Promising results from DeepSeek R1 for code • Hacker News Board

Re: Promising results from DeepSeek R1 for code

#91

Post by byteknight » Tue, Jan 28, 2025, 4:36 PM UTC

chrisguilbeau wrote: post #75

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 a developer that primarily uses gh copilot for python dev. I find it pretty useful as an intelligent auto-completer that understands our project's style, and unusual decorators we use. What tools would you tell a copilot dev to try? For example, I have a $20/mo ChatGPT account and asking it to write code or even fix things hasn't worked very well. What am I missing?

While I dont know your scenario as an avid user of both gpt and claude, I would recommend move away from Google style search queries, and begin conversing. The more you give the LLM the more you'll get close to what you want.

Re: Promising results from DeepSeek R1 for code

#92

Post by SecretDreams » Tue, Jan 28, 2025, 4:37 PM UTC

simonw wrote: post #52

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.…

"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…

The big fear shouldn't be on loss of jobs, it should be the inevitable attack on wages. Wage will track inversely to proximity as a commodity status.

Even the discussion around AI partially replacing coders is a direction towards commoditization.

Re: Promising results from DeepSeek R1 for code

#93

Post by dluan » Tue, Jan 28, 2025, 4:37 PM UTC

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…

> Chinese government backed conspiracy

Do you understand how ginormous China is and how ridiculous this kind of made up boogeyman statement sounds?

Re: Promising results from DeepSeek R1 for code

#94

Post by lgats » Tue, Jan 28, 2025, 4:38 PM UTC

mohsen1 wrote: post #33

simonw wrote: post #26

Earlier quoted context omitted.

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

added context, deepseek is having ddos issues https://status.deepseek.com/

Re: Promising results from DeepSeek R1 for code

#95

Post by UncleOxidant » Tue, Jan 28, 2025, 4:38 PM UTC

simonw wrote: post #52

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.…

"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.

And yet many companies aren't hiring developers right now - folks in the C suite are thinking AI is going to be eliminating their need to hire engineers. Also "demand" doesn't necessarily mean that there's money available to develop this code. And remember that when code is created it needs to be maintained and there are costs for doing that as well.

Re: Promising results from DeepSeek R1 for code

#96

Post by headcanon » Tue, Jan 28, 2025, 4:39 PM UTC

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.…

Agreed, though to your point I think we'll end up seeing more induced demand long-term

- This will enable more software to be built and maintained by same or fewer people (initially). Things that we wouldn't previously bother to do are now possible.

- More software means more problems (not just LLM-generated bugs which can be handled by test suites and canary deploys, but overall features and domains of what software does)

- This means skilled SWEs will still be in demand, but we need to figure out how to leverage them better.

- Many codebases will be managed almost entirely by agents, effectively turning it into the new "build target". This means we need to build more tooling to manage these agents and keep them aligned on the goal, which will be a related but new discipline.

SWEs would need to evolve skillsets but wasn't that always the deal?

Re: Promising results from DeepSeek R1 for code

#97

Post by matsemann » Tue, Jan 28, 2025, 4:39 PM UTC

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 read that Meta is tasking all engineers with figuring out how they got owned by deepseek. Couldn't they just have asked an llm instead? After their claim of replacing all of us...

I'm not too worried. If anything we're the last generation that knows how to debug and work through issues.

Re: Promising results from DeepSeek R1 for code

#98

Post by nine_zeros » Tue, Jan 28, 2025, 4:40 PM UTC

happyopossum wrote: post #71

nine_zeros wrote: post #50

Earlier quoted context omitted.

> 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 This is a key insight - the trade has changed. For a long time, hoarding talent - who could conceive and implement such PRs - was a competitive advantage. It no longer is because companies can hire a…

> literally a single Deepseek release yesterday destroyed large market cap companies Nobody was “destroyed” - a handful of companies had their stock price drop, a couple had big drops, but most of those stocks are up today, showing that the market is reactionary.

Alright, if this is more palatable - let's just say market caps will decline because of small code updates made anywhere in the world.

The point still is: Software/engineering is no longer the moat creator.

Re: Promising results from DeepSeek R1 for code

#99

Post by simonw » Tue, Jan 28, 2025, 4:41 PM UTC

UncleOxidant wrote: post #95

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. And yet many companies aren't hiring developers right now - folks in the C suite are thinking AI is going to be eliminating their need to hire engineers. Also "dema…

I continue to suspect that the hiring problems are mainly due to massive over-hiring during Covid, followed by layoffs that flooded the market with skilled developers looking for work.

I'd love to see numbers around the "execs don't think they need engineers because of AI" factor. I've heard a few anecdotal examples of that but it's hard to tell if it's a real trend or just something that catches headlines.

Re: Promising results from DeepSeek R1 for code

#100

Post by mjr00 » Tue, Jan 28, 2025, 4:41 PM UTC

simonw wrote: post #79

mjr00 wrote: post #72

Earlier quoted context omitted.

> 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. Look at the code that was changed[0]. It's a single file. From what I…

"Yeah, but LLMs can't handle millions of lines of crufty old Java" is a guaranteed reply any time this topic comes up. (That's not to say it isn't a valid argument.) Short answer: LLMs are amazingly useful on large codebases, but they are useful in different ways. They aren't going to bang out a new feature perfectly first time, but in the right hands they can dramatically accelerate all sorts of important activities…

Yes, LLMs are very useful, when used properly. But the linked change request is not a good example of how they would be used by a typical software developer. The linked pull request is essentially output from a compiler that's been hardcoded.

> Writing individual functions, classes and modules. You have to be good at software architecture and good at prompting to use them in this way - you take on the role of picking out the tasks that can be done independently of the rest of the code.

If you have enough skill and understanding to do this, it means you already have enough general software development experience and domain-specific experience and experience with a specific, existing codebase to be in rarefied air. It's like saying, oh yeah a wrench makes plumbing easy. You just need to turn the wrench, and 25 years of plumbing knowledge to know where to turn it.

> Writing tests - again, if you have the skill and experience to prompt them in the right way.

This is very true and more accessible to most developers, though my big fear is it encourages people to crap out low-value unit tests. Not that they don't love to do that already.