-
Intermittent Distillations #3
| 3406 wordsMundane solutions to exotic problems (Paul Christiano) Mundane solutions to exotic problems Summary Thinking about AI safety often leads to considering exotic problems: models purposefully altering their gradients, agents hiding their capabilities to defect when an opportunity arises, or humans being vulnerable to side-channel attacks. These exotic problems might seem...
-
Lumenator Recipe
| 109 wordsLet there be light. My current lumenator consists of three copies of the following: 2x LED Pure White CRI 95 Corn Bulb 1x LED Warm White CRI 95 Corn Bulb 1x Adesso Floor Lamp My previous lumenator consisted of: 3x 16 bulb light string 32x 5000k CRI 90 LED 16x...
-
Pre-Training + Fine-Tuning Favors Deception
| 962 wordsCrossposted from the AI Alignment Forum. May contain more technical jargon than usual. Thanks to Evan Hubinger for helpful comments and discussion. Currently, to obtain models useful for some task X, models are pre-trained on some task Y, then fine-tuned on task X. For example, to obtain a model that...
-
Less Realistic Tales of Doom
| 1263 wordsCrossposted from the AI Alignment Forum. May contain more technical jargon than usual. Realistic tales of doom must weave together many political, technical, and economic considerations into a single story. Such tales provide concrete projections but omit discussion of less probable paths to doom. To rectify this, here are some...
-
Making Markets Over Beliefs
| 949 wordsBetting is an excellent way to improve the accuracy of your beliefs. For example: Me: “I think Alice is 5’11.” Friend: “I’ll bet you $5 1:1 that it’s higher.” Translated, my friend means they’re willing to agree to a deal where I pay them $5 if Alice is taller than...
-
Agents Over Cartesian World Models
| 8610 wordsCoauthored with Evan Hubinger Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Thanks to Adam Shimi, Alex Turner, Noa Nabeshima, Neel Nanda, Sydney Von Arx, Jack Ryan, and Sidney Hough for helpful discussion and comments. Abstract We analyze agents by supposing a Cartesian boundary between...
-
Intermittent Distillations #2
| 2862 wordsServant of Many Masters: Shifting priorities in Pareto-optimal sequential decision-making (Andrew Critch and Stuart Russell) Servant of Many Masters: Shifting priorities in Pareto-optimal sequential decision-making Summary A policy (over some partially observable Markov decision process (POMDP)) is Pareto optimal with respect to two agents with different utility functions if it...
-
Meta-EA Needs Models
| 1251 wordsEpistemic status: a bunch of stuff Sometimes I have conversations with people that go like this: Me: Feels like all the top people in EA would have gotten into EA anyway? I see a bunch of people talking about how sometimes people get into EA and they agree with the...
-
RSS Feed
| 16 wordsMultiple people have requested an RSS feed for my blog. I have created one here.
-
Transparency Trichotomy
| 2062 wordsCrossposted from the AI Alignment Forum. May contain more technical jargon than usual. Introduction In Relaxed Adversarial Training for Inner Alignment, Evan presents a trichotomy of ways to understand a model M: Transparency via inspection: use transparency tools to understand M via inspecting the trained model. Transparency via training: incentivize...