With LLMs, we like to think of 'smart' and 'dumb' as one axis (because we think of humans this way). I'd like to argue against this framing. Instead, try to think of 'smart' and 'dumb' as two differe
Why CEREBRO kept it
Novel LLM capability framing, two-axis model intelligence
The text below is an automated extraction of the article at https://x.com/theo/status/2103975208105443555, stored verbatim in the public cerebro-vault repository. Copyright remains with the original publisher (x.com).
I'd like to argue against this framing. Instead, try to think of "smart" and "dumb" as two differe
> Novel LLM capability framing, two-axis model intelligence
With LLMs, we like to think of "smart" and "dumb" as one axis (because we think of humans this way).
I'd like to argue against this framing. Instead, try to think of "smart" and "dumb" as two different axes. A model can be incredibly smart AND dumb at the same time.
For a good example of this, look at a Gemini model. They are incredibly smart: you can bench them and see the capability. The amount of knowledge Google bakes into their models is incredible. Yet when you ask it to do work, the amount of stupid things the models will do is similarly incredible. They are "smart" and "dumb" at the
Backlinks
Appeared in 1 briefing