The hostile telepaths problem — LessWrong
lesswrong.com · 18,105 words · saved by 4 readers
---------------------------------------- • Imagine you're a very young child. Around, say, three years old. …
x The hostile telepaths problem — LessWrong Best of LessWrong 2024 Self-Deception Newcomb's Problem Subagents Consciousness Rationality Curated 436 The hostile telepaths problem by Valentine 27th Oct 2024 18 min read 107 436 Epistemic status: model-building based on observation, with a few successful unusual predictions. Anecdotal evidence has so far been consistent with the model. This puts it at risk of seeming more compelling than the evidence justifies just yet. Caveat emptor. Imagine you're a very young child. Around, say, three years old. You've just done something that really upsets you
saved by
related reading
- Deep Deceptiveness — LessWronglesswrong.com
- So you wanna de-bog yourself - by Adam Mastroianniexperimental-history.com
- Maybe you’re not Actually Trying - by Cate Hallusefulfictions.substack.com
- Self-Help Tactics That Are Working For Me — LessWronglesswrong.com
- Self-Other Overlap: A Neglected Approach to AI Alignment — LessWronglesswrong.com
- Self-Deception (Stanford Encyclopedia of Philosophy)plato.stanford.edu
- Eliezer's Unteachable Methods of Sanity — LessWronglesswrong.com
- Here's the exit. — LessWronglesswrong.com
- Dark Arts of Rationality — LessWronglesswrong.com
- Why We Fool Ourselvescoffeeandjunk.com
- Sandbagging with misaligned action - Chain-of-Thought Transcript - Anti-Schemingantischeming.ai
- Annoyingly Principled People, and what befalls them — LessWronglesswrong.com