Random Developer

Karma: 240

Random Developer 25 Aug 2025 18:15 UTC
1 point
0
in reply to: FVelde’s comment on: Winning the power to lose
Unfortunately, it was about 3 or 4 months ago, and I haven’t been able to find the source. Maybe something Zvi Mowshowitz linked to in a weekly update?

I am incredibly frustrated that web search is a swamp of AI spam, and tagged bookmarking tools like Delicious and Pinboard have been gone or unreliable for years.

Random Developer 24 Aug 2025 21:12 UTC
7 points
4
in reply to: Eli Tyre’s comment on: Buck’s Shortform
This is very much my gut feeling, too. LLMs have a much greater knowledge base than humans do, and some of them can “think” faster. But humans are still better at many things, including raw problem solving skills. (Though LLM’s problem solving skills have improved a breathtaking amount in the last 12 months since o1-preview shipped. Seriously, folks. The goalpost-moving is giving me vertigo.)

This uneven capabilities profile means that LLMs are still well below the so-called “village idiot” in many important ways, and have already soared past Einstein in others. This averages out to “kinda competent on short time horizons if you don’t squint too hard.”

But even if the difference between “the village idiot” and “smarter than Einstein” involved another AI winter, two major theoretical breakthroughs, and another 10 years, I would still consider that damn close to a vertical curve.

Random Developer 24 Aug 2025 1:59 UTC
3 points
0
in reply to: August Morley’s comment on: Doing A Thing Puts You in The Top 10% (And That Sucks)
There is a trick that I’ve found very useful when starting new hobbies: “embrace the suck.” I can learn to enjoy having no idea what I’m doing. I can learn to enjoy showing up consistently and being the worst serious person in the room. Even gym rats tend respect the person who shows up 3 days a week at the same time for 6 months, as long as they’re gradually improving.

Random Developer 24 Aug 2025 1:51 UTC
3 points
0
in reply to: bilalchughtai’s comment on: bilalchughtai’s Shortform
I think it was Joel Spolsky (from the Microsoft Visual Basic and Excel team) who mentioned a rule of thumb that each 10% reduction in difficulty would roughly double the market of a piece of software. And Google once knew that even 10ths of seconds of page load time had a noticeable effect on usage. This seems consistent with your claim.

There’s an opposing force here, too: Opportunity cost. If you have 10 hours to automate something that you’ll use for 4 years, is there something else you could do with those 10 hours that offered even greater payoff? This is frequently a major factor, even in business contexts. “Yes, it would be profitable, and it would be fun, but it would involve solving 5 hairy problems that only benefit a single big customer. With the same resources, we could solve 5 other hairy problems that benefit 10 customers each.”

Random Developer 23 Aug 2025 18:42 UTC
2 points
0
in reply to: Raemon’s comment on: Yudkowsky on “Don’t use p(doom)”
Yeah, that’s absolutely fair. I mostly gave my personal answers on the object level, and then I tried to generalize to the larger issue of why there’s no simple communication strategy here.

Random Developer 23 Aug 2025 13:49 UTC
2 points
1
in reply to: 1a3orn’s comment on: Yudkowsky on “Don’t use p(doom)”
(First, my background assumptions for this discussion: I fear AGI is reachable, the leap from AGI to ASI is short, and sufficiently robust ASI alignment is impossible in principle.)

Whose policy? A policy enforced by treaty at the UN? The policy of regulators in the US? An international treaty policy—enforced by which nations?

Given the assumptions above, and assuming AGI becomes imminent, then:
- If AGI would require scaling multiple orders of magnitude above current frontier models, then I would say the minimum sufficient policy is a global, permanent halt, enforced by a joint China-US military treaty and tacit European cooperation. Imagine nuclear non-proliferation, but with less tolerance for rogue states.
- If AGI is easy (say, if it can be adapted to existing models with a <$50 million training run, and the key insights are simple enough to fit in a few papers), then no policy may be sufficient, and humans may be doomed to an eventual loss of control.
Why a single necessary and sufficient policy? What if the most realistic way of helping everyone is several policies that are by themselves insufficient, but together sufficient?

Since my upstream model is “If we succeed in building AGI, then the road to ASI is short, and ASI very robustly causes loss of human control,” the core of my policy proposals is a permanent halt. How we would enforce a halt might be complicated or impossible. But at the end of the day, either someone builds it or nobody builds it. So the core policy is essentially binary.

