Podcast Transcript: Daniela and Dario Amodei on Anthropic 2023-03-07T16:47:53.589Z

[Simulators seminar sequence] #2 Semiotic physics - revamped 2023-02-27T00:25:52.635Z

Full Transcript: Eliezer Yudkowsky on the Bankless podcast 2023-02-23T12:34:19.523Z

Human decision processes are not well factored 2023-02-17T13:11:10.854Z

Don't accelerate problems you're trying to solve 2023-02-15T18:11:30.595Z

FLI Podcast: Connor Leahy on AI Progress, Chimps, Memes, and Markets (Part 1/3) 2023-02-10T13:55:59.387Z

Book Review: Worlds of Flow 2023-01-16T20:17:16.022Z

[Simulators seminar sequence] #1 Background & shared assumptions 2023-01-02T23:48:50.298Z

Mental acceptance and reflection 2022-12-22T14:32:15.589Z

Tradeoffs in complexity, abstraction, and generality 2022-12-12T15:55:19.064Z

Biases are engines of cognition 2022-11-30T16:47:58.318Z

Methodological Therapy: An Agenda For Tackling Research Bottlenecks 2022-09-22T18:41:03.346Z

An extended rocket alignment analogy 2022-08-13T18:22:03.687Z

AI Alignment YouTube Playlists 2022-05-09T21:33:54.574Z

Comment by remember on Full Transcript: Eliezer Yudkowsky on the Bankless podcast · 2023-05-11T10:48:57.488Z · LW · GW

Thank you so much for doing this! Andrea and I both missed this when you first posted it, I'm really sorry I missed your response then. But I've updated it now! 

Comment by remember on Podcast Transcript: Daniela and Dario Amodei on Anthropic · 2023-03-07T23:21:53.587Z · LW · GW

Yes, good call! Added it.

Comment by remember on Full Transcript: Eliezer Yudkowsky on the Bankless podcast · 2023-02-23T23:20:21.517Z · LW · GW

thanks, fixed!!!

Comment by remember on Bankless Podcast: 159 - We’re All Gonna Die with Eliezer Yudkowsky · 2023-02-23T12:37:38.121Z · LW · GW

I just posted a full transcript on LW here!

Comment by remember on Bankless Podcast: 159 - We’re All Gonna Die with Eliezer Yudkowsky · 2023-02-23T12:36:42.955Z · LW · GW

Since there was no full transcript of the podcast, I just made one.  You can find it here.

Comment by remember on Don't accelerate problems you're trying to solve · 2023-02-22T20:10:40.758Z · LW · GW

I think that Anthropic's work also accelerates AI arrival, but it is much easier for it to come out ahead on a cost-benefit: they have significantly smaller effects on acceleration, and a more credible case that they will be safer than alternative AI developers. I have significant unease about this kind of plan, partly for the kinds of reasons you list and also a broader set of moral intuitions. As a result it's not something I would do personally.

From the outside perspective of someone quite new to the AI safety field and with no contact with the Bay Area scene, the reasoning behind this plan is completely illegible to me. What is only visible instead is that they’re working ChatGPT-like systems and capabilities, as well as some empirical work on evaluations and interpretability.The only system more powerful than ChatGPT I’ve seen so far is the unnamed one behind Bing, and I’ve personally heard rumours that both Anthropic and OpenAI are already working on systems beyond ChatGPT/GPT-3.5 level.

Comment by remember on Elicit: Language Models as Research Assistants · 2022-11-30T22:05:13.171Z · LW · GW

We'd love to get feedback on how to make Elicit more useful for LW and to get thoughts on our plans more generally.

A lot of alignment is on lesswrong and alignmentforum, and as far as I can tell elicit doesn't support those. I could be missing something, but if they aren't supported it would be great to have them in Elicit! I use elicit from time to time when I'm doing background research, and it definitely feels far more useful for general ML/capabilities stuff than alignment (to the point I kinda stopped trying for alignment after a few searches turned up nothing).