khafra

Karma: 3,790

khafra 29 Aug 2025 6:56 UTC
2 points
0
on: Zetetic explanation
There’s an article type called “You Could Have Invented” that I became aware of on reading Gwern’s You Could Have Invented Transformers.
This type dates back to at least 2012. I believe they’re usually good zetetic explanations.

khafra 29 Aug 2025 5:43 UTC
1 point
−1
in reply to: dawnstrata’s comment on: Underdog bias rules everything around me
In a stereotypical old-west gunfight, one fighter is more experienced and has a strong reputation; the other fighter is the underdog and considered likely to lose. But who’s the underdog of a grenade fight inside a bank vault? Both sides are overwhelmingly likely to lose.
At least one side of many political battles believe they’re in a grenade fight, where there’s little or nothing they can do to prevent the other side from destroying a lot of value. and could reasonably feel like an underdog even if they have a full bandolier of grenades and the other side has only one or two.

khafra 18 Jul 2025 7:42 UTC
2 points
0
in reply to: TAG’s comment on: A Simple Explanation of AGI Risk
I don’t think “perfect” is a good descriptor for the missing solution. The solutions we have lack (at least) two crucial features:
1. A way to get an AI to prioritize the intended goals, with high enough fidelity to work when AI is no longer extremely corrigible, as today’s AIs are (because they’re not capable enough to circumvent human methods of control).
2. A way that works far enough outside of the training set. E.g., when AI is substantially in charge of logistics, research and development, security, etc.; and is doing those things in novel ways.

khafra 28 May 2025 6:22 UTC
3 points
1
on: Colonialism in space: Does a collection of minds have exactly two attractors?
Robin Hanson’s model of quiet vs loud aliens seems fundamentally the same as this question, to me.

khafra 28 May 2025 5:28 UTC
6 points
2
in reply to: Rauno Arike’s comment on: It’s hard to make scheming evals look realistic for LLMs
Linear probes give better results than text output for quantitative predictions in economics. They’d likely give a better calibrated probability here, too.

khafra 21 May 2025 8:03 UTC
3 points
0
in reply to: dschwarz’s comment on: Thomas Kwa’s Shortform
I, too, would like to know how long it will be until my job is replaced by AI; and what fields, among those I could reasonably pivot to, will last the longest.

khafra 20 May 2025 9:00 UTC
2 points
1
in reply to: BryceStansfield’s comment on: One Year in DC
I think it’s especially true for the type of human that likes Lesswrong. Using Scott’s distinction between Metis and Techne, we are drawn to Techne. When a techne-leaning person does a deep dive into metis, that can generate a lot of value.

More speculatively, I feel like often—as in the case of lobbying for good government policy—there isn’t a straightforward way to capture any of the created value; so it is under-incentivized.

khafra 22 Apr 2025 5:06 UTC
1 point
0
in reply to: Viliam’s comment on: Pablo’s Shortform
Well, that was an interesting top-down processing error.

khafra 21 Apr 2025 11:39 UTC
0 points
0
in reply to: Viliam’s comment on: Pablo’s Shortform
Note that Alexander Kruel still blogs regularly on axisofordinary.blogspot.com, and from his Facebook account; he just doesn’t say anything directly about rationalists. He mostly lists recent developments in AI, science, tech, and the Ukraine war.

khafra 15 Apr 2025 6:33 UTC
4 points
0
on: Unbendable Arm as Test Case for Religious Belief
I’ve done some Aikido and related arts, and the unbending arm demo worked on me (IIRC, it was decades ago). But learning the biomechanics also worked. More advanced, related skills, like relaxing while maintaining a strongly upright stance, also worked best by starting out with some visualizations (like a string pulling up from the top of my head, and a weight pulling down from my sacrum).

But having a physics-based model of what I was trying to do, and why it worked, was essential for me to really solidify these skills—and incorrect explanations, which I sometimes got at first, did not help me. Could just be more headology, though—other students seemed to be able to do well based off the visualizations and practice.

https://www.lesswrong.com/posts/rZX4WuufAPbN6wQTv/no-really-i-ve-deceived-myself seems relevant.

khafra 10 Apr 2025 10:25 UTC
2 points
0
in reply to: Noosphere89’s comment on: LLM AGI will have memory, and memory changes alignment
Good timing—the day after you posted this, a round of new Tom & Jerry cartoons swept through twitter, fueled by transformer models which included in their layers MLPs that can learn at test time. Github repo here: https://github.com/test-time-training (The videos are more eye-catching, but they’ve also done text models).

khafra 12 Mar 2025 6:54 UTC
4 points
0
in reply to: RobinHanson’s comment on: Detached Lever Fallacy
It may be time to revisit this question. With Owain Evans et. al. discovering a generalized evil vector in LLMs, and older work like [Pretraining Language Models with Human Preferences](https://www.lesswrong.com/posts/8F4dXYriqbsom46x5/pretraining-language-models-with-human-preferences) that could use a follow-up, AI in the current paradigm seems ripe for some experimentation with parenting practices in pre-training—perhaps something like affect markers for the text that goes in, or pretraining on children’s literature before going on to the more technically and morally complex text?
I haven’t run any experiments of my own, but this doesn’t seem obviously stupid to me.

khafra 11 Feb 2025 15:21 UTC
4 points
0
in reply to: Shankar Sivarajan’s comment on: Wired on: “DOGE personnel with admin access to Federal Payment System”
When there’s little incentive against classifying harmless documents, and immense cost to making a mistake in the other direction, I’d expect overclassification to be rampant in these bureaucracies.
Your analysis of the default incentives is correct. However, if there is any institution that has noticed the mounds of skulls, it is the DoD. Overclassification, and classification for inappropriate reasons (explicitly enumerated in written guidance: avoiding embarrassment, covering up wrongdoing) is not allowed, and the DoD carries out audits of classified data to identify and correct overclassification.

