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

171–180 of 765 posts

Re: Promising results from DeepSeek R1 for code

#171

Post by buyucu »

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…

DeepSeek-R1-Distill-Qwen-32B is my new default model on my home server. previously it was aya-32b.

Re: Promising results from DeepSeek R1 for code

#172

Post by jeswin »

myrmi wrote: post #131
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 feel uncomfortably called out by all three points. What tools should I be trying to see what you are?

I use my own tools and scripts, and those aren't for everyone - so I'm just gonna make some general suggestions.

1. You should try Aider. Even if you don't end up using it, you'll learn a lot from it.

2. Conversations are useful and important. You need to figure out a way to include (efficiently, with a few clicks) the necessary files into the context, and then start a conversation. Refine the output as a part of the conversation - by continuously making suggestions and corrections.

3. Conversational editing as a workflow is important. A better auto-complete is almost useless.

4. Github copilot has several issues - interface is just one of them. Conversational style was bolted on to it later, and it shows. It's easier to chat on Claude/Librechat/etc and copy files back manually. Or use a tool like Aider.

5. While you can apply LLMs to solve a particular lower level detail, it's equally effective (perhaps more effective) to have a higher level conversation. Start your project by having a conversation around features. And then refine the structure/scaffold and drill-down to the details.

6. Gradually, you'll know how to better organize a project and how to use better prompts. If you are familiar with best practices/design patterns, they're immediately useful for two reasons. (1) LLMs are also familar with those, and will help with prompt clarity; (2) Modular code is easier to extend.

7. Keep an eye on better performing models. I haven't used GPT-4o is a while, Claude works much, much better. And sometimes you might want to reach for o1 models. Other lower-end models might not offer any time savings; so stick to top tier models you can afford. Deepseek models have brought down the API cost, so it's now affordable to even more people.

8. Finally, it takes time. Just as any other tool.

Re: Promising results from DeepSeek R1 for code

#173

Post by LeFantome »

sitkack wrote: post #78
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…

We have already entered a new paradigm of software development, where small teams build software for themselves to solve their own problems rather than making software to sell to people. I think selling software will get harder in the future unless it comes with special affordances.

I think some of the CEOs have it right on this one. What is going to get harder is selling “applications” that are really just user friendly ways of getting data in and out of databases. Honestly, most enterprise software is just this.

AI agents will do the same job.

What will still matter is software that constrains what kind of data ends up in the database and ensures that data means what it is supposed to. That software will be created by local teams that know the business and the data. They will use AI to write the software and test it. Will those teams be “developers”? It is probably semantics or a matter of degree. Half the people writing advanced Excel spreadsheets today should probably be considered developers really.

Re: Promising results from DeepSeek R1 for code

#174

Post by matsemann »

nkozyra wrote: post #116
matsemann wrote: post #97

Earlier quoted context omitted.

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.

> If anything we're the last generation that knows how to debug and work through issues. I suspect that comment might soon feel like saying "not too worried about assembly line robots, we're the only ones who know how to screw on the lug nuts when they pop off"

Heh, yeah. But the llm in this instance only wrote 99% after the author guided it and prompted over and over again and even guided it how to start certain lines. I can do that. But can a beginner ever get to that level when not having that underlying knowledge?

Re: Promising results from DeepSeek R1 for code

#175

Post by littlestymaar »

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…

I couldn't agree more.

And this kind of fear mongering is particularly irritating when you see that our industry already faced a similar productivity shock less than twenty years ago: before open source went mainstream github and library hubs like npm we used to code the same things over and over again, most of the time in a half-backed fashion because nobody had time for polishing stuff that was needed but only tangentially related to the code business. Then came the open-source tsunami, and suddenly there was a high quality library for solving your particular problem and the productivity gain was insane.

Fast forward a few years, does it look like this productivity gains took any of our jobs? Quite the opposite actually, there has never been as many developers as today.

(Don't get me wrong, this is massively changing how we work, like the previous revolution did, and how job is never going to be the same again)

Re: Promising results from DeepSeek R1 for code

#176

Post by dumbfounder »

matsemann wrote: post #97
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.

Yep, and we still need COBOL programmers too. Your job as a technologist is to keep up with technology and use the best tools for the job to increase efficiency. If you don’t do this you will be left behind or you will be relegated to an esoteric job no one wants.

Re: Promising results from DeepSeek R1 for code

#177

Post by 6510 »

cjbgkagh wrote: post #46
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.…

Who would the new applications be for? I figure that it’ll be far easier to build apps for use by LLMs than building apps for people to use. I don’t think there will be this large increase of induced demand, the whole world just got a lot more efficient and that’s probably a bad thing for the average person.

Oh right, we will have a B2B B2C B2L L2B L2C and ultimately the L2L market.

Re: Promising results from DeepSeek R1 for code

#178

Post by aibot923 »

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…

It's interesting. Maybe I'm in the bigtech bubble, but to me it looks like there isn't enough work for everyone already. Good projects are few and far between. Most of our effort is keeping the lights on for the stuff built over the last 15-20 years. We're really out of big product ideas.

Re: Promising results from DeepSeek R1 for code

#179

Post by buyucu »

blakesterz wrote: post #4
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…

Is DeepSeek really that big of a deal that everyone else should worry?

There are two things. First, deepseek v3 and r1 are both amazing models.

Second, the fact that deepseek was able to pull this off with such modest resources is an indication that there is no moat, and you might wake up tomorrow and find an even better model from a company you have never heard of.

Post reply on HN