Viewing profile — sebnado
sebnado
HN member- Joined
- Mon, Apr 28, 2025, 2:50 AM UTC
- HN karma
- 4
- Public activity
- 9 items
- HN profile
- View on Hacker News ↗
About sebnado
No profile information was provided.
Recent public activity
-
story
Show HN: WorldBuild Bench repo: testing LLM world coherence with 3D games
I built WorldBuild Bench because, as we all know, llm bench scores often say something very different from what models actually feel like to use. It's really dependent on the type …
-
comment
Comment #48982451
I think it would benefit from having a upvote type of feature to surface opinions/comments that people agree with. if you have many people with the same insight in your thread, the…
-
comment
Comment #48982307
love it I can think of many projects that could use that
- story
-
comment
Comment #44161523
We’ve been running an AI-first dev loop in production for ~2 years (disclaimer: I help build Ze1 and Sandscape, they are both Ai driven products). A few things we’ve learned: Inste…
-
comment
Comment #44161438
Fascinating read. I see the same tension: today’s models are masters of interpolation, but they still lack intentionality. If we push them toward “cognitive exoskeletons” (handling…
-
comment
Comment #44161385
Thing whole thing is a bit dumb tbh. You send conflicting requests to the LLM and it fails at doing both. It's nothing new, we all know it. Every article's headline make it sound l…
-
comment
Comment #44154608
By saying that's its gold mine, I think OP meant that's it's funny, not that it brings valuable insight. ie: THEY KNOW -> that made me laugh and as the article said "an LLM who jus…
-
comment
Comment #44154581
It's a really good approach for procedural maps, but if you want to achieve realism, you'll likely need something like Gaea