Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
simonw
6 months ago
|
parent
|
context
|
favorite
| on:
GPT-5 Thinking in ChatGPT (a.k.a. Research Goblin)...
Yeah, I've been disappointed in GPT-5 for OCR - Gemini 2.5 is
much
better on that front:
https://simonwillison.net/2025/Aug/29/the-perils-of-vibe-cod...
IanCal
6 months ago
[–]
Images in general, nothing comes close to Gemini 2.5 for understanding scene composition. They perform segmentation and so you can even ask for things like masks of arbitrary things or bounding boxes.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: