KatWoods

• KatWoodsMar 25, 2025, 9:14 PM

  5 points

  0

  on: A Bear Case: My Pre­dic­tions Re­gard­ing AI Progress

  Deep Research was this for me, at first. Some of its summaries were just pleasant to read, they felt so information-dense and intelligent! Not like typical AI slop at all! But then it turned out most of it was just AI slop underneath anyway,

  Can you elaborate on what you mean by this? Do you mean it’s hallucinating a ton underneath? Or that the writing is somehow bad? Or something else?

• KatWoodsMar 18, 2025, 8:56 PM

  10 points

  0

  in reply to: katriel’s comment on: Steel­man soli­taire: how to take play­ing devil’s ad­vo­cate to the next level

  I provided one here!

  Totally agree about LLMs. I’ve recently been finding giving o3 Deep Research this prompt to be super helpful:

  “X=[thing I want to research]

  Do a deep dive into X. Tell me the steelman arguments in favor of X.

  Then tell me the steelman counter-arguments to X.

  Then tell me the steelman counter-counter-arguments to X.

  Then tell me the steelman counter-counter-counter-arguments to X

  Make sure to link to primary sources and the full thing that happened, to avoid things being quoted out of context”

  It’s been particularly helpful for investigating anything political.

• KatWoodsMar 13, 2025, 5:48 PM

  4 points

  2

  on: Re­view of Soft Take­off Can Still Lead to DSA

  To be fair, I think you could make the case that the technological advancement of the Western European powers led to almost a DSA.

  England had the biggest empire in the history of the world (population wise). The countries which were technologically ahead of others did kinda stomp on the rest of the world

  It wasn’t literally one world power, but it was a sizeable fraction that way, especially if you consider European culture as a unit instead of just the UK.

• KatWoodsFeb 24, 2025, 2:35 PM

  6 points

  0

  in reply to: GeneSmith’s comment on: How to Make Superbabies

  Ah well. At least you can take credit for the name then.

• KatWoodsFeb 24, 2025, 12:56 PM

  0 points

  −1

  on: How to Make Superbabies

  Very not important question: is Gene Smith your actual name or a pseudonymn?

  Either way, it’s the perfect name for the author of this post.

  Hats off to you gene smith.

  

• KatWoodsJan 20, 2025, 3:36 PM

  8 points

  0

  on: Who is mar­ket­ing AI al­ign­ment?

  Robert Miles has a great channel spreading AI safety content. There’s also Rational Animations and Siliconversations and In a Nutshell.

  I think FLI does a lot of work in outreach + academia.

  Connor Leahy does a lot of outreach and he’s one of my favorite AI safety advocates.

  Nonlinear doesn’t do outreach to academia in particular, but we do target people working in ML, which is a lot of academia.

  AI Safety Memes does a lot of outreach but is focused on broad appeal, definitely not specifically academia.

  Pause AI and Stop AI both work on outreach to the broader public.

  CAIS does great outreach work. Not sure if any academia specific stuff.

  Are you on the Nonlinear Network? You can sort by the category of “content/​media creation” to find a bunch of AI safety orgs limited by funding who are working on advocacy. Quick scan of the section shows 36.

  Might be able to find more possibilities on the AI safety map too https://​​map.aisafety.world

• KatWoodsJan 3, 2025, 4:25 PM

  3 points

  0

  on: Hire (or be­come) a Think­ing As­sis­tant /​ Body Double

  I saw somebody using one of the latest Google models for this. I forget the one, but it’s the one that can see your screen as you type. It can be used to keep you focused.

  (Haven’t researched it yet, so might not work very well)

o3 is not be­ing re­leased to the pub­lic. First they are only giv­ing ac­cess to ex­ter­nal safety testers. You can ap­ply to get early ac­cess to do safety testing

• KatWoodsDec 20, 2024, 5:05 PM

  17 points

  14

  on: “Align­ment Fak­ing” frame is some­what fake

  I see it called “goal guarding” in some papers. That seems like a pretty good term to use.

