Kunvar avatar
Kunvar Thaman

@Kunvar

Mechanistic Interpretability researcher

mechinterp.com
$1,095total balance
$1,095charity balance
$0cash balance

$0 in pending offers

Projects

Outgoing donations

Comments

Kunvar avatar

Kunvar Thaman

4 months ago

I have been in this position before for my own first paper, and I can understand how important and useful it can be, especially for an early career-researcher. I am funding this project with $300 and hope that others are able to support you further.

Kunvar avatar

Kunvar Thaman

10 months ago

I donated some starting amount that should help get started with the project. I think it’s a fairly low cost investment towards studying a clear problem with a big blind spot (so few RCTs include asian indians, the highest risk group? I was really surprised when I looked it up - they're one of the most at-risk groups and still there's not much research towards that particular demographic).

I do hope other people contribute more towards this project - lab tests for 120 people over 5 months and a literature review, for ~$20k? That alone seems like a good deal to me, and the potential impact of improving health for at-risk people with low-cost routine is really good.

Kunvar avatar

Kunvar Thaman

11 months ago

I think Michael's podcast (and sometimes "not a podcast") episodes are fantastic. The Inside view (Michael's podcast), Dwarkesh's podcast, and the MLST (Machine learning street talk) are my go-to AI-related podcasts and the selection of guests that Michael brings is impressive, with a good focus on AI-safety researchers.

I've personally listened to a lot of his episodes, almost all released in 2022 and 2023, and I've recommended a fair amount of them to others - they're quite well done (such as the recent episode with Evan Hubinger - really good).

I don't think it's the production quality that's the barrier for youtube views which @Austin points out below, but more to do with marketing, and I'd recommend reaching out to more established people in the podcasting world for figuring that out.

I'm going to donate a token $500 and hope others can help fund Michael more, the work he's doing is great and quite impactful (especially for people in the early stages of an AI safety career).

Transactions

ForDateTypeAmount
Travel funding to the International Conference on Algorithmic Decision Theory.4 months agoproject donation300
Manifund Bank10 months agodeposit+500
Manifund Bank10 months agomana deposit+68
Investigating the Effects of IF in the reversal of Type 2 Diabetes Mellitus.10 months agoproject donation8500
Manifund Bank10 months agomana deposit+31
Manifund Bank10 months agomana deposit+16
Manifund Bank10 months agomana deposit+20
Manifund Bank10 months agomana deposit+22
Manifund Bank10 months agomana deposit+73
Manifund Bank11 months agomana deposit+37
Making 52 AI Alignment Video Explainers and Podcasts11 months agoproject donation500
Manifund Bank11 months agomana deposit+10
Manifund Bank11 months agomana deposit+9
Manifund Bank11 months agomana deposit+8
Manifund Bank11 months agomana deposit+84
Manifund Bank11 months agomana deposit+58
Manifund Bank11 months agomana deposit+38
Manifund Bank12 months agomana deposit+200
Manifund Bank12 months agomana deposit+56
Manifund Bankabout 1 year agomana deposit+350
Manifund Bankabout 1 year agomana deposit+20
Manifund Bankabout 1 year agomana deposit+400
Manifund Bankabout 1 year agomana deposit+210
Manifund Bankabout 1 year agomana deposit+75
Manifund Bankabout 1 year agomana deposit+1000
Manifund Bankabout 1 year agomana deposit+5000
Manifund Bankabout 1 year agomana deposit+200
Manifund Bankabout 1 year agomana deposit+100
Manifund Bankabout 1 year agomana deposit+100
Manifund Bankabout 1 year agomana deposit+180
Manifund Bankabout 1 year agomana deposit+150
Manifund Bankabout 1 year agomana deposit+300
Manifund Bankabout 1 year agomana deposit+240
Manifund Bankabout 1 year agomana deposit+240
Manifund Bankabout 1 year agomana deposit+300
Mapping neuroscience and mechanistic interpretability about 1 year agoproject donation100
Manifund Bankabout 1 year agowithdraw8500
Exploring feature interactions in transformer LLMs through sparse autoencodersabout 1 year agoproject donation+8500
Manifund Bankabout 1 year agomana deposit+400