Longterm Wiki

Fine-tuning large language models for an interpretability challenge (compute costs)

$11K
Funder
Long-Term Future Fund (LTFF)
Recipient
Andrei Alexandru
Program
xng_1vsce_
Date
2022
Source
funds.effectivealtruism.org↗
Notes

[Long-Term Future Fund] Fine-tuning large language models for an interpretability challenge (compute costs)

Other Grants by Long-Term Future Fund (LTFF)

544
GrantFunderRecipientAmountDate
6-month salary to translate AGI safety-related texts, e.g. LessWrong and AI Alignment Forum, into RussianLong-Term Future Fund (LTFF)Maksim Vymenets$13KJan 2022
Working on long-term macrostrategy and AI Alignment, and up-skilling and career transition towards that goalLong-Term Future Fund (LTFF)Tushant Jha$40KJan 2020
Characterizing the properties and constraints of complex systems and their external interactions to inform AI safety researchLong-Term Future Fund (LTFF)Alexander Siegenfeld$20KJul 2019
6-month salary to write a book on philosophy + history of longtermist thinking, while longer-term funding is arrangedLong-Term Future Fund (LTFF)Thomas Moynihan$28KOct 2021
12-month salary for researching value learningLong-Term Future Fund (LTFF)Charlie Steiner$50KJan 2022
Conducting a computational study on using a light-to-vibrations mechanism as a targeted antiviral.Long-Term Future Fund (LTFF)Gavin Taylor$30KJul 2020
Support Sam's participation in ‘Mid-term AI impacts’ research projectLong-Term Future Fund (LTFF)Sam Clarke$4KOct 2020
PhD at CambridgeLong-Term Future Fund (LTFF)Richard Ngo$150KJul 2020
Funding a nordic conference for senior X-risk researchers and junior talents interested in entering the fieldLong-Term Future Fund (LTFF)Effektiv Altruism Sverige (EA Sweden)$5KOct 2021
Funding for a degree in the Biological Sciences at UCSD (University of California San Diego)Long-Term Future Fund (LTFF)Kristaps Zilgalvis$250KOct 2021
Showing 10 of 544 grants
← Back to all grants
Fine-tuning large language models for an interpretability challenge (compute costs) | Grants | Longterm Wiki