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

301–310 of 765 posts

Re: Promising results from DeepSeek R1 for code

#301

Post by AznHisoka »

gmt2027 wrote: post #134
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.…

If AI increases the productivity of a single engineer between 10-100x over the next decade, there will be a seismic shift in the industry and the tech giants will not walk away unscathed. There are coordination costs to organising large amounts of labour. Costs that scale non-linearly as massive inefficiencies are introduced. This ability to scale, provide capital and defer profitability is a moat for big tech and th…

To play devils advocate, the main obstacle in launching a product doesn't involve the actual development/coding. Unless you're building something in hard-tech, it's relatively easy to build the run of the mill software.

The obstacles are in marketing, selling it, building a brand/reputation, integrating it with lots of 3rd party vendors, and supporting it.

So yes, you can build your own Salesforce, or your own Adobe Photoshop with a one-man crew much faster and easier. But that doesn't mean you, as an engineer can now build your own business selling it to companies who don't know anything about you.

Re: Promising results from DeepSeek R1 for code

#302

Post by punkpeye »

punkpeye wrote: post #157
simonw wrote: post #73

Earlier quoted context omitted.

DeepSeek published a bunch of benchmarks when they released the models: https://github.com/deepseek-ai/DeepSeek-R1?tab=readme-ov-fil... I'd like to see detailed benchmarks run by other unaffiliated organizations.

This is very useful. Thank you. so basically there is not much reason to go beyond DeepSeek-R1-Distill-Qwen-32B, at least for coding tasks

Just had a chance to play around with 32B model

https://glama.ai/models/deepseek-r1-distill-qwen-32b

I am using it with Cline VSCode extension to write code.

It works impressively well for a model this size.

Thanks again for sharing those benchmarks!

Re: Promising results from DeepSeek R1 for code

#303

Post by sdesol »

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…

Full disclosure: I am writing a chat app that is designed for software development

> It's a difficult problem to solve, requiring new sets of books, courses etc.

I think new tooling built around LLMs that fits into our current software development lifecycle is going to make a big difference. I am experiencing firsthand how much more productive I am with LLM, and I think that in the future, we will start using "Can you review my conversation?" in the same way we use "Can you review my code?"

Where I believe LLMs are a real game changer is they make it a lot easier for us to consume information. For example, I am currently working on adding a Drag and Drop feature for my chat input box. If a junior developer is tasked with this, the senior developer can easily have the LLM generate a summary of their conversation like so:

https://beta.gitsense.com/?chat=d36e0282-4326-46cf-83b1-4207...

At this point, the senior developer can see if anything is missed; if desired, they can fork the conversation to ask the LLM questions like "Was this asked?" or "Was this mentioned?"

And once everybody is happy, you can have the LLM generate a PR title and message like so:

https://beta.gitsense.com/?chat=8aa19528-5891-4dda-9a88-247a...

All of this took me about 10 minutes, which would have taken me an hour or maybe more without LLMs.

And from here, you are now ready to think about coding with or without LLM.

I think with proper tooling, we might be able to accelerate the learning process for junior developers as we now have an intermediate layer that can better articulate the senior developers' thoughts. If the junior developer is too embarrassed to ask for clarification on why the senior developer said what they did, they can easily ask the LLM to explain.

The issue right now is that we are so focused on the moon shots for LLM, but the simple fact is that we don't need it for coding if we don't want to. We can use it in a better way to communicate and gather requirements, which will go a long way to writing better code faster.

Re: Promising results from DeepSeek R1 for code

#304

Post by bee_rider »

LeFantome wrote: post #173
sitkack wrote: post #78

Earlier quoted context omitted.

We have already entered a new paradigm of software development, where small teams build software for themselves to solve their own problems rather than making software to sell to people. I think selling software will get harder in the future unless it comes with special affordances.

I think some of the CEOs have it right on this one. What is going to get harder is selling “applications” that are really just user friendly ways of getting data in and out of databases. Honestly, most enterprise software is just this. AI agents will do the same job. What will still matter is software that constrains what kind of data ends up in the database and ensures that data means what it is supposed to. That so…

Mostly agree, even without a database-centered worldview.

Programming languages are languages to tell the computer what to do. In the beginning, people wrote in machine code. Then, high level languages like C and FORTRAN were invented. Since then we’ve been iterating on the high level language idea.

These LLM based tools seem to be a more abstract way of telling the computer what to do. And they really might, if they work out, be a jump similar to the low/high level split. Maybe in the future we’ll talk about low-level, high-level, and natural programming languages. The only awkwardness will be saying “I have to drop down to a high level language to really understand what the computer is doing.” But anyway, there were programmers on either side of that first split (way more after), if there’s another one I suspect there will still be programmers after.

Re: Promising results from DeepSeek R1 for code

#306

Post by SkyPuncher »

reitzensteinm wrote: post #254
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…

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.

Re: Promising results from DeepSeek R1 for code

#307

Post by htrp »

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…

Run your deepseek R1 model on your own hardware.

Re: Promising results from DeepSeek R1 for code

#308

Post by terhechte »

mohsen1 wrote: post #10

I am subscribed to o1 Pro and am working on a little Rust crate. I asked both o1 Pro and Deepseek R1 to write e2e tests given all of the code in the repo (using yek[1]). o1 Pro code: https://github.com/bodo-run/clap-config-file/pull/3 Deepseek R1: https://github.com/bodo-run/clap-config-file/pull/4 My judgement is that Deepseek wrote better tests. This repo is small enough for making a judgement by reviewing the code…

I have a set of tests that I can run against different models implemented in different languages (e.g. the same tests in Rust, Ts, Python, Swift), and out of these languages, all models have by far the most difficulty with Rust. The scores are notably higher for the same tests in other languages. I'm currently preparing the whole thing for release to share, but its not ready yet because some urgent work-work came up.

Re: Promising results from DeepSeek R1 for code

#309

Post by steeeeeve »

blakesterz wrote: post #4
simonw wrote: post #3

Given these initial results, I'm now experimenting with running DeepSeek-R1-Distill-Qwen-32B for some coding tasks on my laptop via Ollama - their version of that needs about 20GB of RAM on my M2. https://www.ollama.com/library/deepseek-r1:32b It's impressive! I'm finding myself running it against a few hundred lines of code mainly to read its chain of thought - it's good for things like refactoring where it will thi…

Is DeepSeek really that big of a deal that everyone else should worry?

Today it is. Tomorrow everyone will look at it like Wish or Temu.

Re: Promising results from DeepSeek R1 for code

#310

Post by p_j_w »

CamperBob2 wrote: post #235
hooverd wrote: post #85

Earlier quoted context omitted.

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.

Billionaires don't think about you at all. That's what nobody seems to get. We enjoy many luxuries unavailable even to billionaires only a few decades ago. For this trend to continue, the same thing needs to happen in other sectors that happened in (for example) the agricultural sector over the course of the 20th century: replacement of human workers by mass automation and superior organization.

>Billionaires don't think about you at all.

If that were true they wouldn't be building ultra secure bunkers to escape to when the climate shit hits the fan.

Post reply on HN