It is easier to ask than to answer.
That’s my whole point.
It is much cheaper to ask questions than answer them so beware of situations where it is implied that asking and answering are equal.
Let's say there is a maths game. I get a minute to ask questions. You get a minute to answer them. If you answer them all correctly, you win, if not, I do. Who will win?
Preregister your answer.
Okay, let's try. These questions took me roughly a minute to come up with.
What's 56,789 * 45,387?
What's the integral from -6 to 5π of sin(x cos^2(x))/tan(x^9) dx?
What's the prime factorisation of 91435293173907507525437560876902107167279548147799415693153?
Good luck. If I understand correctly, that last one's gonna take you at least an hour1 (or however long it takes to threaten...
I agree with your assertion that pure factual questions are cheaper and easier than (correct) answers. I fully disagree with the premise that they're currently "too cheap".
I see many situations where questions and answers are treated as symmetric.
I see almost none. I see MANY situations where both are cheap, but even then answers are more useful and valued. I see others where finding the right questions is valued, but answering is even more so. And plenty where the answer isn't available, but the thinking about how to get closer to ...
I've been on the lookout for new jobs recently and one thing I have noticed is that the market seems flooded with ads for AI-related jobs. What I mean is not work on building models (or aligning them, alas), but rather, work on building applications using generative AI or other advances to make new software products. My impression of this is that first, there's probably something of a bubble, because I doubt many of these ideas can deliver on their promises, especially as they rely so heavily on still pretty unreliable LLMs and such. And second, that while the jobs are well paid and sound fun, I'm not sure how I feel about them. These jobs all essentially aim at automating away other jobs, one way or another....
It's definitely overhyped. I hesitate to call it a bubble - it's more like the normal software business model with a new cover. Tons of projects and startups with pretty tenuous business models and improbable grand visions, most of which will peter out after a few years. But that has been going on for decades, and will likely continue until true AI makes it all irrelevant.
Most of these jobs are less interesting, and less impactful than they claim. Which makes the ethical considerations far less important. My advice is to focus on th...
I discovered the Netherlands actually has a good dating app that doesn't exist outside of it... I'm rather baffled. I have no idea how they started. I've messaged them asking if they will localize and expand and they thanked me for the compliment so... Dunno?
It's called Paiq and has a ton of features I've never seen before, like speed dating, picture hiding by default, quizzes you make for people that they can try to pass to get a match with you, photography contacts that involve taking pictures of stuff around and getting matched on that, and a few other things... It's just this grab bag of every way to match people that is not your picture or a blurb. It's really good!
Co-Authors: @Rocket, @Ryan Kidd, @LauraVaughan, @McKennaFitzgerald, @Christian Smith, @Juan Gil, @Henry Sleight
The ML Alignment & Theory Scholars program (MATS) is an education and research mentorship program for researchers entering the field of AI safety. This winter, we held the fifth iteration of the MATS program, in which 63 scholars received mentorship from 20 research mentors. In this post, we motivate and explain the elements of the program, evaluate our impact, and identify areas for improving future programs.
Key details about the Winter Program:
I'm noticing there are still many interp mentors for the current round of MATS -- was the "fewer mech interp mentors" change implemented for this cohort, or will that start in Winter or later?
I am trying to gather a list of answers/quotes from public figures to the following questions:
I am writing them down here if you want to look/help: https://docs.google.com/spreadsheets/d/1HH1cpD48BqNUA1TYB2KYamJwxluwiAEG24wGM2yoLJw/edit?usp=sharing
Thank you, this is the kind of thing I was hoping to find.
The first speculated on why you’re still single. We failed to settle the issue. A lot of you were indeed still single. So the debate continues.
The second gave more potential reasons, starting with the suspicion that you are not even trying, and also many ways you are likely trying wrong.
The definition of insanity is trying the same thing over again expecting different results. Another definition of insanity is dating in 2024. Can’t quit now.
A guide to taking the perfect dating app photo. This area of your life is important, so if you intend to take dating apps seriously then you should take photo optimization seriously, and of course you can then also use the photos for other things.
I love the...
Manifold Love: pro-tip: if a woman measures her hand against yours, this is almost always flirtation.
Totally did not know this. Is this true? [10% react x 2]
A little taken aback by this response. It's not just flirting, it's outright romantic. Asking this is like asking if a woman resting their head on a mans chest and purring is "flirting". I didn't realize this was a common experience for guys not in a relationship with the particular woman.
epistemic/ontological status: almost certainly all of the following -
To avoid confusion: this post and my reply to it were also on a past version of this post; that version lacked any investigation of dominance criterion desiderata for lottery-lotteries.
The curious tale of how I mistook my dyslexia for stupidity - and talked, sang, and drew my way out of it.
Sometimes I tell people I’m dyslexic and they don’t believe me. I love to read, I can mostly write without error, and I’m fluent in more than one language.
Also, I don’t actually technically know if I’m dyslectic cause I was never diagnosed. Instead I thought I was pretty dumb but if I worked really hard no one would notice. Later I felt inordinately angry about why anyone could possibly care about the exact order of letters when the gist is perfectly clear even if if if I right liike tis.
I mean, clear to me anyway.
I was 25 before it dawned on me that all the tricks...
Yeah, I myself subvocalize absolutely everything and I am still horrified when I sometimes try any "fast" reading techniques - those drain all of the enjoyment our of reading for me, as if instead of characters in a story I would imagine them as p-zombies.
I speed-read fiction, too. When I do, though, I'll stop for a bit whenever something or someone new is being described, to give myself a moment to picture it in a way that my mind can bring up again as set dressing.
TLDR; I demonstrate the use of refusal vector ablation on Llama 3 70B to create a bad agent that can attempt malicious tasks such as trying to persuade and pay me to assassinate another individual. I introduce some early work on a benchmark for Safe Agents which comprises two small datasets, one benign, one bad. In general, Llama 3 70B is a competent agent with appropriate scaffolding, and Llama 3 8B also has decent performance.
In this post, I use insights from mechanistic interpretability to remove safety guardrails from the latest Llama 3 model. I then use a custom scaffolding for tool use and agentic planning to create a “bad” agent that can perform many unethical tasks. Examples include tasking the AI with persuading me to end the life of...
No particular disagreement that your marginal contribution is low and that this has the potential to be useful for durable alignment. Like I said, I'm thinking in terms of not burning days with what one doesn't say.