NoFOMO
Search 中EN Sign in Sign up

Peaked at #2 Off the board

Developer says LLMs outpace tuning

Dev argues LLM models improve faster than users' custom workflows, so naively using vanilla Codex is closer to state of the art.

First on the board · How the board is ranked

Rank over time

Original post

dax @thdxr 175.5K followers

a weird inversion with LLMs is the models improve faster than the tinkerers when i see people with custom workflows and setups they're all addressing problems that don't exist anymore the person naively using vanilla codex is more likely to be experiencing state of the art
7,596likes 341reposts 444replies 339.3Kviews

View on X Save

Top replies on X

Sign in to see 5 top replies from X

From @wolfr_2, @LasanKH8, @DavidKPiano and others. Spam removed, with English and Chinese translations.

Sign up free Have an account? Sign in

Discussion 0

Top Newest

No comments yet. Start the conversation.

Suggest a source

Is there a first-hand source we're missing, or a topic we should watch? Tell us. Once approved, everyone's board covers it.

@username or profile link