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

341–350 of 765 posts

Re: Promising results from DeepSeek R1 for code

#341

Post by yoyohello13 »

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…

Maybe this is answered, but I didn't see it. How does aider deal with secrets in a git repo? Like if I have passwords in a `.env`?

Edit: I think I see. It only adds files you specify.

Re: Promising results from DeepSeek R1 for code

#342

Post by andrei_says_ »

the_af wrote: post #314
bubbleRefuge wrote: post #300

Earlier quoted context omitted.

Think the marginal cost of developing complex software goes down thereby making it affordable to a greater market. There will still be a need for skilled software engineers to understand domains, limitations of AI, and how to harness and curate AI to develop custom apps. Maybe software engineering for the masses. Local small businesses can now maybe afford to take on custom software projects that were before unthinka…

> There will still be a need for skilled software engineers to understand domains, limitations of AI, and how to harness and curate AI to develop custom apps. But will there be a need for fewer engineers, though? That's the question. And the competition for those who remain employed would be fierce, way worse than today. Or so I fear. I hope I'm wrong.

I think it might be useful to look at this as multiple forces to play.

One force is a multiplier of a software engineer’s productivity.

Another force is the pressure of the expectation for constant, unlimited increase in profits. This pressure force the CEOs and managers to look for cheaper alternatives to expensive software engineers, ultimately to eliminate the position and expense. The lie that this is a possibility draws huge investments.

And another force is the infinite number of applications of software, especially well designed, truly useful, software.

Re: Promising results from DeepSeek R1 for code

#343

Post by FeepingCreature »

yoyohello13 wrote: post #341
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…

Maybe this is answered, but I didn't see it. How does aider deal with secrets in a git repo? Like if I have passwords in a `.env`? Edit: I think I see. It only adds files you specify.

Aider has a command to add files to the prompt. For files that are not added, it uses tree-sitter to extract a high-level summary. So for a `.env`, it will mention to the LLM the fact that the file exists, but not what is in it. If the model thinks it needs to see that file, it can request it, at which point you receive a prompt asking whether it's okay to make that file available.

It's a very slick workflow.

Re: Promising results from DeepSeek R1 for code

#344

Post by adrianlzt »

yoyohello13 wrote: post #341
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…

Maybe this is answered, but I didn't see it. How does aider deal with secrets in a git repo? Like if I have passwords in a `.env`? Edit: I think I see. It only adds files you specify.

[dead]

Re: Promising results from DeepSeek R1 for code

#345

Post by root_axis »

jmward01 wrote: post #329
root_axis wrote: post #325

Earlier quoted context omitted.

> So, AGI will likely be here in the next few months because the path is now actually clear: Training will be in three phases My bet: "AGI" won't be here in months or even years, but it won't stop prognosticators from claiming it's right around the corner. Very similar to prophets of doom claiming the world is going to end any day now. Even in 10k years, the claim can never be falsified, it's always just around the c…

Maybe, but I know what my laser focus will be on for the next few weeks. I suspect a massive number of researchers around the world have just switched their focus in a similar way. The resources applied to this problem have been going up exponentially and the recent RL techniques have now opened the floodgates for anyone with a 4090 (or even smaller!) to try crazy things. In a world where the resources are constant I…

Your reasoning still assumes that "AGI" can emerge from quadratic time brute force on some text and images scraped off the internet. Personally, I'm skeptical of that premise.

Re: Promising results from DeepSeek R1 for code

#346

Post by 7thpower »

SkyPuncher wrote: post #306
reitzensteinm wrote: post #254

Earlier quoted context omitted.

R1 is available on both together.ai and fireworks.ai, it should be a drop in replacement using the OpenAI API.

The problem is it's very expensive. More expensive than Claude.

You can use the distilled version on Groq for free for the time being. Groq is amazing but frequently has capacity issues or other random bugs.

Perhaps you could set up Groq as your primary and then fail back to fireworks, etc by using litellm or another proxy.

Re: Promising results from DeepSeek R1 for code

#347

Post by OvbiousError »

LeFantome wrote: post #162
AnotherGoodName wrote: post #120

Earlier quoted context omitted.