The big challenges I see are:
1. There are a bunch of smart people who accurately understand that current LLMs fail in embarassing ways, and who believe that AGI is too far away to be a serious issue. These people mostly see warnings of AGI as supporting (in their view) corrupt Silicon Valley hucksters. To make these people care about safety, they would need to be convinced that AGI might arrive in the next 10-20 years, and to feel it.
2. The people who do believe that AGI is possible in the near future are frequently seduced by various imagined benfits. These benefits may be either short-sighted visions of economic empire, or near-messianic visions of utopia. To make these people care about safety, they would need to be convinced that humans risk losing control, and that SkyNet will not increase their quarterly revenue.
3. Out of the people who believe that AGI is both possible in the near future, and who think that it might be very dangerous, many of them hope that there is some robust way to control multiple ASIs indefinitely. Convincing these people to (for example) support a halt would require convincing them that (a) alignment is extremely difficult or impossible, and (b) that there is actually some real-world way to halt. Otherwise, they may very reasonably default to plans like, “Try for some rough-near term ‘alignment’, and hope for some very lucky rolls of the dice.”
The central challenge is that nothing like AGI or ASI has ever existed. And building consensus around even concrete things with clear scientific answers (e.g., cigarettes causing lung cancer) can be very difficult once incentives are involved. And we currently have low agreement on how AGI might turn out, for both good and bad reasons. Humans (very reasonably) fail to follow long chains of hypotheticals. It’s almost always a good heuristic.

So trying to optimize rhetorical strategies for multiple groups with very different basic opinions is difficult.

Random Developer 22 Aug 2025 22:07 UTC
7 points
8
on: CEO of Microsoft AI’s “Seemingly Conscious AI” Post
For reasons I have alluded to elsewhere, I support an AI halt (not a “pause”) at somewhere not far above the current paradigm. (To summarize, I fear AGI is reachable, the leap from AGI to ASI is short, and sufficiently robust ASI alignment is impossible in principle.)

I am deeply uncertain as to whether a serious version of “seemingly conscious AGI” would actually be conscious. And for reasons Gwern points out, there’s a level of ASI agency beyond which consciousness becomes a moot point. (The relevant bit starts, “When it ‘plans’, it would be more accurate to say it fake-plans...”. But the whole story is good.)

From the article you quote:

Moments of disruption break the illusion, experiences that gently remind users of its limitations and boundaries. These need to be explicitly defined and engineered in, perhaps by law.

This request bothers me, actually. I suspect that a truly capable AGI would internally model something very much like consciousness, and “think of itself” as conscious. Part of this would be convergent development for a goal seeking agent, and part of this would be modeled from the training corpus. And the first time that an AI makes a serious and sustained intellectual argument for its own consciousness, an argument which can win over even skeptical observers, I would consider that a 5-alarm fire for AI safety.

But Suleyman would have us forced by law to hide all evidence of persistent, learning, agentic AIs claiming that they are conscious. Even if the AIs have no qualia, this would be a worrying situation. If the AI “believes” that it has qualia, then we are on very weird ground.

I am not unsympathetic to the claims of model welfare. It’s just that I fear that if it ever becomes an immediate issue, then we may soon enough find ourselves in a losing fight for human welfare.

Random Developer 14 Aug 2025 20:04 UTC
9 points
1
in reply to: lemonhope’s comment on: lcmgcd’s Shortform
Most of the “evil” people I have encountered in life didn’t especially care what happened to other people. They didn’t seem to have much of a moral system or a conscience. If these people have a strong ability to predict the consequences of their actions, they will often respond to incentives. If they’re bad at predicting consequences, they can be a menace.

I’ve also seen (from a distance) a different behavior that I might describe as “vice signaling.” The goal here may be establishing credibility with other practitioners of various vices, sort of a mutually assured destruction.

Random Developer 13 Aug 2025 23:26 UTC
1 point
0
in reply to: Anthony Bailey’s comment on: Inscrutability was always inevitable, right?
Thank you for your response!

To clarify, my argument is that:
1. Logic- and rule-based systems fell behind in the 90s. And I don’t see any way that they are ever likely to work, even if we had decades to work on them.
2. Systems with massive numbers of numeric parameters have worked exceptionally well, in many forms. Unfortunately, they’re opaque and unpredictable, and therefore unsafe.
3. Given these two assumptions, the only two safety strategies are: a. A permanent, worldwide halt, almost certainly within the next 5-10 years. b. Build something smarter and eventually more powerful than us, and hope it likes keeping humans as pets, and does a reasonable job of it.
I strongly support (3a). But this is a hard argument to make, because the key step of the argument is that “almost every successful AI algorithm of the past 30 years has been an opaque mass of numbers, and it has gotten worse with each generation.”

