←back to thread

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

(simonwillison.net)
200 points simonw | 1 comments | 20 Oct 25 17:24 UTC | HN request time: 0.256s | source
Show context
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 #
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 #
1. 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.