The ask from every new grad to be assigned to ai development is unreasonable right now and they are probably hurting their careers by all going the same direction honestly. It’s a small fraction of our development efforts and we usually hire very senior for that sort of role. We still need people that can program for the day to day business needs and it’s a perfect starting role for a new grad yet almost all of them…

Agree and disagree. You do it need a “degree in AI”. However, you need to be using AI in your degree. Really using it. What are those “day to day business needs” that you think people are going to do without AI? In my view, this is like 1981. If you are saying, we will still need non-computer people for day-to-day business needs, you are wrong. Even the guy in the warehouse and the receptionist at the front are using…

Wouldn't the AI track be more about the knowing the internals, being able to build models, ... So in your 1981 example that would be saying about half of the people are enrolling in computer hardware courses, whereas only a fraction of those are needed?

I would assume any other CS course teaches/is going to be teaching how to use AI to be an effective software developer.

Re: Promising results from DeepSeek R1 for code

#348

Post by Capricorn2481 »

chunky1994 wrote: post #274
20k wrote: post #139

Earlier quoted context omitted.

The thing is, that's not true at all. AI is great for some tasks, and poor for other tasks. That's the reason to break it down like this, because people are trying to explain where AI will and won't revolutionise things, instead of following along with the already-popping AI bubble uncritically For example: AI's smash translation. They won't ever beat out humans, but as an automated solution? They rock. Natural langu…

The difference is though there isn't a whole lot of "whole cloth novel solutions" being written in software today so much as a "write me this CRUD app to do ABC" which current generations are exceedingly good at. There are probably 10% of truly novel problems out there, the rest are just already solved problems with slightly different constraints of resources ($), quality (read: reliability) and time. If LLMs get goo…

I think there's a gap of problems between CRUD and novel. I imagine novel to be very difficult, unsolved problems that would take some of the best in the industry to figure out. CRUD problems are really basic reading/writing data to a database with occasional business logic.

But there's also bespoke problems. They aren't quite novel, yet are complicated and require a lot of inside knowledge on business edge cases that aren't possible to sum up in a word document. Having worked with a lot of companies, I can tell you most businesses literally cannot sum up their requirements, and I'm usually teaching them how their business works. These bespoke problems also have big implications on how the app is deployed and run, which is a whole different thing.

Then you have LLMs, which seem allergic to requirements. If you tell an LLM "make this app, but don't do these 4 things," it's very different from saying "don't do these 12 things." It's more likely to hallucinate, and when you tell it to please remember requirement #3, it forgets requirement #7.

Well, my job is doing things with lots of restraints. And until I can get AI to read those things without hallucinating, it won't be helpful to me.

Re: Promising results from DeepSeek R1 for code

#349

Post by jmward01 »

hn_throwaway_99 wrote: post #340
jmward01 wrote: post #332

Earlier quoted context omitted.

AGI is defined by the loss function. We are on the verge of a loss function that enables self determined rewards and learning and that to me is AGI. That is step 3.

You're just proving my point. "AGI is defined by the loss function" may be a definition used by some technologists (or maybe just you, I don't know), but to purport that that equals capability equivalence with humans in all tasks (again, which is how it is often presented to the wider public audience) shows the uselessness or deliberate obfuscation embedded in that term.

Well, I guess we will see what the discussion will be about in a couple months. You are right that 'AGI' is in the eye of the beholder so there really isn't a point in discussing it since there isn't an acceptable definition for this discussion. I personally care about actual built things and the things that will be built, and released, in the next few months will be in a category all their own. No matter what you call them, or don't call them, they will be extraordinary.

Re: Promising results from DeepSeek R1 for code

#350

Post by anotherpaulg »

yoyohello13 wrote: post #341
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…

Maybe this is answered, but I didn't see it. How does aider deal with secrets in a git repo? Like if I have passwords in a `.env`? Edit: I think I see. It only adds files you specify.

You can use an .aiderignore file to ensure aider doesn't use certain files/dirs/etc. It conforms to the .gitignore spec.
Post reply on HN