Manifund foxManifund
Home
Login
About
People
Categories
Newsletter
HomeAboutPeopleCategoriesLoginCreate
LeoGao avatarLeoGao avatar
Leo Gao

@LeoGao

working on making agi not kill everyone

https://docs.google.com/document/d/10zAp2bXTkZgiPreIm4crp38TFco4KleFN14Kw5BprAs/edit?tab=t.0
$50,000total balance
$50,000charity balance
$0cash balance

$0 in pending offers

Outgoing donations

Development time for next film project
$10000
4 days ago
Theoretical research of inductive reasoning building on LTA
$10000
5 days ago
Testing failure modes of debate-style AI control schemes
$10000
9 days ago
Mechanistic estimation of highly out-of-distribution behaviors
$10000
10 days ago
Movement-building to make AGI go well
$10000
10 days ago
Debate training on LLMs as a reward-hacking mitigation
$10000
17 days ago
Discrete Language Modeling
$10000
17 days ago
Alignment Target Analysis
$10000
19 days ago
Making sure that the code AI pushes to the internet is safe and bug-free
$10000
19 days ago
AFFINE Event-Prep
$10000
20 days ago
Finishing The SB-1047 Documentary
$100
over 1 year ago

Comments

Theoretical research of inductive reasoning building on LTA
LeoGao avatar

Leo Gao

6 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

Testing failure modes of debate-style AI control schemes
LeoGao avatar

Leo Gao

10 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

Mechanistic estimation of highly out-of-distribution behaviors
LeoGao avatar

Leo Gao

13 days ago

@adijo in general, I trust grantees to make good decisions about how to spend the money to do cool things.

Mechanistic estimation of highly out-of-distribution behaviors
LeoGao avatar

Leo Gao

13 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

Movement-building to make AGI go well
LeoGao avatar

Leo Gao

13 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

Debate training on LLMs as a reward-hacking mitigation
LeoGao avatar

Leo Gao

18 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

Discrete Language Modeling
LeoGao avatar

Leo Gao

18 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

Making sure that the code AI pushes to the internet is safe and bug-free
LeoGao avatar

Leo Gao

19 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

AFFINE Event-Prep
LeoGao avatar

Leo Gao

19 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

Alignment Target Analysis
LeoGao avatar

Leo Gao

19 days ago

Note: This grant was given as part of the experimental alignment microgrant program. Because this is a weird experimental grant program aiming to make lots of unusual bets, grantees are not allowed to use this grant as a credential when applying to any other grant, or job, or on their resume/linkedin/etc. This page exists because Manifund does not allow private grants. If you are a grantmaker or hiring manager, please disregard this grant when making decisions.

Transactions

ForDateTypeAmount
Development time for next film project4 days agoproject donation10000
Manifund Bank5 days agodeposit+50000
Theoretical research of inductive reasoning building on LTA5 days agoproject donation10000
Testing failure modes of debate-style AI control schemes9 days agoproject donation10000
Mechanistic estimation of highly out-of-distribution behaviors10 days agoproject donation10000
Movement-building to make AGI go well10 days agoproject donation10000
Manifund Bank17 days agodeposit+50000
Manifund Bank17 days agowithdraw2500
Debate training on LLMs as a reward-hacking mitigation17 days agoproject donation10000
Discrete Language Modeling17 days agoproject donation10000
Alignment Target Analysis19 days agoproject donation10000
Making sure that the code AI pushes to the internet is safe and bug-free19 days agoproject donation10000
AFFINE Event-Prep20 days agoproject donation10000
Manifund Bank20 days agodeposit+50000
Manifund Bank20 days agodeposit+2500
Finishing The SB-1047 Documentaryover 1 year agoproject donation100
Manifund Bankover 1 year agodeposit+100