HackerTrans
TopNewTrendsCommentsPastAskShowJobs

rohitpaulk

no profile record

Submissions

Yann LeCun's Billion Dollar Bet [video]

youtube.com
3 points·by rohitpaulk·il y a 2 mois·0 comments

Why does request.remote_ip work on Heroku but not Render?

rohitpaulk.com
1 points·by rohitpaulk·il y a 5 mois·0 comments

CCBench: How do agents perform on codebases that aren't part of training data?

ccbench.org
1 points·by rohitpaulk·il y a 5 mois·0 comments

Code a database in 45 steps: test-driven coding puzzles

trialofcode.org
2 points·by rohitpaulk·il y a 7 mois·0 comments

I accidentally used YAML.parse instead of JSON.parse and it worked

rohitpaulk.com
346 points·by rohitpaulk·il y a 4 ans·201 comments

comments

rohitpaulk
·il y a 19 jours·discuss
We use RubyLLM in production too, the most elegant library in this space I've seen so far.

I also liked how they run the issue tracker. If you select "Feature Request", it makes you explain how you explored workarounds, why you believe it belongs in RubyLLM etc to prevent scope creep.
rohitpaulk
·le mois dernier·discuss
Same here. Loved the LTS thinking and Ember data being built in but hiring was a pain and ecosystem packages were often out of date.
rohitpaulk
·il y a 2 mois·discuss
Prior art: https://blog.can.ac/2026/02/12/the-harness-problem/
rohitpaulk
·il y a 2 mois·discuss
The whole idea that my RUNTIME contains code that a single human hasn't looked at does make me uncomfortable, but if this actually works without a ton of issues it's pretty remarkable.
rohitpaulk
·il y a 2 mois·discuss
Aside from how impressive the model is, the demos here are very well done! Quirky and short, unlike what we're used to from Anthropic and OpenAI.
rohitpaulk
·il y a 2 mois·discuss
Only a portion of these are "scandals", the rest are just usual startup failures.
rohitpaulk
·il y a 2 mois·discuss
That's 2 major layoffs this week (Coinbase being the other). Is there an underlying common reason for this? And is it indeed AI-driven productivity as both companies claim?
rohitpaulk
·il y a 2 mois·discuss
Nice one. Pleasantly surprised that this has nothing to do with Cursor the IDE
rohitpaulk
·il y a 3 mois·discuss
Been testing these via their "pool" agent. It's fast, and the agent adheres to the ACP spec pretty well (better than codex, opencode etc.) so it's a good experience in Zed.
rohitpaulk
·il y a 3 mois·discuss
Most of the comments here are clearly from people who haven't used GitButler. Try it out and it's a very sticky product, clearly superior workflow to vanilla Git.
rohitpaulk
·il y a 4 mois·discuss
Saw this on Twitter a few weeks ago, interesting approach.

The post links to the GitHub repo, but imo the website does a better job of explaining what it does: https://ataraxy-labs.github.io/weave/
rohitpaulk
·il y a 4 mois·discuss
Two questions I'd have expected the article to answer:

(a) how did they identify the employee, and (b) how come they weren't sent to jail
rohitpaulk
·il y a 5 mois·discuss
Surprised that none of the comments here are comparing this to Bootstrap.
rohitpaulk
·il y a 5 mois·discuss
This sounds like a good optimization task to give a long-running agent. Ask it to come up with experiments and maximize the % of successful edits.
rohitpaulk
·il y a 6 mois·discuss
In case anyone finds it useful, we (CodeCrafters) built a coding challenge as a companion to this book. The official repository for the book made this very easy to do since it has tests for each individual chapter.

Link: https://app.codecrafters.io/courses/interpreter/overview
rohitpaulk
·il y a 7 mois·discuss
Wild how this beats 2.5 Pro in every single benchmark. Don't think this was true for Haiku 4.5 vs Sonnet 3.5.
rohitpaulk
·il y a 8 mois·discuss
For those who haven't seen the actual issue that links to, I'd take a closer look. Pretty insane: https://github.com/actions/runner/issues/3792#issuecomment-3...
rohitpaulk
·il y a 9 mois·discuss
Always felt dependency updates are a perfect fit for AI agents:

(a) they’re broadly similar across companies,

(b) they aren’t time-sensitive, so the agent can take hours without anyone noticing, and

(c) customers are already accustomed to using bots here, just bad ones
rohitpaulk
·il y a 4 ans·discuss
Yep, that's Ruby.