• KatWoodsDec 18, 2024, 1:57 PM

  4 points

  0

  on: Sur­vival with­out dignity

  I laughed out loud so many times reading this. Thank you for writing it.

• KatWoodsDec 17, 2024, 6:06 PM

  3 points

  0

  in reply to: ryan_greenblatt’s comment on: Would catch­ing your AIs try­ing to es­cape con­vince AI de­vel­op­ers to slow down or un­de­ploy?

  If I recall correctly, it was told that it had a goal, like optimizing traffic. Then, it was given information where it “discovered” that it was going to be turned off the next day.

  That seems like the sort of thing that would happen pretty often. Imagine the current AIs that have access to your computer, reading your emails, and seeing that you’re going to switch to a different AI or install “updates” (which is often deleting existing AI and replacing with a new one)

• KatWoodsDec 16, 2024, 3:30 PM

  5 points

  0

  in reply to: ryan_greenblatt’s comment on: Would catch­ing your AIs try­ing to es­cape con­vince AI de­vel­op­ers to slow down or un­de­ploy?

  Can you elaborate on why that’s relevant?

• KatWoodsDec 15, 2024, 8:26 PM

  7 points

  −4

  in reply to: Noosphere89’s comment on: Would catch­ing your AIs try­ing to es­cape con­vince AI de­vel­op­ers to slow down or un­de­ploy?

  How does it not show that it would try to escape if it could?

  It tried to escape about 5% of the time when it was told to pursue a goal “at all costs”. Gemini still tried to escape 1% of the time, even without any behavioral nudging.

  1% might not sound like a lot, but when it’s 1% of the millions of instantiations it’s run on every day, that ends up being a lot of times a week.

  Also, a lot of people will tell their chatbots to pursue their goals at all costs over the span of a week or month. This doesn’t seem like a very unlikely prompt

  

• KatWoodsDec 15, 2024, 3:31 PM

  4 points

  0

  on: Would catch­ing your AIs try­ing to es­cape con­vince AI de­vel­op­ers to slow down or un­de­ploy?

  This is published before Apollo’s evals report showing AIs trying to escape. Is that just an amazing coincidence, or did you see the paper’s results before they were published?

• KatWoodsSep 9, 2024, 4:45 PM

  2 points

  0

  in reply to: Anon’s comment on: Med­i­ta­tion course claims 65% en­light­en­ment rate: my review

  Great review! Thanks for sharing.

  I’m curious—even if you didn’t achieve fundamental well-being, do you feel like there were any intermediate improvements in your general well-being?

  Also, did you end up continuing to try the extended course which they offered?

  I remember they offered that for me since I hadn’t attained fundamental well-being. I’d totally been meaning to do it, but never followed through, showing that the class format really was quite helpful.

• KatWoodsFeb 13, 2024, 3:54 AM

  4 points

  1

  on: Manag­ing risks while try­ing to do good

  This may be true in other communities, but I think if you’re more status motivated in AI safety and EA you are more likely to be concerned about potential downside risks. Especially post SBF.

  Instead of trying to maximize the good, I see a lot of people trying to minimize the chance that things go poorly in a way that could look bad for them.

  You are generally given more respect and funding and social standing if you are very concerned about downside risks and reputation hazards.

  If anything, the more status-oriented you are in EA, the more likely you are to care about downside risks because of the Copenhagen theory of ethics.

• KatWoodsDec 21, 2023, 6:20 PM

  1 point

  −4

  in reply to: habryka’s comment on: Non­lin­ear’s Ev­i­dence: De­bunk­ing False and Mislead­ing Claims

  This text was sent on November 4th, almost a month before she arrived to come travel with us (not to work for us).

  Emerson is not referring to her saying she would make $3000 a month if she worked full-time on her Amazon business. The context of the conversation is she’s trying to figure out whether she should spend an additional $90 to visit her family before joining us, and Emerson is replying saying “If you make $3k a month [$90] is very little money”, so he’s telling her she should spend the $90 to spend time with family. Directly going against the “keeping her isolated from family” story and also supporting (albeit not conclusively proving) that Alice had told him she made $3k per month with her business.

