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

261–270 of 765 posts

Re: Promising results from DeepSeek R1 for code

#261

Post by ceejayoz »

simonw wrote: post #205
WhitneyLand wrote: post #102

Earlier quoted context omitted.

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

That goes both ways, though. Every new ability is "the big one" that hints at AGI just around the corner.

Re: Promising results from DeepSeek R1 for code

#262

Post by xd »

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.…

The thing with programming, to do it well, you need to fully understand the problem and then you implement the solution expressing it in code. AI will be used to create code based on a deficit of clear understanding and we will end up with a hell of a lot of garbage code. I foresee the industry demand for programmers sky rocketing in the future, as companies scramble to unfuck the mountains of shit code they lash up over the coming years. It's just a new age of copy paste coders.

Re: Promising results from DeepSeek R1 for code

#263

Post by curious_cat_163 »

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…

> If you ask me why this will take time, my argument is that effectively wielding an LLM for coding requires broad knowledge.

This is a problem that the Computer Science departments of the world have been solving. I think that the "good" departments already go for the "broad knowledge" of theory, systems with a balance between the trendy and timeless.

Re: Promising results from DeepSeek R1 for code

#264

Post by joshstrange »

anotherpaulg wrote: post #113
joshstrange wrote: post #106

Earlier quoted context omitted.

First off I want to thank you for Aider. I’ve had so much fun playing with it and using it for real work. It’s an amazing tool. How do you determine how much was written by you vs the LLM? I assume it consists of parsing the git log and getting LoC from that or similar? If the scripts are public could you point me at them? I’d love to run it on a recent project I did using aider.

Glad to hear you’re finding aider useful! There’s a faq entry about how these stats are computed [0]. Basically using git blame, since aider is tightly integrated with git. The faq links to the script that computes the stats. It’s not designed to be used on any repo, but you (or aider) could adapt it. You’re not the first to ask for these stats about your own repo, so I may generalize it at some point. [0] https://ai…

Thank you so much for linking me to that! I think an `aider stats`-type command would be really cool (it would be cool to calculate stats based activity since the first aider commit or all-time commits of the repo).

Re: Promising results from DeepSeek R1 for code

#265

Post by almostgotcaught »

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…

> 99% of the code in this PR [for llama.cpp] is written by DeekSeek-R1

you're assuming the PR will land:

> Small thing to note here, for this q6_K_q8_K, it is very difficult to get the correct result. To make it works, I asked deepseek to invent a new approach without giving it prior examples. That's why the structure of this function is different from the rest.

This certainly wouldn't fly in my org (even with test coverage/passes).

Re: Promising results from DeepSeek R1 for code

#266

Post by gauge_field »

freshtake wrote: post #148
amarcheschi wrote: post #34

For what i can understand, he asked deepseek to convert arm simd code to wasm code. in the github issue he links he gives an example of a prompt: Your task is to convert a given C++ ARM NEON SIMD to WASM SIMD. Here is an example of another function: (follows a block example and a block with the instructions to convert) https://gist.github.com/ngxson/307140d24d80748bd683b396ba13b... I might be wrong of course, but ask…

This. For folks who regularly write simd/vmx/etc, this is a fairly straightforward PR, and one that uses very common patterns to achieve better parallelism. It's still cool nonetheless, but not a particularly great test of DeepSeek vs. alternatives.

That is what I am struggling to understand about the hype. I regularly use them to generate new simd. Other than a few edge cases (issues around handling of nan values, order of argument for corresponding ops, availability of new avx512f intrinsics), they are pretty good at converting. The names of very intrinsics are very similar from simd to another. The very self-explanatory nature of the intrinsics names and having similar apis from simd to another makes this somewhat expected result given what they can already accomplish.

Re: Promising results from DeepSeek R1 for code

#268

Post by worik »

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…

> It will be a while before vocational programming courses retool to teach this new way of writing code

Why?

Are they not already?

Re: Promising results from DeepSeek R1 for code

#269

Post by Myrmornis »

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.…

In my experience a lot of it is (d) defaulting to criticizing new things, especially things that are "trendy" or "hot" and (e) not liking to admit that one's own work can partially be done by such a trendy or hot thing.

Re: Promising results from DeepSeek R1 for code

#270

Post by unshavedyak »

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 still just looking for a good workflow where I can stay in my editor and largely focus on code, rather than trying to explain what I want to an LLM.

I want to stay in Helix and find a workflow that “just works”. Not sure even what that looks like yet

Post reply on HN