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

221–230 of 765 posts

Re: Promising results from DeepSeek R1 for code

#221

Post by herval »

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…

This is my main worry with the entire AI trend too. We're creating a huge gap for those joining the industry right now, with markedly fewer job openings for junior people. Who will inherit the machine?

Re: Promising results from DeepSeek R1 for code

#222

Post by casenmgreen »

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 may be wrong, but I think right now, from reading stories of people looking at use AI and having poor experiences, AI is useful and effective for some tasks and not for others, and this is an intrinsic property - it won't get better with bigger models. You need a task which fits well with what AI can do, which is basically auto-complete. If you have a task which does not fit well, it's not going to fly.

Re: Promising results from DeepSeek R1 for code

#223

Post by mring33621 »

cft wrote: post #22

I am writing some python code to do Order Flow Imbalance analysis from L2 orderbook updates. The language is unimportant: the logic is pretty subtle, so that the main difficulties are not in the language details, but in the logic and handling edge cases. Initially I was using Claude 3.5 sonnet, then writing unit tests and manually correcting sonnet's code. Sonnet's code mostly worked, except for failing certain compl…

Classic whack-a-mole

IMHO, this can happen with human or robot co-workers.

Re: Promising results from DeepSeek R1 for code

#224

Post by entropicdrifter »

cyanydeez wrote: post #202
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…

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 a…

>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.

I would argue that we already accept relatively random car fatalities at a huge scale and simply engage in post-hoc rationalization of the why and how of individual accidents that affect us personally. If we can drastically reduce the rate of accidents, the remaining accidents will be post-hoc rationalized the same way we always have rationalized accidents.

Re: Promising results from DeepSeek R1 for code

#225

Post by simonw »

casenmgreen wrote: post #222
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 may be wrong, but I think right now, from reading stories of people looking at use AI and having poor experiences, AI is useful and effective for some tasks and not for others, and this is an intrinsic property - it won't get better with bigger models. You need a task which fits well with what AI can do, which is basically auto-complete. If you have a task which does not fit well, it's not going to fly.

Right: LLMs have a "jagged frontier". They are really good at some things and terrible at other things, but figuring out WHAT those things are is extremely unintuitive.

You have to spend a lot of time experimenting with them to develop good intuitions for where they make sense to apply.

I expect the people who think LLMs are useless are people who haven't invested that time yet. This happens a lot, because the AI vendors themselves don't exactly advertise their systems as "they're great at some stuff and terrible at other stuff and here's how to figure that out".

Re: Promising results from DeepSeek R1 for code

#226

Post by LeoPanthera »

Going from English to code via AI feels a lot like going from code to binary via a compiler.

I wonder how long it will be before we eliminate the middle step and just go straight from English to binary, or even just develop an AI interpreter that can execute English directly without having to "compile" it first.

Re: Promising results from DeepSeek R1 for code

#227

Post by CalChris »

tomrod wrote: post #117
onetimeusename wrote: post #107

Earlier quoted context omitted.

Just as a side note, at my university about half the CS people are in the AI track. I would guess that number will keep increasing. There is also a separate major that kind of focuses on AI/psychology that is pretty popular but I am not sure how many people are in it. A good number of the students have some kind of "AI startup". Also, although it violates the honor code, I would be willing to bet many students use AI…

Yeah, the younguns smell opportunity and run towards it. They'll be fine. It's younguns) the less experienced folks in the current corporate world that will have the most to lose.

Or perhaps it will be the more experienced knuckle draggers, hardened in our ways.

Re: Promising results from DeepSeek R1 for code

#228

Post by simonw »

plandis wrote: post #219
antonislav wrote: post #144

Earlier quoted context omitted.

I think, seeing recordings of people using LLMs to accomplish non-trivial tasks would go a long way. I’d love to watch, e.g. you Simon, using these tools. I assume there are so many little tricks you figured out over time that together make a big difference. Things that come to mind: - how to quickly validate the output? - what tooling to use for iterating back and forth with the LLM? (just a chat?) - how to steer th…

I believe Simon has full transcripts for some of the projects he’s had LLMs generate the code for. You can see how he steers the LLM for what is desired and how it is course corrected.

I've published probably over a hundred of those now, but they're scattered around. This tag on my blog has a lot of them: https://simonwillison.net/tags/ai-assisted-programming/

Re: Promising results from DeepSeek R1 for code

#229

Post by Capricorn2481 »

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…

> cue the apologists

How are you defining apologists here? Anti-AI apologists? Human apologists? That's not a word you can just sprinkle on opposing views to make them sound bad.

Re: Promising results from DeepSeek R1 for code

#230

Post by paulryanrogers »

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…

Dev effort isn't always the bottleneck. It's often stakeholders ironing out the ambiguities, conflicting requirements, QA, ops, troubleshooting, etc.

Maybe devs will be replaced with QA, or become glorified QA themselves.

Post reply on HN