Dharshan Kumaran

Neuroscientist → ML researcher @ DeepMind · LLMs, Metacognition, confidence · Chess GM · London

[Dharshan Kumaran @dharshsky]

Are LLMs stubborn or oversensitive to pushback? Both—at once. Our new @NatMachIntell paper helps us understand why LLMs become more confident in their initial answers, and how they markedly overweight opposing advice. Open access at: https://t.co/JzSjAAxwQQ @GoogleDeepMind × @UCL_ICN

[Dharshan Kumaran @dharshsky]

@marcgbellemare @hugo_larochelle Congratulations Marc!

[Dharshan Kumaran @dharshsky]

@summerfieldlab congrats Chris that's great :)