MATS 10.0 Neel Subliminal Learning

active

Write a paper explaining the mechanisms of subliminal learning as steering vector distillation, funded retroactively for time spent by Agam Bhatia.

Endorsed by

Neel

Donate:Manifund

Write a paper explaining the mechanisms of subliminal learning as steering vector distillation, funded retroactively for time spent by Agam Bhatia.

Endorsed by

Neel

Donate:Manifund

Project Details

Project summary

Subliminal Learning is Steering Vector Distillation

What are this project's goals? How will you achieve them?

Writing a paper explaining the mechanisms behind subliminal learning

How will this funding be used?

Retroactive grant for hours worked on the paper

Who is on your team? What's your track record on similar projects?

Agam Bhatia

What are the most likely causes and outcomes if this project fails?

It has already succeeded

How much money have you raised in the last 12 months, and from where?

People

Camila Blank

creator

Funding Details

Start Date: -
End Date: -
Expected Duration: -
Funding Raised to Date: -
Annual Budget: -
Monthly Burn Rate: -
Current Runway: -
Funding Goal: $19,200
Funding Stage: -
Fiscal Sponsor: -

Grants Received

Add grant

Neel Nanda → MATS 10.0 Neel Subliminal Learning

from Neel Nandamanifund.org

$19,200

Discussion

NNeel Nanda2mo

I’m funding two of my MATS scholars for two months each for work done on a paper explaining what’s going on with subliminal learning. This was during a period when they were not funded by the main MATS programme, paid at the same rates as MATS. While there is an obvious conflict of interest, since I supervised the paper, I do not financially profit and my bar for mentoring people is noticeably higher than my bar for funding them, so I am not too worried about this. And I think this is a great paper! Subliminal learning is a mysterious phenomenon of wide interest, and I think the forthcoming paper provides a satisfying explanation. Basic science on mysterious phenomena in LLMs is valuable work in a bunch of hard to foresee ways.

CCamila Blank2mo

Thanks @NeelNanda!