Subscribe
Sign in
Home
Podcast
Website
Archive
About
Notes on Inference Integrity
Claude Fable’s deliberately triggered sandbagging shows that training-time targets are, by themselves, insufficient to guarantee particular LLM…
Jul 13
•
James Tillman
12
2
Plan A’s problem with dry tinder
How bad would it be to make the intelligence explosion 10x faster?
Jul 10
•
Tom Davidson
27
2
6
Can AI do philosophy?
A guest post by Bentham’s Bulldog, created while they were a visiting scholar at Forethought.
Jul 7
•
Bentham's Bulldog
13
6
2
Will We Put Data Centers In Space?
A podcast episode from Forethought
Jul 7
•
Fin Moorhouse
2
3
How Fast Is Post-AGI Growth?
A podcast episode from Forethought
Jul 5
•
Fin Moorhouse
Latest
Top
Discussions
We Should Hand Off To Morally Reflective AIs
This article was created by Forethought. See our research on our website.
Jun 24
•
Bentham's Bulldog
44
44
13
Risk-Averse AIs
This article was created by Forethought. Read the full article on our website.
Jun 24
•
Elliott Thornley
and
Will MacAskill
16
12
6
Could AI Help Solve Philosophy?
A podcast conversation with Wei Dai
Jun 19
•
Fin Moorhouse
22
1
What should go in a model spec?
Suppose an AI company is considering whether to include some particular quality X – a rule, virtue, heuristic, default, attitude, goal, or style – in a…
Jun 4
•
James Tillman
7
1
How can the middle powers avoid getting trounced during the intelligence explosion? A plan.
Superintelligence will likely be developed by US companies; run on US data centres; and be under the jurisdiction of the US government.
May 27
•
Tom Davidson
17
2
2
Will We Really Put Data Centers in Space?
This article was created by Forethought. Read the full article on our website.
May 22
•
Avi Parrack
and
Fin Moorhouse
21
2
1
A Research Agenda for Secret Loyalties
Kwon et al., have published a new paper: “AIs with Secret Loyalties are a Serious but Addressable Threat”.
May 21
•
Forethought
11
1
See all
ForeWord
How should we navigate explosive AI progress? The latest research from Forethought.
Subscribe
Recommendations
View all 14
Miles’s Substack
Miles Brundage
Transformer
Transformer
Strange Cities
Owen Cotton-Barratt
Benjamin Todd
Benjamin Todd
AI Futures Project
Daniel Kokotajlo
Links
Podcast
Our website
ForeWord
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
