Most active commenters
  • bahmboo(3)

←back to thread

Getting DeepSeek-OCR working on an Nvidia Spark via brute force with Claude Code

(simonwillison.net)
200 points simonw | 16 comments | 20 Oct 25 17:24 UTC | HN request time: 0s | source | bottom
1. bahmboo ◴[21 Oct 25 23:04 UTC] No.45662877[source]▶
I see a lot of snark in the comments. Simon is a researcher and I really like seeing his experiments! Sounds like the goal here was to delegate a discrete task to an LLM and have it solve the problem much like one would task a junior dev to do the same.

And like a junior dev it ran into some problems and needed some nudges. Also like a junior dev it consumed energy resources while doing it.

In the end I like that the chunk size of work that we can delegate to LLMs is getting larger.

replies(2): >>45663098 #>>45665643 #
2. Upvoter33 ◴[21 Oct 25 23:30 UTC] No.45663098[source]▶
No offense, but I hate all the comparisons to a "junior dev" that I see out there. This process is just like any dev! I mean, who wouldn't have to tinker around a bit to get some piece of software to work? Is there a human out there who would just magically type all the right things - no errors - first try?
replies(4): >>45663166 #>>45663461 #>>45664538 #>>45664889 #
3. solumos ◴[21 Oct 25 23:39 UTC] No.45663166[source]▶
> And like a junior dev it ran into some problems and needed some nudges.

There are people who don't get blocked waiting for external input in order to get tasks like this done, which I think is the intended comparison. There's a level of intuition that junior devs and LLMs don't have that senior devs do.

replies(1): >>45663975 #
4. bahmboo ◴[22 Oct 25 00:14 UTC] No.45663461[source]▶
Point taken and I should have known better. I fully agree with you. I suppose I should say inexperienced dev or something more accurate. Having worked with many inexperienced devs there was quite a spread in capabilities. Using terms that are dismissive to individuals is not helpful.
5. the-grump ◴[22 Oct 25 01:32 UTC] No.45663975{3}[source]▶
To offer a counterpoint, I had much better intuition as a junior than I do now, and it was also better than the seniors on my team.

Sometimes looking at the same type of code and the same infra day in and day out makes you rusty. In my olden days, I did something different every week, and I had more free time to experiment.

replies(2): >>45664202 #>>45665113 #
6. fastball ◴[22 Oct 25 02:14 UTC] No.45664202{4}[source]▶
So you are a worse dev now than you were before? Have you asked for a pay cut from your employer?
replies(3): >>45664681 #>>45665120 #>>45672474 #
7. conradev ◴[22 Oct 25 03:11 UTC] No.45664538[source]▶
Codex is actually pretty good at getting things working and unblocking itself.

It’s just that when I review the code, I would do things differently because the agent doesn’t have experience with our codebase. Although it is getting better at in-context learning from the existing code, it is still seeing all of it for the “first time”.

It’s not a junior dev, it’s just a dev perpetually in their first week at a new job. A pretty skilled one, at that!

and a lot of things translate. How well do you onboard new engineers? Well written code is easier to read and modify, tests helps maintain correctness while showing examples, etc.

8. arthurcolle ◴[22 Oct 25 03:38 UTC] No.45664681{5}[source]▶
pay increase - with better tools, I'd imagine
9. pedrosorio ◴[22 Oct 25 04:29 UTC] No.45664889[source]▶
> Is there a human out there who would just magically type all the right things - no errors - first try?

If they know what they're doing and it's not an exploratory task where the most efficient way to do it is by trial and error? Quite a few. Not always, but often.

That skill seems to have very little value in today's world though.

10. baq ◴[22 Oct 25 05:15 UTC] No.45665113{4}[source]▶
Hobby coding is imho a high entropy signal that you joined the workforce with a junior title but basically senior experience, which is what I see from kids who learned programming young due to curiosity vs those who only started learning in university. IOW I suspect you were not a junior in anything but name and pay.

There’s also a factor of the young being very confident that they’re right ;)

11. baq ◴[22 Oct 25 05:16 UTC] No.45665120{5}[source]▶
https://en.wikipedia.org/wiki/Peter_principle

;)

12. fumeux_fume ◴[22 Oct 25 06:45 UTC] No.45665643[source]▶
Another top comment that fabricates negativity saying “I see a lot of snark in the comments.” Hardly anything negative, let alone snarky, is being directed to one of HNs most popular voices. It’s a weird dark pattern to get upvotes under the pretext of being supportive and it should be called out more often.
replies(1): >>45665720 #
13. bahmboo ◴[22 Oct 25 06:59 UTC] No.45665720[source]▶
Huh? My post was very positive and hopefully let's not get too meta. I felt the comments did not address the merits or contents of what was being presented. That's all!

edit: did you see my comment when it was first posted? The topic was being dumped on at that time and drowning out the signal. I promise I'm not part of a dark pattern.

replies(1): >>45666345 #
14. CaptainOfCoit ◴[22 Oct 25 08:39 UTC] No.45666345{3}[source]▶
> I felt the comments did not address the merits or contents of what was being presented

That's wildly different from:

> I see a lot of snark in the comments

The first is essentially "People should talk about the actual content more" while the second is "People are mocking the submission". If no other top-level comments actually seem like mocking, it seems fair that someone reacts to the second sentiment

> The topic was being dumped on at that time and drowning out the signal.

There was a whole of 7 comments when you made yours (https://ditzes.com/item/45646559), most of them children comments, none of them mocking the submission nor the author.

15. the-grump ◴[22 Oct 25 17:35 UTC] No.45672474{5}[source]▶
Believe it or not, my employer likes what I'm doing so I'm still on the promotion track.

They seem more concerned with my ability to work on the company's bread and butter.

replies(1): >>45678216 #
16. fastball ◴[23 Oct 25 04:40 UTC] No.45678216{6}[source]▶
And you are better at working on the company's bread and butter with worse intuition?