LESSWRONG
LW

epistemic meristem
350270
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
Self-fulfilling misalignment data might be poisoning our AI models
epistemic meristem4mo40

See also: If Bad Things Happen, It Is Your Fault For Predicting Them :)

Reply3
johnswentworth's Shortform
epistemic meristem8mo20

(There was already a linkpost.)

Reply
AI #88: Thanks for the Memos
epistemic meristem8mo10

What are the most noteworthy sections to read? (Looks like you forgot to bold them.) Thanks!

Reply
Exercise: Solve "Thinking Physics"
epistemic meristem1y10

The Amazon link in the post is for the third (and latest) edition, only $28. Your other links are for the second edition, except the Harvard link's dead.

Reply
Cortés, AI Risk, and the Dynamics of Competing Conquerors
epistemic meristem2y70

Related: Lessons on AI Takeover from the conquistadors

Reply
AI #33: Cool New Interpretability Paper
epistemic meristem2y20

Did you forget to bold the particularly noteworthy sections in the table of contents?

Reply
Open Call for Research Assistants in Developmental Interpretability
epistemic meristem2y41

More than a 76% pay cut, because a lot of the compensation at Google is equity+bonus+benefits; the $133k minimum listed at your link is just base salary.

Reply
Alignment Grantmaking is Funding-Limited Right Now
epistemic meristem2y21

I'd thought it was a law of nature that quiet norms for open plans don't actually work; it sounds like you've found a way to have your cake and eat it too!

Reply
MIRI announces new "Death With Dignity" strategy
epistemic meristem2y20

That's fair; thanks for the feedback! I'll tone down the gallows humor on future comments; gotta keep in mind that tone of voice doesn't come across.

BTW a money brain would arise out of, e.g., a merchant caste in a static medieval society after many millennia. Much better than a monkey brain, and more capable of solving alignment!

Reply
Towards Hodge-podge Alignment
epistemic meristem2y10

Beren, have you heard of dependent types, which are used in Coq, Agda, and Lean? (I don't mean to be flippant; your parenthetical just gives the impression that you hadn't come across them, because they can easily enforce integer bounds, for instance.)

Reply
Load More
No posts to display.