That PR is a maintainer's nightmare.
"Here's a massive bunch of AI generated code. LGTM. Let me know if there are any problems"
Promising results from DeepSeek R1 for code
81–90 of 765 posts
Re: Promising results from DeepSeek R1 for code
#82> 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.…
When GPT-4 came out, I worked on a project called Duopoly [1], which was a coding bot that aimed to develop itself as much as possible.
The first commit was half a page of code that read itself in, asked the user what change they'd like to make, sent that to GPT-4, and overwrote itself with the result. The second commit was GPT-4 adding docstrings and type hints.
Over 80% of the code was written by AI in this manner, and at some point, I pulled the plug on humans, and the last couple hundred commits were entirely written by AI.
It was a huge pain to develop with how slow and expensive and flaky the GPT-4 API was at the time. There was a lot of dancing around the tiny 8k context window. After spending thousands in GPT-4 credits, I decided to mark it as proof of concept complete and move on developing other tech with LLMs.
Today, with Sonnet and R1, I don't think it would be difficult or expensive to bootstrap the thing entirely with AI, never writing a line of code. Aider, a fantastic similar tool written by HN user anotherpaulg, wasn't writing large amounts of its own code in the GPT-4 days. But today it's above 80% in some releases [2].
Even if the models froze to what we have today, I don't think we've scratched the surface on what sophisticated tooling could get out of them.
[1]: https://github.com/reitzensteinm/duopoly [2]: https://aider.chat/HISTORY.html
Re: Promising results from DeepSeek R1 for code
#83> 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.…
LLMs excel at tasks with very clear instructions and parameters. Porting from one language to another is something that is one step away from being done by a compiler. Another place that I've used them is for initial scaffolding of React components.
Re: Promising results from DeepSeek R1 for code
#84> 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.
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?
Re: Promising results from DeepSeek R1 for code
#85Earlier quoted context omitted.
Why though? I'm worried these technologies may take my job away and make the balance between capital and labor even more uneven. Why should I be happy?
You won't be happy doing a robot's job either, at least not for long. In the ideal case, we won't be dependent on the unwilling labor of other humans at all. Would you do your current job for free? If not -- if you'd rather do something else with your productive life -- then it seems irrational to defend the status quo. One thing's for certain: ancient Marxist tropes about labor and capital don't bring any value to t…
Because billionaires think that you are a horse and that the best course of action is to turn you into glue while they hope AGI lets them live forever.
Re: Promising results from DeepSeek R1 for code
#86> 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…
> 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 testing times for so many of them. If you ask me why this will take time, my argument is that effectively wielding an LLM for coding requires broad knowledge. 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.
It's a difficult problem to solve, requiring new sets of books, courses etc.
Re: Promising results from DeepSeek R1 for code
#87Earlier quoted context omitted.
Is DeepSeek really that big of a deal that everyone else should worry?
A lot of the niceness about DeepSeek-R1's usage in coding is that you can see the thought process, which (IME) has been more useful than the final answer. It may well be that o1's chain of thought reasoning trace is also quite good. But they hide it as a trade secret and supposedly ban users for trying to access it, so it's hard to know.
I have a lot of fun just posting a function into R1, saying "Improve this" and reading the chain of thought. Lots of insight in there that I would usually miss or glance over.
Re: Promising results from DeepSeek R1 for code
#88When these models succeed in building a whole program and a whole system then the software industry that creates products and services will disappear. Any person and any organization will create from scratch the software they need perfectly customized to their needs and the AI system will evolve it over time. At most they will have to cooperate on communication protocols. In my opinion we are less than 5 years away f…
Any person who has the ability to break down a problem to the point that code can be written to solve it, and the ability to work with an LLM system to get that work done, and the ability to evaluate if the resulting code solves the problem.
That's a mixture of software developer, program manager, product manager and QA engineer.
I think that's what software developer roles will look like in the future: a slightly different mix of skills, but still very much a skilled specialist.
Re: Promising results from DeepSeek R1 for code
#89> 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.…
It's making programming more boring and more of an admin task- which is sure to attract different types of people to the field.
Seems like the exact opposite. The very example you are replying to is the mechanistic translation of one low level language to another, maybe one of the most boring tasks imaginable.
Re: Promising results from DeepSeek R1 for code
#90Earlier 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…
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.