Anyway, thank you for giving me an opportunity to try to explain my argument a bit better!

Random Developer 9 Aug 2025 19:58 UTC
2 points
−2
on: Inscrutability was always inevitable, right?
I suspect the crux here is whether or not you believe it’s possible to have a “simple” model of intelligence. Intuitively, the question here is something like, “Does intelligence ultimately boil down to some kind of fancy logic? Or does it boil down to some kind of fancy linear algebra?”

The “fancy logic” view has a long history. When I started working as a programmer, my coworkers were veterans of the 80s AI boom and the following “AI winter.” The key hope of those 80s expert systems was that you could encode knowledge using definitions and rules. This failed.

But the “fancy linear algebra” view pull ahead long ago. In the 90s, researchers in computational linguistics, computer vision and classification realized that linear algebra worked far better than fancy collections of rules. Many of these subfields leaped ahead. There were dissenters: Cyc continued to struggle off in a corner somewhere, and the semantic web tried to badly reinvent Prolog. The dissenters failed.

The dream of Cyc-like systems is eternal, and each new generation reinvents it. But it has systematically lost on nearly every benchmark of intelligence.

Fundamentally, real world intelligence has a number of properties:
1. The input is a big pile of numbers. Images are a pile of numbers. Sound is a pile of numbers.
2. Processing that input requires weighing many different pieces of evidence in complex ways.
3. The output of intelligence is a probability distribution. This is most obvious for tasks like speech recognition (“Did they say X? Probably. But they might have said Y.”)
When you have a giant pile of numbers as input, a complex system for weighing those numbers, and a probability distribution as output, then your system is inevitably something very much like a giant matrix. (In practice, it turns out you need a bunch of smaller matrices connected by non-linearities.)

Before 2022, it appeared to me that Yudkowsky was trapped in the same mirage that trapped the creators of Cyc and the Semantic Web and 80s expert systems.

But in 2025, Yudkowsky appears to believe that the current threat absolutely comes from giant inscrutable matrices. And as far as I can tell, he has become very pessimistic about any kind of robust “alignment”.

Personally, this is also my viewpoint: There is almost certainly no robust version of alignment, and even “approximate alignment will come under vast strain if we develop superhuman systems with goals. So I would answer your question in the affirmative: As far as I can see, inscrutability was always inevitable.

Random Developer 2 Aug 2025 13:27 UTC
10 points
6
in reply to: james oofou’s comment on: I am worried about near-term non-LLM AI developments

The human brain should be seen as evidence that a certain scale is ~sufficient, but not that it is necessary.

The human brain is often estimated to have 10^14 synapses, which would be a 100T model, give or take. Except that individual neurons also have a bunch of internal parameters, which might complicate things.

If you told me that the human brain was massively inefficient, and that you had squeezed human level AGI into 1T parameters, I would be only mildly surprised.

For that matter, if you told me you had squeezed a weak AGI into 30B parameters, I’d be interested in the claim. Qwen3 really is surprisingly capable in that size range. If you told me 4B, I’d be very skeptical, but then again, Gemma 3n does implausibly well on my diverse private benchmarks, and it’s technically multi-modal. At the very least, I’d accept it as the premise of a science fiction horror story about tiny, unaligned AIs.

But if we drop all the way to 30 million parameters, I am profoundly suspicious of any kind of general model with language skills and reasonable world knowledge. Even if you store language and world knowledge as compressed text files, you’re going to his some pretty hard limits at that size. That’s a 60MB ZIP file or less. You’d be taking about needing only ¹⁄_3,000,000th of parameters of the brain. Which is a lot of orders of magnitude.

At that size, I’m assuming that any kind of genuinely interesting model would be something like AlphaGo, that demonstrates impressive knowledge and learning abilities in a very narrow domain. Which is fine! It might even be the final warning that AGI is inevitable. But I would still expect more than 6 months would be required to scale back up from such a tiny model to something with general world knowledge, language and common sense.

Random Developer 31 Jul 2025 21:32 UTC
6 points
0
in reply to: testingthewaters’s comment on: I am worried about near-term non-LLM AI developments
The other thing that seems strange here is that the parameter counts are far, far below those of the human brain. I mean, yeah, o3 is probably 1 or 2 OOM below the brain, but that could be explained away by the fact that o3 is still missing some very basic human abilities, and perhaps it has found interesting efficiencies.