It’s possible they’re not doing enough to fight against the natural incentive gradient toward overclassification, but they’re trying hard enough that I wouldn’t expect positive EV from disregarding all the rules.

khafra 6 Feb 2025 11:02 UTC
28 points
18
in reply to: robo’s comment on: Wired on: “DOGE personnel with admin access to Federal Payment System”
As someone who has been allowed access into various private and government systems as a consultant, I think the near mode view for classified government systems is different for a reason.

E.g., data is classified as Confidential when its release could cause damage to national security. It’s Secret if it could cause serious damage to national security, and it’s Top Secret if it could cause exceptionally grave damage to national security.
People lose their jobs for accidentally putting a classified document onto the wrong system, even if it’s still owned by the government and protected (but, protected at an insufficient level for the document). People go to jail for putting classified data onto the wrong system on purpose, even if they didn’t intend to, say, sell it to the Chinese government.

Bringing in personnel who haven’t had the standard single-scope background investigation and been granted a clearance, and a new set of computers which has not gone through any accreditation and authorization process, and giving unrestricted write and read access to classified data is technically something the president could allow. But it’s a completely unprecedented level of risk to assume; and AFAICT the president has not actually written any authorizations for doing this.

There is, actually, a Government Accounting Office which does audits; they have identified billions in fraud, waste, and abuse, identified the perpetrators for punishment, and remediated the programs at fault. They have done it without unprecedented breaches in national security, or denying lawful, non-fraudulent payments from the US Treasury.
(Also, outside of my personal area of expertise, I believe denying lawful, non-fraudulent payments from the US Treasury is crossing a really big Chesterton’s Fence. GPT-4o estimated a $1T-$5T impact from treasury bond yield spread, forex USD reserves, CDS spreads on US foreign debt, loss of seignorage in global trade, depending on how rare and targeted the payment denial is).

khafra 3 Feb 2025 6:38 UTC
11 points
0
in reply to: Friendly Monkey’s comment on: Thread for Sense-Making on Recent Murders and How to Sanely Respond
The quoted paragraph is a reference to a CS Lewis essay about living under the threat of global thermonuclear war. The euphony and symmetry with the original quote is damaged by making it slightly more accurate by using that phrase instead of “if we are going to be destroyed by Zizianism.”

khafra 27 Jan 2025 12:30 UTC
4 points
0
on: Kessler’s Second Syndrome
This is the most optimistic believable scenario I’ve seen in quite a while!

khafra 13 Jan 2025 10:26 UTC
2 points
−2
on: Alignment Implications of LLM Successes: a Debate in One Act
And yet it behaves remarkably sensibly. Train a one-layer transformer on 80% of possible addition-mod-59 problems, and it learns one of two modular addition algorithms, which perform correctly on the remaining validation set. It’s not a priori obvious that it would work that way! There are $59^{0.2 \cdot 59^{2}}$ other possible functions on $Z / 59 Z$ compatible with the training data.
Seems like Simplicia is missing the worrisome part—it’s not that the AI will learn a more complex algorithm which is still compatible with the training data; it’s that the simplest several algorithms compatible with the training data will kill all humans OOD.

khafra 30 Dec 2024 11:19 UTC
4 points
0
in reply to: Martin Randall’s comment on: Review: Planecrash
AFAICT, in the Highwayman example, if the would-be robber presents his ultimatum as “give me half your silk or I burn it all,” the merchant should burn it all, same as if the robber says “give me 1% of your silk or I burn it all.”
But a slightly more sophisticated highwayman might say “this is a dangerous stretch of desert, and there are many dangerous, desperate people in those dunes. I have some influence with most of the groups in the next 20 miles. For x% of your silk, I will make sure you are unmolested for that portion of your travel.”
Then the merchant actually has to assign a probabilities to a bunch of events, calculate Shapley values, and roll some dice for his mixed strategy.

khafra 17 Dec 2024 6:33 UTC
7 points
2
on: Communications in Hard Mode (My new job at MIRI)
Tangentially to Tanagrabeast’s “least you can do” suggestion, as a case report: I came out to my family as an AI xrisk worrier over a decade ago, when one could still do so in a fairly lighthearted way. They didn’t immediately start donating to MIRI and calling their senators to request an AI safety manhattan project, but they did agree with the arguments I presented, and check up with me, on occasion, about how the timelines and probabilities are looking.
I have had two new employers since then, and a few groups of friends; and with each, when the conversation turns to AI (as it often does, over the last half-decade), I mention my belief that it’s likely going to kill us all, and expand on Instrumental Convergence, RAAP, and/or “x-risk, from Erewhon, to IJ Good, to the Extropians,” depending on which aspect people seem interested in. I’ve been surprised by the utter lack of dismissal and mockery, so far!

khafra 4 Dec 2024 12:58 UTC
5 points
0
in reply to: Screwtape’s comment on: Mob and Bailey
See also Steven Kaas’ aphorisms on twitter:

> First Commandment of the Church of Tautology: Live next to thy neighbor
And
> “Whatever will be will be” is only the first secret of the tautomancers.