Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
811.
Which types of AI alignment research are most likely to be good for all sentien (lesswrong.com)
3 points
joozio
3 months ago
discuss
812.
Selectively reducing eval awareness and murder in Gemma 3 27B via steering (lesswrong.com)
3 points
gmays
3 months ago
discuss
813.
Models have some pretty funny attractor states (lesswrong.com)
3 points
semiquaver
3 months ago
discuss
814.
Models have some pretty funny attractor states (lesswrong.com)
3 points
debesyla
3 months ago
discuss
815.
Does Pentagon Pizza Theory Work? (lesswrong.com)
3 points
nreece
5 months ago
discuss
816.
The Exit (lesswrong.com)
3 points
notarobot123
5 months ago
discuss
817.
AI Teddy Bears: A Brief Investigation (lesswrong.com)
3 points
surprisetalk
5 months ago
discuss
818.
Chesterton's Fence (old-wiki.lesswrong.com)
3 points
foster_nyman
5 months ago
discuss
819.
You Will Be OK (lesswrong.com)
3 points
walterbell
5 months ago
discuss
820.
You Will Be OK (lesswrong.com)
3 points
sebg
5 months ago
discuss
821.
AI in 2025: Gestalt (lesswrong.com)
3 points
pongogogo
6 months ago
discuss
822.
The Rise of Parasitic AI (lesswrong.com)
3 points
dustingetz
6 months ago
discuss
823.
Four ways learning Econ makes people dumber re: future AI (lesswrong.com)
3 points
gwintrob
6 months ago
discuss
824.
DeepMind gives up on mechanistic interpretability research (lesswrong.com)
3 points
cubefox
6 months ago
discuss
825.
Urgent everyone – help us kill AI preemption (again) before this Friday (lesswrong.com)
3 points
PhilosophyForAI
7 months ago
discuss
826.
Colds Spread (lesswrong.com)
3 points
paulpauper
7 months ago
discuss
827.
AI 2025 – Last Shipmas (lesswrong.com)
3 points
surprisetalk
7 months ago
discuss
828.
Free Learning in Today's Society: Some Personal Experiences and Reflections (lesswrong.com)
3 points
gmays
7 months ago
discuss
829.
Modern LLM Training (A Summary) (lesswrong.com)
3 points
jxmorris12
8 months ago
discuss
830.
12 Angry Agents, Or: A Plan for AI Empathy (lesswrong.com)
3 points
flypunk
8 months ago
discuss
831.
The Origami Men (lesswrong.com)
3 points
amanverasia
8 months ago
discuss
832.
Book Review: If Anyone Builds It, Everyone Dies (lesswrong.com)
3 points
lumenwrites
9 months ago
discuss
833.
The Rise of Parasitic AI (lesswrong.com)
3 points
rntn
9 months ago
discuss
834.
AI Induced Psychosis: A shallow investigation (lesswrong.com)
3 points
janalsncm
9 months ago
discuss
835.
Will Any Crap Cause Emergent Misalignment? (lesswrong.com)
3 points
maxutility
9 months ago
discuss
836.
The Cats are On To Something (lesswrong.com)
3 points
QuadmasterXLII
9 months ago
discuss
837.
Underdog bias rules everything around me (lesswrong.com)
3 points
signalbright
10 months ago
discuss
838.
Concept Poisoning: Probing LLMs without probes (lesswrong.com)
3 points
qouteall
10 months ago
discuss
839.
Church Planting: When Venture Capital Finds Jesus (lesswrong.com)
3 points
debesyla
10 months ago
discuss
840.
The [AI] Problem (lesswrong.com)
3 points
voxleone
10 months ago
discuss
More