Researcher pitches a multimodal scoring model: any image, any freeform texts, calibrated fit scores
ducha_aiki · x · 2026-10-01
Researcher duchaaiki, replying to @giffmana, half-jokingly sketches a 'multimodal Jevons' idea: given any image and any set of freeform texts, the model would return how well each text fits the image, plus calibrated yes/no outputs via sigmoid. He quips it might take hundreds of millions in funding, and teases giffmana to survive a few years on softmax before jumping to sigmoid.
Related event: Researchers Envision a Sub-1B Multimodal Scoring Model(2 posts)→
More from Fun
- Easter egg: liking any Grok Bot post on X triggers a surprise — soleio · 2026-10-01
- DevDay demo: Codex builds Minecraft for 30-year-old Game Boy hardware via ModRetro plugin — pvncher · 2026-10-01
- FuhuihuaBench meme benchmark: every model scores Pass@16 = 0 — bowenc0221 · 2026-10-01
- AI Kept Saying Ice It; ER Doctor Said Heat, Swelling Gone Next Day — DesireeCachette · 2026-10-01
- Researcher Says He Genuinely Enjoys LeetCode: 'I Did These Puzzles for Fun' — TimDarcet · 2026-10-01
- A literary glimpse of AI-native government: chatting with a .gov chatbot — KadriJibraan · 2026-10-01