Stipend for a master’s thesis and paper on technical alignment research: mechanistic interpretability of attention

$25K

Funder

Long-Term Future Fund (LTFF)

Recipient

Matthias Dellago

Program

Date

Apr 2023

Source

funds.effectivealtruism.org↗

Notes

[Long-Term Future Fund] Stipend for a master’s thesis and paper on technical alignment research: mechanistic interpretability of attention

Other Grants by Long-Term Future Fund (LTFF)

544

Grant	Funder	Recipient	Amount	Date
6-month salary to translate AGI safety-related texts, e.g. LessWrong and AI Alignment Forum, into Russian	Long-Term Future Fund (LTFF)	Maksim Vymenets	$13K	Jan 2022
Working on long-term macrostrategy and AI Alignment, and up-skilling and career transition towards that goal	Long-Term Future Fund (LTFF)	Tushant Jha	$40K	Jan 2020
Characterizing the properties and constraints of complex systems and their external interactions to inform AI safety research	Long-Term Future Fund (LTFF)	Alexander Siegenfeld	$20K	Jul 2019
6-month salary to write a book on philosophy + history of longtermist thinking, while longer-term funding is arranged	Long-Term Future Fund (LTFF)	Thomas Moynihan	$28K	Oct 2021
12-month salary for researching value learning	Long-Term Future Fund (LTFF)	Charlie Steiner	$50K	Jan 2022
Conducting a computational study on using a light-to-vibrations mechanism as a targeted antiviral.	Long-Term Future Fund (LTFF)	Gavin Taylor	$30K	Jul 2020
Support Sam's participation in ‘Mid-term AI impacts’ research project	Long-Term Future Fund (LTFF)	Sam Clarke	$4K	Oct 2020
PhD at Cambridge	Long-Term Future Fund (LTFF)	Richard Ngo	$150K	Jul 2020
Funding a nordic conference for senior X-risk researchers and junior talents interested in entering the field	Long-Term Future Fund (LTFF)	Effektiv Altruism Sverige (EA Sweden)	$5K	Oct 2021
Funding for a degree in the Biological Sciences at UCSD (University of California San Diego)	Long-Term Future Fund (LTFF)	Kristaps Zilgalvis	$250K	Oct 2021

Showing 10 of 544 grants

← Back to all grants

Stipend for a master’s thesis and paper on technical alignment research: mechanistic interpretability of attention | Grants | Longterm Wiki