Viewing profile — gnunicorn
gnunicorn
HN member- Joined
- Wed, Jun 10, 2026, 11:15 PM UTC
- HN karma
- 29
- Public activity
- 8 items
- HN profile
- View on Hacker News ↗
About gnunicorn
Recent public activity
-
story
What are you looking for when reviewing LLM generated code?
For work I often have to review multi thousand file changes in PR mostly generated by AI/Llama/claude code. It's mainly rust with many unit tests, so there is a lot tooling helps v…
-
comment
Comment #48515484
Interestingly, despite it being much more detailed and a lot more process and procedure than what I currently do - which is more akin to the version 0 described, but in parallel - …
-
comment
Comment #48506736
Just because everything is a potential threat vector now: doesn't this also mean you could easily put AI specific malicious instructions into the PDF that the regular human would n…
-
comment
Comment #48503297
Sounds like the default k8s setup every startup deploys to not fail it single digit number of users. It learned from the best
-
comment
Comment #48495233
Yeah, same sentiment here. I agree that some more people need to be told to relax a little in our field, but on the other side, the product and project managers are constantly look…
-
comment
Comment #48494812
I totally see where they are coming from, jitsu, too is making every change its own artifact. And it plays hard to the "faster shipping" that especially AI-driven teams are pushing…
-
comment
Comment #48490725
Odd though, isn't it? Considering it is supposedly from April already...?!?
-
comment
Comment #48484253
It was a great hack, but it was always just that: a hack. We all always knew that the "certificate authority"-hierarchy is broken and can easily be abused by the ones in power. I a…