Zsolt Ero (@hyperknot) / X

Zsolt Ero
@hyperknot
Sep 24
Dear @pidotdev team (@mitsuhiko @badlogicgames) I opened my 11th meaningful GitHub issue: auto-closed like always. I've spent at least 10 minutes on each of those issues and many have contributed to meaningful discussion or PRs. No matter how much I love pi and the core
1
Zsolt Ero
@hyperknot
Sep 24
Opus 5.5 is the first model in a very long time which I really enjoy using. It doesn't want to over-engineer, happy to remove and simplify, and is generally an nice partner to work with. Last model which I enjoyed so much was Opus 4.6 from almost a year ago.
1
Zsolt Ero
@hyperknot
Sep 10
That's how you create generational wealth in 14 hours. (After spending a decade of your life tackling difficult problems.) Thank you for the inspiration @tldraw!
tldraw
@tldraw
Sep 10
Here you go, link in the next post
00:00
Quote
Tibo
@thsottiaux
Sep 10
Show me. Post tomorrow by EOD
Zsolt Ero
@hyperknot
Sep 9
Opus happily finished the UI refining step, with visual feedback in a Playwright loop. Do LLMs not feel pain when looking at this?
Zsolt Ero
@hyperknot
Sep 7
OpenAI researchers be like: 25% of the human cortex is dedicated to vision, why not do the same in GPT-6? Mixture of Experts could also let vision parts stay dormant for non-vision tasks, so it doesn’t add much inference cost.
SkalskiP
@skalskip92
Sep 7
Astra can do segmentation this is pure VLM result. no expert models (like SAM) were used No other VLM even comes close to this quality - high effort - avg input tokens / image: 2,052 - avg output tokens / image: 4,685 - avg cost / image: $0.255 - median time / image: 78.3 s