Community Polls on Alignment Controversies II
Please spend
Latest
My Assessment of Compute Verification in Plan A (+ open questions)
OverviewThese are my non-expert notes on the compute verification section of AIFP’s Plan A. I cover interconnect limits, memory wipes, network taps + replay, and ZKPs.…
Hint-based CoT faithfulness evals still mostly work on Claude
Thanks to Fabien Roger (Anthropic), who pointed out this system card mistake to me. This mistake will likely be fixed in the relevant system cards after…
Internal State Control is a General Property of LLMs
tl;dr:Lindsey 2025 found models can modulate their internal states: when instructed to “think about” a concept while writing an unrelated sentence, the representation of the concept…
New role: Senior Researcher – MIT AI Risk Initiative
As AI capabilities rapidly advance, we face critical information gaps in effective AI risk management: What are the risks from AI, which are most important, and…
So you want to use plants to reduce CO₂
Humans make carbon dioxide. Carbon dioxide is bad for cognition. But plants turn carbon dioxide back into oxygen. And plants are the one true home decoration…
Big-World Intuitions
Consider the following situations:when you are a small, growing startup in a big market, standard advice is not to worry too much about your competitors or…
Prompt to make Opus 5 act like a base model
The text as follows:see the below—makes Claude think that the prompt is unfinished, and fill in its own prompt.It will subsequently claim that it recieved what…
Testing LLMs on Undergraduate Music Theory
I spent the past week designing a test that I hoped would serve as a benchmark. But LLMs are improving faster than I expected, and my…
The Entangled Dimensions of Decision Theory
TL;DR. LessWrong's decision-theory debates (Newcomb, FDT vs CDT, counterfactual muggings) are almost entirely about what we suppose when we consider a candidate action or policy. There…