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

351–360 of 765 posts

Re: Promising results from DeepSeek R1 for code

#351

Post by inglor_cz »

p_j_w wrote: post #310
CamperBob2 wrote: post #235

Earlier quoted context omitted.

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.

How many of them did that? Five out of a thousand?

Anecdotally, around two people in a hundred in my proximity are preppers as well, though obviously with smaller budgets.

It is just a specific fringe way of thinking.

Re: Promising results from DeepSeek R1 for code

#352

Post by unshavedyak »

stnmtn wrote: post #339
unshavedyak wrote: post #324

Earlier quoted context omitted.

I've not tried tbh. Most of the workflows i've seen (i know i looked at Cursor, but it's been a while) appear to be to write lengthy descriptions of what you want it to do. As well as struggling with the amount of context you need to give it because context windows are way too small. I feel like i want a more intuitive, natural process. Purely for illustration -- because i have no idea what the ideal workflow is -- I…

I'd recommend trying out Cursor, I personally find it does more or less what you want out of the box.

I'll look into it, thanks!

I'm currently trying to figure out how it works with my editor, though. Ie i don't want to leave my tooling of choice, Helix editor.

Re: Promising results from DeepSeek R1 for code

#353

Post by breuleux »

joshmarlow wrote: post #68
bbzealot wrote: post #42

Earlier 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?

> make the balance between capital and labor even more uneven. I think it's interesting to note that as opens source models evolve and proliferate, the capital required for a lot of ventures goes down - which levels the playing field. When I can talk to one agent-with-a-CAD-integration and have it design a gadget for me and ship the design off to a 3D printer and then have another agent write the code to run on the g…

What value do you bring to the venture, though? What makes your venture more likely to succeed than anybody else's, if the barrier is that low? I mean, I'll tell you: if anyone can spend $100 to design the same new gadget, the winner is going to be whoever can spend a million in production (to get economy of scale) and marketing. Currently, financial capital needs your brain, so you can leverage that. But if they can use a brain in the cloud instead, they're going to do just that. Sure, you can use it and design anything you can imagine, but nobody is going to pay you for it unless you, yourself, bring some irreplaceable value to the table.

Re: Promising results from DeepSeek R1 for code

#354

Post by AnotherGoodName »

CalChris wrote: post #227
tomrod wrote: post #117

Earlier quoted context omitted.

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.

The really experienced of us will have made this mistake enough times to know to avoid it.

I didn’t get a smart phone until the 2010s. Stupid I know but it was seen as a badge of honour in some circles ‘bah I don’t even use a smart phone’ we’d say as the young crowd went about their lives never getting lost without a map and generally having an easier time of it since they didn’t have that mental block.

Ai is going to be similar no doubt. I’m already seeing ‘bah I don’t use ai coding assistants’ type of posts, wearing it as a badge of honour. ‘Ok you’re making things harder for yourself’ should be the reply but we’ll no doubt have people wearing it as a badge of honour for some time yet.

Re: Promising results from DeepSeek R1 for code

#355

Post by swfsql »

cft wrote: post #45
cft wrote: post #30

Earlier quoted context omitted.

DeepSeek R1

@jetbalsa - HN does not allow me to reply, the reply depth is limited, so replying here. I was simply clicking the paperclip and attaching the .py files to the prompt.

Using a local 7B for chatting, I saw it tries very hard to check for inconsistencies of itself, and that may spill to also checking for the user's "inconsistencies".

Maybe it's better to carefully control and explain the talk progression. Selectively removing old prompts (adapting where necessary) - which also reduces the context - results in it not having to "bother" to check for inconsistencies internal to irrelevant parts of the conversation.

Eg. asking it to extract Q&A from a line of text and format it to json, which could be straightforward, sometimes it would wonder about the contents from within the Q&A itself, checking for inconsistencies eg:

  - I need to be careful to not output content that's factually incorrect. Wait but I'm not sure about this answer I'm dealing with here..
  - Before the questions were about mountains and now it's about rivers, what's up with that?
  - etc..
I had to strongly demand it to treat it all as jumbled text/verbatim, and never think about their meaning. So it should be more effective if I always branched from the starting prompt when entering a new Q&A for it to work on. So this is what I meant by "selectively remove old prompts".

Re: Promising results from DeepSeek R1 for code

#356

Post by danielbln »

freshtake wrote: post #151
gejose wrote: post #58

Loving this comment on that PR: > I'm losing my job right in front of my eyes. Thank you, Father.

Until the code breaks and no one can figure out how to fix (or prompt to fix) it :)

"This broke. Here is the error behavior, here are diagnostics, here is the code. Help me dig in and figure this out."

Re: Promising results from DeepSeek R1 for code

#357

Post by cess11 »

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…

No, enterprise software is typically also risk management and compliance, domains where rules rule. Someone needs to sign off on the software being up to spec and taking responsibility for failures, that's something any submissive LLM is willing to do but can't.

Re: Promising results from DeepSeek R1 for code

#358

Post by breuleux »

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.

In the past, human workers were displaced. The value of their labour for certain tasks became lower than what automation could achieve, but they could still find other things to do to earn a living. What people are worrying about here is what happens when the value of human labour drops to zero, full stop. If AI becomes better to us at everything, then we will do nothing, we will earn nothing, and we will have nothing that isn't gifted to us. We will have no bargaining power, so we just have to hope the rich and powerful will like us enough to share.

Re: Promising results from DeepSeek R1 for code

#359

Post by danenania »

withinboredom wrote: post #127
simonw wrote: post #99

Earlier quoted context omitted.

I continue to suspect that the hiring problems are mainly due to massive over-hiring during Covid, followed by layoffs that flooded the market with skilled developers looking for work. I'd love to see numbers around the "execs don't think they need engineers because of AI" factor. I've heard a few anecdotal examples of that but it's hard to tell if it's a real trend or just something that catches headlines.

I think execs don’t see the problems we have with AI because you don’t need to be an expert to be an exec. I run into the edges of AI every day. There are things it is good at and things not so good at, and it varies from model to model and context to context (you can have two conversations with the same model, about the same thing, and get vastly different outputs; eg a test that uses different assertion patterns/li…

Definitely. The brilliant moments also get cherry picked for social media.

Re: Promising results from DeepSeek R1 for code

#360

Post by jonas21 »

bbzealot wrote: post #42
pavitheran wrote: post #12

Earlier quoted context omitted.

Deepseek is a big deal but we should be happy not worried that our tools are improving.

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?

Do you feel the same way about open source software?
Post reply on HN