• KatWoodsDec 21, 2023, 3:43 PM

  0 points

  2

  in reply to: Ben Pace’s comment on: Non­lin­ear’s Ev­i­dence: De­bunk­ing False and Mislead­ing Claims

  I’m currently focusing on 2-3 of the claims in their response that most contradict my post, investigating them further, and intend to publish the results of that.

  I hope that while you’re investigating this, you talk to us and ask us for any evidence we have. We’re more than happy to share relevant evidence and are willing to set reasonable deadlines for how long it’ll take for us to send it to you.

  We also don’t want to waste more people’s time on going back and forth publicly about the evidence when you can easily check with us first before publishing.

  I also recommend you talk to us and see our evidence before you write the post. If you’ve already written the post, it’s hard to update afterward when you get more information. And it’s hard to write an accurate post before you’ve seen all the relevant information.

  We did not share all of the relevant evidence because it was already hundreds of pages long and we tried to prioritize. We have more evidence that might be relevant to your post.

  I am trying to avoid writing my bottom line, and reduce any (further) friction to me changing my mind on this subject, which is a decent chunk of why I’m not spending time arguing in the comments right now (I expect that to give me a pretty strong “digging in my heels” incentive).

  I think this is smart and appreciate it.

• KatWoodsDec 20, 2023, 7:51 PM

  8 points

  5

  in reply to: Viliam’s comment on: Effec­tive Asper­sions: How the Non­lin­ear In­ves­ti­ga­tion Went Wrong

  We said this in our post about the vegan food:

  “We chose this example not because it’s the most important (although it certainly paints us in a very negative and misleading light) but simply because it was the fastest claim to explain where we had extremely clear evidence without having to add a lot of context, explanation, find more evidence, etc.

  We have job contracts, interview recordings, receipts, chat histories, and more, which we are working full-time on preparing.

  This claim was a few sentences in Ben’s article but took us hours to refute because we had to track down all of the conversations, make them readable, add context, anonymize people, check our facts, and write up an explanation that was rigorous and clear. Ben’s article is over 10,000 words and we’re working as fast as we can to respond to every point he made.

  Again, we are not asking for the community to believe us unconditionally. We want to show everybody all of the evidence and also take responsibility for the mistakes we made.”

  As for the “isolated” claim, we showed that this did not happen. Alice lived/​worked apart from us for 50% of the time. Chloe’s boyfriend was invited to travel with us 40% of the time. We encouraged them to have regular calls with friends and family when they weren’t visiting. We have the invite policy where it says they’re encouraged to invite friends and family (and they followed up on this, like with Chloe’s boyfriend).

• KatWoodsDec 20, 2023, 4:51 PM

  −2 points

  −6

  in reply to: habryka’s comment on: Non­lin­ear’s Ev­i­dence: De­bunk­ing False and Mislead­ing Claims

  I have noticed that you are asking yourself “can I believe this?” when assessing Alice and Chloe’s claims and “must I believe this?” when assessing our claims. Please try to apply similar evidentiary standards to all claims.

  she would be provided benefits adding up to the remainder (which wasn’t specified in the contract, but was explained during the relevant interview which Kat posted the transcript off).

  Where does it say that in the transcript? I’m reading it again and I just don’t see where we say anything even like that.

  

  And it would be really weird to say that too. I’ve never heard of somebody offering room & board + a stipend who’s said that it has to add up to a certain amount, otherwise you pay the difference (but you don’t pay the difference if the costs go over).

  Kat’s job interview transcript seems to suggest the total compensation would be $70k of benefits plus $1k/​mo of stipend for a total of $82k

  This isn’t what was said. It was (paraphrasing to get rid of verbal tiks): “So what we’re thinking is basically, like having a package where it’s about equivalent of being paid like 70k a year in terms of:

  • Housing

  • Food

  • Travel

  • Random fun stuff

  • $1k a month for things not covered by that.

  Saying “and then on top of that” is just another way for saying “and”. It was a verbal conversation, not a legal contract.

  The contract states clearly that there wasn’t any “and then we’ll pay the difference if it’s below $70k” clause.
  
  She clearly communicated that she understood the compensation package before she arrived.