x

LESSWRONG

LW

hiki_t — LessWrong

hiki_t

hiki_t

Message

Cognitive Neuroscience Researcher at Cardiff University/UCL, aiming to develop biologically-inspired robust internal representations of everyday objects in AI systems (and then more complex internal representations for further complex tasks).

2

2y

hiki_t

Cognitive Neuroscience Researcher at Cardiff University/UCL, aiming to develop biologically-inspired robust internal representations of everyday objects in AI systems (and then more complex internal representations for further complex tasks).

AI alignment for mental health supports

Initial Draft on 23 February Goals As an affiliate member of Cajal.org, I[1] would like to introduce a novel application of AI alignment as a tool for diagnosing, visualising, predicting, preventing and improving mental health symptoms in human users. Motivations Globally, nearly a billion people (1 in 8) are disgnosed...

Feb 24, 2025•1

Automated monitoring systems

Initial draft on 28th Nov, 2024 After participating in the last (18th Nov, 2024) and this week (25th Nov, 2024)'s group discussion about topics of the “𝘀𝗰𝗮𝗹𝗮𝗯𝗹𝗲 𝗼𝘃𝗲𝗿𝘀𝗶𝗴𝗵𝘁” and AI model's “𝗿𝗼𝗯𝘂𝘀𝘁𝗻𝗲𝘀𝘀” at the AI Safety Fundamentals program, I have been stuck with thinking what are effective use cases of...

Nov 28, 2024•1