Re:Show HN: Tarsier – Vision utilities for web interaction a...
by pk19238 on Wednesday May 15, 2024 @12:59PM
(#40369513)
this is such a creative solution. reminds me of how a team rendered wolfenstein into ASCII characters and fine tuned mistral to successfully play it.
[ Parent
| on HN ]
Re:Show HN: Tarsier – Vision utilities for web interaction a...
by KhoomeiK on Wednesday May 15, 2024 @01:04PM
(#40369569)
Thanks! Yeah, it seems like a lot can be done with just text while we wait for multimodal models to catch up. The recent Platonic Representation Hypothesis [1] also suggests that different models, regardless of modality, build the same internal representations of the world.