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

241–250 of 765 posts

Re: Promising results from DeepSeek R1 for code

#241

Post by kadushka »

LeFantome wrote: post #145
jeswin wrote: post #86

Earlier quoted context omitted.

> 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…

Think of how much easier it is to learn to code if you actually want to. The mantra has always been that the best way to learn to code is to read other people’s code. Now you can have “other people” write you code for whatever you want. You can study it and see how it works. You can explore different ways of accomplishing the same tasks. You can look at the similar implementations in different languages. And you may…

People get wicked good by solving hard problems. Many young developers use AI to solve problems with little effort. Not sure what effect this will have on the quality of future developers.

Re: Promising results from DeepSeek R1 for code

#242

Post by rane »

lukan wrote: post #191
rane wrote: post #184

Earlier quoted context omitted.

The idea is that you give the libraries and APIs as context with your prompt.

Thank you. But that doesn't work for me. If you mean just the name of the version in the prompt? No way. If you mean all the libary and my code in the contextwindow? Way too small.

Not _all_ the code. Just the relevant parts.

Re: Promising results from DeepSeek R1 for code

#243

Post by chefandy »

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.…

GH copilot code completion is really the only one I’ve found to be consistently more of a benefit than a time sync. Even with the spiffy code generators using Claude or whatever, I often find myself spending as much time figuring out where the logical problem is than if I had just coded it myself, and you still need to know exactly what needs to be done.

I’d be interested in seeing how much time they spent debugging the generated code and and how long they spent constructing and reconstructing the prompts. I’m not a software developer anymore as my primary career, so if the entire lower-half of the software development market went away catering wages as it did, it wouldn’t directly affect my professional life. (And with the kind of conceited, gleeful techno-libertarian shit I’ve gotten from the software world at large over the past couple of years as a type of specialized commercial artist, it would be tough to turn that schadenfreude into empathy. But we honestly need to figure out a way to stick together or else we’re speeding towards a less mechanical version of Metropolis.)

Re: Promising results from DeepSeek R1 for code

#244

Post by gamblor956 »

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…

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.

Most companies don't have a milelong backlog of coding projects. That's a uniquely tech industry-specific issue, and a lot of it is driven by the tech industry's obsessive compulsion to perpetually reinvent wheels.

Companies that would never have considered building 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.

No, because most companies that can afford custom software want reliable software. Downtime is money. Getting unreliable custom software means that the next time around they'll just adapt their business processes to software that's already available on the market.

Re: Promising results from DeepSeek R1 for code

#245

Post by plainOldText »

herval wrote: post #214
plainOldText wrote: post #201

Earlier quoted context omitted.

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 w…

Until now, the march of technology has taken place through a realm which was somewhat limited or slowed down only by our advancements in the physical and cognitive realities. This has given us ample time to catch up, to adjust.

The cognitive reality of AI, and more specifically of AI+Humans in the context of a social and globally connected world, is on a higher level of sophistication and can unfold much faster, which in turn might generate entirely unexpected trajectories.

Re: Promising results from DeepSeek R1 for code

#246

Post by Barrin92 »

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"

I don't even see the irony in the comparison to be honest, being the assembly line robot controller and repairman is quite literally a better job than doing what the robot does by hand.

If you're working in a modern manufacturing business the fact that you do your work with the aid of robots is hardly a sign of despair

Re: Promising results from DeepSeek R1 for code

#247

Post by astrobe_ »

simonw wrote: post #60
TheBigSalad wrote: post #55

Earlier quoted context omitted.

LLMs are only marginally useful for coding. You have simply chosen to dismiss or or 'give up' on that fact. You've chosen what you want to believe in contrast to the reality that we are all experiencing.

LLMs are incredibly useful for coding, if you learn how to apply them effectively. You have simply chosen to dismiss or 'give up' on that fact.

I think the reality is that these AI output the "average" of what was in their training set, and people receive it differently depending on if they are below or above this average.

It's a bit like what happens with "illusion of knowledge" or "illusion of understanding". When one knows the topic, one can correct the output of AI. When one doesn't, one tends to forget it can be inaccurate or plain wrong.

Re: Promising results from DeepSeek R1 for code

#248

Post by nine_zeros »

djmips wrote: post #158
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…

You write this as if DeepSeek's R1 was conceived and written by AI itself. Do you have a link to that?

Of course R1 wasn't written by AI. But the point is that in the past, such high quality software could only be written in a concentrated location - SV - because of computing resources and people who could use those computing resources.

Then in the 00s, the computing resources became widely available. The bottleneck was the people who could build interesting things. Imagine a third world country with access to AWS but no access to developers who could build something meaningful.

With these models, now these geographically distributed companies can build similarly high quality stuff.

R1 IS the example of something that previously only could be built in the bowels of large SV corporations.

Re: Promising results from DeepSeek R1 for code

#249

Post by minkzilla »

tantalor wrote: post #84
gejose wrote: post #54

Earlier quoted context omitted.

How long do you see the humans in the loop being necessary?

Where companies depend on code for business critical applications? Forever. When your AI-managed codebase breaks, who are you going to ask to fix it? The AI?

Yes.

Re: Promising results from DeepSeek R1 for code

#250

Post by simonw »

jvanderbot wrote: post #187
simonw wrote: post #112

Earlier quoted context omitted.

"Or, how do you get them to use a recent API that doesn't dominate their training data?" Paste in the documentation or some examples. I do this all the time - "teaching" an LLM about an API it doesn't know yet is trivially easy if you take advantage of the longer context inputs to models these days.

I've tried this. I've scraped example pages directly from github, and given them a 200 line file with the instructions "just insert this type of thing", and it will invariably use bad APIs. I'd be happy to share the example with you.

Go for it - can you share it in a Gist?

I use this technique all the time. Here's one written-up example: https://simonwillison.net/2024/Mar/30/ocr-pdfs-images/ - transcript here: https://gist.github.com/simonw/6a9f077bf8db616e44893a24ae1d3...

Post reply on HN