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

211–220 of 765 posts

Re: Promising results from DeepSeek R1 for code

#211

Post by ksec »

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…

>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.

We really are in AI moment of iPhone. I never thought I would witness something bigger than the impact of Smartphone. There are insane amount of value that we could extract out. Likely in tens of trillions from big to small business.

We keep asking how Low Code or No Code "tools" could achieve custom apps. Turns out we are here via a different route.

>custom software because they'd need a team of 6 working for 12 months may now hire developers if they only need 2 working for 3 months to get something useful.

I am wondering if it be more like 2 working for 1 month?

Re: Promising results from DeepSeek R1 for code

#212

Post by nkassis »

agsqwe wrote: post #188
aibot923 wrote: post #178

Earlier quoted context omitted.

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.

This is very similar to my experience as a software development agency to enterprise customers. Out of big product ideas.

Yes a capacity increase from the developer side is great but it's supply side and we need to figure out how to accelerate transforming needs into demand. This is what I foresee developers turning into (at least some capable of this). Articulating logical solutions to be built to problems and evaluating results from what's generated to ensure it meets the needs.

Aka Devs can move up the chain into what was traditionally product roles to increase development of new projects. This is using the time they have regain from more menial tasks being automated away.

Re: Promising results from DeepSeek R1 for code

#213

Post by lukan »

AlwaysRock wrote: post #207
lukan wrote: post #109

Earlier quoted context omitted.

"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…

We are getting closer and closer to that. For a while llm assistants were not all that useful on larger projects because they had limited context. That context has increased a lot over the last 6 months. Some tools will even analysis your entire codebase and use that in responses. It is frustrating that any smaller tool or api seem to stump llms currently but it seems like context is the main thing that is missing an…

I have not kept up, can you recommend something?

Re: Promising results from DeepSeek R1 for code

#214

Post by herval »

plainOldText wrote: post #201
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.…

Indeed, our trade has changed forever, and more specifically, we might have to alter our operational workflows in the entire industry as well. There are so many potential trajectories going forward for things to turn sour, I don't even know where to start the analysis. The level of sophistication an AI can achieve has no upper bound. I think we've had a good run so far. We've been able to produce software in the open…

I don't think trusting that someone wrote the code was ever a good assurance of anything, and I don't see how that changes with AI. There will always be certain _individuals_ who are more reliable than others, not because they handcraft code, but because they follow through with it (make sure it works, fix bugs after release, keep an eye to make sure it worked, etc).

Yes, AI will enable exponentially more people to write code, but that's not a new phenomenon - bootcamps enabled an order of magnitude more people to become developers. So did higher level languages, IDEs, frameworks, etc. The march of technology has always been about doing more while having to understand less - higher and higher levels of abstraction. Isn't that a good thing?

Re: Promising results from DeepSeek R1 for code

#215

Post by yobbo »

fragmede wrote: post #143
cjbgkagh wrote: post #46

Earlier quoted context omitted.

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.

take some process that you, or someone you know does right now that involves spreadsheets and copy-pasting between various apps. hiring a software engineer to build an app so it's just a [do-it] button previously didn't make sense because software engineer time was too expensive. Now, that app can be made, so the HR or whatever person doesn't need to waste their time on automatable tasks.

If their time was actually wasted, paying a few or several thousand dollars for a tool would have been profitable a long time ago.

Usually, there are hidden payoffs that motivate things that seem like waste.

Re: Promising results from DeepSeek R1 for code

#216

Post by Imanari »

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…

Love aider, thank you for your work! Out of curiousity, what are your future plans and ideas for aider in terms of features and workflow?

Re: Promising results from DeepSeek R1 for code

#217

Post by simonw »

lukan wrote: post #213
AlwaysRock wrote: post #207

Earlier quoted context omitted.

We are getting closer and closer to that. For a while llm assistants were not all that useful on larger projects because they had limited context. That context has increased a lot over the last 6 months. Some tools will even analysis your entire codebase and use that in responses. It is frustrating that any smaller tool or api seem to stump llms currently but it seems like context is the main thing that is missing an…

I have not kept up, can you recommend something?

My review of 2024 is a good place to catch up on what's changed in the past 12 months: https://simonwillison.net/2024/Dec/31/llms-in-2024/

Re: Promising results from DeepSeek R1 for code

#218

Post by mrtesthah »

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

You can run it through Openrouter/Fireworks hosted in the US.

Re: Promising results from DeepSeek R1 for code

#219

Post by plandis »

antonislav wrote: post #144
simonw wrote: post #90

Earlier quoted context omitted.

Yeah, it's going to suck for junior developers for a while. The ones who are self-starters will do fine - they'll figure out how to accelerate their way up the learning curve using these new tools. People who prefer classroom-learning / guided education are going to be at a disadvantage for a few years while the education space retools for this new world.

I think, seeing recordings of people using LLMs to accomplish non-trivial tasks would go a long way. I’d love to watch, e.g. you Simon, using these tools. I assume there are so many little tricks you figured out over time that together make a big difference. Things that come to mind: - how to quickly validate the output? - what tooling to use for iterating back and forth with the LLM? (just a chat?) - how to steer th…

I believe Simon has full transcripts for some of the projects he’s had LLMs generate the code for. You can see how he steers the LLM for what is desired and how it is course corrected.

Re: Promising results from DeepSeek R1 for code

#220

Post by motorest »

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…

> 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 testing times for so many of them.

I don't agree. LLMs work as template engines on steroids. The role of a developer now includes more code reviewing than code typing. You need the exact same core curriculum to be able to parse code, regardless if you're the one writing it, it's a PR, or it's outputted by a chatbot.

> For example, if you're writing web apps, you need to be able to spot say security issues. And various other best practices, depending on what you're making.

You're either overthinking it or overselling it. LLMs generate code, but that's just the starting point. The bulk of developer's work is modifying your code to either fix an issue or implement a feature. You need a developer to guide the approach.

Post reply on HN