HackerTrans
TopNewTrendsCommentsPastAskShowJobs

jerpint

no profile record

Submissions

Show HN: Woltspace – a lodge for your coding agents

woltspace.com
2 points·by jerpint·19 gün önce·0 comments

Show HN: Clangine-de-Poitrine

github.com
3 points·by jerpint·3 ay önce·1 comments

The paradox of shipping more while coding less

jerpint.io
1 points·by jerpint·4 ay önce·0 comments

Humans.md

jerpint.io
2 points·by jerpint·4 ay önce·1 comments

Coding at the Speed of Thought

jerpint.io
1 points·by jerpint·5 ay önce·0 comments

I Maintain My Blog in the Age of Agents

jerpint.io
3 points·by jerpint·5 ay önce·1 comments

I don't write code anymore – I sculpt it

jerpint.io
45 points·by jerpint·6 ay önce·62 comments

The Rise of the 0.1x Engineer

jerpint.io
3 points·by jerpint·7 ay önce·0 comments

Different Models, Same Slop?

jerpint.io
2 points·by jerpint·8 ay önce·1 comments

comments

jerpint
·11 gün önce·discuss
Solutions like these are really cementing the view that LLMs are becoming a commodity
jerpint
·4 ay önce·discuss
I like the concept!
jerpint
·5 ay önce·discuss
Oops- typo in the title, should be “How I Maintain My Blog in the age of Agents”
jerpint
·6 ay önce·discuss
Author here - I agree that to learn the best thing is to implement and fail along the way. My point was I would never professionally opt to write a sorting algorithm instead of using the builtin sort() most languages come equipped with
jerpint
·6 ay önce·discuss
Author here - wrote this myself but I’ll take that as a complement :)
jerpint
·6 ay önce·discuss
Nice! I made my own version of this many years ago, with a very basic manim animation

https://www.jerpint.io/blog/2021-03-18-cnn-cheatsheet/
jerpint
·7 ay önce·discuss
I did a post [0] about this last year, and vanilla LLMs didn’t do nearly as well as I’d expected on advent of code, though I’d be curious to try this again with Claude code and codex

[0] https://www.jerpint.io/blog/2024-12-30-advent-of-code-llms/
jerpint
·9 ay önce·discuss
Best is very subjective depends what you want it to do and if you want to fine tune and how big you consider small
jerpint
·geçen yıl·discuss
> This code repository and the model weights are licensed under the MIT License. DeepSeek-R1 series support commercial use, allow for any modifications and derivative works, including, but not limited to, distillation for training other LLMs.

Wow. They’re really trying to undercut closed source LLMs
jerpint
·3 yıl önce·discuss
Do you mean to say that changes I make from GitHub.dev are reflected on my local machine?
jerpint
·3 yıl önce·discuss
Ouch
jerpint
·4 yıl önce·discuss
This is incredible (I’m assuming this was chatGPT output)