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

201–210 of 765 posts

Re: Promising results from DeepSeek R1 for code

#201

Post by plainOldText »

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 with contributions from any human on the planet, trusting it was them who wrote the code, and with the expectation that they also understand it.

But now things will change. Any developer, irrespective of skill and understanding of the problem and technical domains can generate sophisticated looking code.

Unfortunately, we've reached a level of operational complexity in the software industry, that thanks to AI, could be exploited in a myriad ways going forward. So perhaps we're going to have to aggressively re-adjust our ways.

Re: Promising results from DeepSeek R1 for code

#202

Post by cyanydeez »

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…

that's basically the AI rubicon everywhere. From flying plans to programming: Soon there'll be no real fallback. When AI fails, you can't just put the controls in front of a person and expect them to have reasonable expertise to respond.

Really, what seems on the horizon is a cliff of techno risks that have nothing to do with "AI will take over the world" and more "AI will be so integral to functional humanity that actual risks become so diffuse that no one can stop it."

So it's more a conceptual belief: Will AI actually make driving cares safer or will the fatalities of AI just be so randomly stochastic that it's more acceptable.

Re: Promising results from DeepSeek R1 for code

#203

Post by smokel »

LeFantome wrote: post #147
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…

“ It's a difficult problem to solve, requiring new sets of books, courses etc.” Instead of this, have you considered asking Deep Seek to explain it to you?

Before this comment is being downvoted, please note the irony. The AI models may solve some technical problems, but the actual problems to be solved are of a societal nature, and won't be solved in our lifetimes.

Re: Promising results from DeepSeek R1 for code

#205

Post by simonw »

WhitneyLand wrote: post #102
20k wrote: post #74

Earlier quoted context omitted.

Eh it performed a 1:1 conversion of ARM NEON to wasm SIMD, which with the greatest will in the world is pretty trivial work. Its something that ML is good at, because its the same problem area as "translate this from english to french", but more mechanistic This is a task that would likely have taken as long to write by hand as the AI took to do it, given how long the actual task took to execute. 98% of the work is f…

Every time AI achieves something new/productive/interesting, cue the apologists who chime in to say “well yeah but that really just decomposes into this stuff so it doesn’t mean much”. I don’t get why people don’t understand that everything decomposes into other things. You can draw the line for when AI will truly blow your mind anywhere you want, the point is the dominoes keep falling relentlessly and there’s no end…

This is called the AI effect - where the goalposts are moved every time an AI system demonstrates a new ability. It's been going on for decades. https://en.wikipedia.org/wiki/AI_effect

Re: Promising results from DeepSeek R1 for code

#206

Post by svachalek »

plainOldText wrote: post #153

I just commented this on a related story, so I'll just repost it here: Can’t help but wonder about the reliability and security of future software. Given the insane complexity of software, I think people will inevitably and increasingly leverage AI to simplify their development work. Nevertheless, will this new type of AI assisted coding produce superior solutions or will future software artifacts become operational…

Humans have nearly perfected the art of creating operational time bombs, AI still has to work very hard if it wants to catch up on that. If AI can improve the test:code ratio in any meaningful way it should be a positive for software quality.

Re: Promising results from DeepSeek R1 for code

#207

Post by AlwaysRock »

lukan wrote: post #109
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 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 and that is increasing more and more.

Re: Promising results from DeepSeek R1 for code

#208

Post by Jerrrry »

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.…

Maybe those software engineers should "lrn2code", just as the journalists, artists, and trucker drivers had to.

Re: Promising results from DeepSeek R1 for code

#209

Post by tokioyoyo »

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.

I'm very sorry, but the goalposts are moving so far ahead now, that's it's very hard to keep track of. 6 months ago the same comments were saying "AI generated code is complete garbage is useless, and I have to rewrite everything all the time anyways". Now we're onto "need to prompt, apply patch, verify" and etc.

Come on guys, time to look at it a bit objectively, and decide where we're going with it.

Re: Promising results from DeepSeek R1 for code

#210

Post by 6510 »

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.

The thing that has me most inspired is that one will finally get to ask the questions that seemed strange to ask before. Like, 1:40 times, when I press the button nothing happens for 10 seconds and I don't know if I've pressed the button properly.
Post reply on HN