As an HR leader, I'm often asked how to justify LLM-driven decisions. I wonder if we'll end up understanding LLM reasoning and interpretability better than we can explain why humans make certain decisions.
The full paper is available here: transformer-circuits.pub/202…
We're hiring researchers and engineers to investigate AI cognition and interpretability: job-boards.greenhouse.io/ant…
*leaping up and down wildly*
I'm barely a quarter into this paper but it's already SO COOL!!
Look at Opus exactly replicating the "split brain confabulation" behavior that we see in humans!
The full paper is available here: transformer-circuits.pub/202…
We're hiring researchers and engineers to investigate AI cognition and interpretability: job-boards.greenhouse.io/ant…
An interesting paper, presenting a smart method for examining reflexion and self-representation of LLMs.
The full paper is available here: transformer-circuits.pub/202…
We're hiring researchers and engineers to investigate AI cognition and interpretability: job-boards.greenhouse.io/ant…