Alexander_Heckett

Karma: 159

Undergraduate math major at Carnegie Mellon University, interested in theoretical aspects of AI Safety via Debate, control, game theory, and probabilistic logic. I’m currently doing theoretical AI Safety via Debate research under Professor Vincent Conitzer.

Topological Debate Framework

Alexander_Heckett16 Jan 2025 17:19 UTC

10 points

5 comments9 min readLW link

Theoretical Alignment’s Second Chance

Alexander_Heckett22 Dec 2024 5:03 UTC

30 points

4 comments2 min readLW link

lunatic_at_large’s Shortform

Alexander_Heckett21 Dec 2024 17:13 UTC

2 points

4 comments1 min readLW link

[Question] Current State of Probabilistic Logic

Alexander_Heckett7 Oct 2023 5:06 UTC

3 points

2 comments1 min readLW link

Underspecified Probabilities: A Thought Experiment

Alexander_Heckett4 Oct 2023 22:25 UTC

8 points

4 comments2 min readLW link

Conditionals All The Way Down

Alexander_Heckett30 Sep 2023 21:06 UTC

33 points

2 comments3 min readLW link

[Question] Lesswrong’s opinion on infinite epistemic regress and Bayesianism

Alexander_Heckett17 Sep 2023 2:03 UTC

6 points

3 comments1 min readLW link

Probabilistic argument relationships and an invitation to the argument mapping community

Alexander_Heckett9 Sep 2023 18:45 UTC

13 points

4 comments10 min readLW link