“capture code” could be a very cool basis for RLHF/retraining. this thing is bootstrapping itself!
@swyx
-
Telemetry Insights and Alternative Metrics for AI Suggestion Success
By
–
enjoyed the telemetry bit, shows how much they care about reporting success of this thing perhaps time based measurement might be buggy if eg i walk away from my desk after seeing a horrible suggestion perhaps could measure based on #’s of edits after a suggestion was accepted
-
Debug Mode for Copilot: Expose Scores, Latencies, and Prompts
By
–
idea for extension: offer a “debug mode” modified version of copilot with all these scores and latencies and prompts exposed, so that people can gain an intuition of whats coming in and out as they type
-
Principal Components as Axes: A Humorous PCA Visualization Concept
By
–
imagine "principal component 1" and "principal component 2" as axes haha
-

Stable Diffusion Generates Music by Learning Images of Sheet Music
By
–
wait lol so turns out the solve to AI music generation wasnt novel approaches to learning the underlying structures of music
— swyx 🐣 (@swyx) 15 décembre 2022
it was taking #StableDiffusion and finetuning for IMAGES OF MUSIC
and THAT WORKS?!?
synesthetes could never 🤯 https://t.co/zSfpFqsP3N pic.twitter.com/8gTbG5ZZuHwait lol so turns out the solve to AI music generation wasnt novel approaches to learning the underlying structures of music it was taking #StableDiffusion and finetuning for IMAGES OF MUSIC and THAT WORKS?!? synesthetes could never
-
What if smaller, sparser models all fail?
By
–
there is ongoing research toward smaller, sparser, human-efficient models, but what if they *all* fail. scary thought.
-
AI as Alien Intelligence: Different from Human Inspiration
By
–
“Artificial Intelligence is a very alien intelligence – just like birds inspired airplanes, but airplanes work very differently than birds.” — dynamite quote from @sama
-
Seeking source for GPT-3 family tree graphic
By
–
great graphic – is there a canonical source for the gpt3 family tree or did you just come up with this? (want to make sure i cite properly when i definitely use this in future)
-
Added AI products notes to GitHub repository
By
–
added! https://
github.com/sw-yx/ai-notes
/blob/main/TEXT.md#products-1
… -
AGI Existential Risk Concern Contradicts Luddite Philosophy
By
–
i think believing AGI could be an existential threat is the exact opposite of Luddism