSeek R1 for code

#37

Post by eptcyka »

simonw wrote: post #24
netdevphoenix wrote: post #16

Earlier quoted context omitted.

Why did DeepSeek not kept this for themselves? Is this a Meta style scorched earth strategy?

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…

It makes Trump look like a chump.

Re: Promising results from DeepSeek R1 for code

#38

Post by jetbalsa »

cft wrote: post #30
simonw wrote: post #27

Earlier quoted context omitted.

DeepSeek v3 or DeepSeek R1?

DeepSeek R1

what work flow where you using to feed it code? was it cline? Cline has major prompting issues with DeepSeek, Deepseek really doesn't like you changing out its prompt with what normal LLMs are using.

Re: Promising results from DeepSeek R1 for code

#40

Post by mclau156 »

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.…

Its cope
Post reply on HN