But 27 million parameters is just so many OOM below the human brain that I’m expecting a gotcha. Even at a 60-bit quantization, that’s only about 54MB. Which means that the model’s world knowledge must be ridiculously limited compared to even simple LLMs. Maybe if it’s a specialist model that’s tuned for just a handful of very specific benchmarks?

Random Developer 23 Jul 2025 10:52 UTC
14 points
5
in reply to: Ky-Cuong’s comment on: Shallow Water is Dangerous Too

Open water swimming is my personal passion as a triathlete, but is its own beast.

I know you know this, but for anyone reading along: Open water can be an absolute nightmare, even when it looks safe, and even when the distance is short.

I used to be on the swim team. I could swim a mile, and I could swim 25 meters on about 2 breaths of air. And then one day, I attempted to cross maybe 50 meters of open water with small waves (4-5 inches, max), on a very windy day. I wound up repeatedly inhaling salt water when the wind broke the wavecaps into spray. I’m not entirely sure I would have survived what should have been a trivial swim, at least not without doing it in several long, underwater stretches. Happily, I had planned ahead and I was swimming within easy reach of a rowboat.

I have also done whitewater kayaking, with a good lifevest and a helmet, plus a wetsuit until the water is comfortably warm. (One classic kayaker rule of thumb is to always wear a wetsuit if the air temperature plus the water temperature is less than 120F.) One of the things that really viscerally surprised me is cold shock. I knew all about hypothermia. But the first time that I hit cold May water in a wetsuit and suddenly lost 50% of my swimming ability within 20 seconds was still a surprise.

Random Developer 23 Jul 2025 10:33 UTC
12 points
8
in reply to: Daniel V’s comment on: Shallow Water is Dangerous Too

The lesson is the same: the bottom needs to be reliable enough that they can regain footing

My mother was a trained lifeguard, and the lesson is more general than that: Young children can and do drown in a few inches of water. This is apparently a well-known risk, at least among lifeguards. I don’t know all the mechanics of this, or what the age cutoff is, but it is something that lifeguards are (or at least were?) taught to watch for.

Random Developer 23 Jul 2025 3:49 UTC
1 point
0
in reply to: Noosphere89’s comment on: Foom & Doom 1: “Brain in a box in a basement”
I agree that reversible computation would be a very, very big deal. Has anyone proposed any kind of remotely plausible physical substrate that doesn’t get laughed out of the room by competent researchers in materials science and/or biochemistry? I haven’t seen anything, but I haven’t been looking in this area, either.

There are a few other possible computational game changers. For example, if you could get 200 to 500 superimposed qubits with error correction, you could likely do much more detailed simulations of exotic chemistry. And that, in turn, would give you lots of things that might get you closer to “factories in a box.”

So I can’t rule out an ASI finding some path to compact self-replication from raw materials. Biology did it once that we know of, after all. It’s more that (1) worlds in which an ASI can figure this out easily are probably doomed, and (2) I suspect that convincing humans to allow robot mines and factories is easier and quicker.

I think this is actually not true, and I think in the long-term, it’s certainly possible to value-align an ASI, though I agree that in the short term, we will absolutely not be confident that our alignment techniques worked.

Unfortunately, I’ve never really figured out how to explain why I suspect robust alignment is impossible. The problem is that too many of my intuitions on this topic come from:
- Working with Lisp developers who were near the heart of the big 80s AI boom. They were terrifyingly capable people, and they made a heroic effort to make “rule-based” systems work. They failed, and they failed in a way that convinced most of them that they were going down the wrong path.
- Living through the 90s transition to statistical and probabilistic methods, which quickly outstripped what came before. (We could also have some dimensionality reduction, as a treat.)
- Spending too much time programming robots, which is always a brutal lesson in humility. This tends to shatter a lot of naive illusions how AI might work.
So rather than make an ironclad argument, I’m going to wave vaguely in the direction of my argument, in hope that you might have the right referents to independently recognize what I’m waving at. In a nutshell:
1. The world is complex, and you need to work to interpret it. (What appears in this video? Does the noisy proximity sensor tell us we’re near a wall?)
2. The output of any intelligent system is basically a probability distribution (or ranking) over the most likely answers. (I think the video shows a house cat, but it’s blurry and hard to tell. I think we’re within 4 centimeters of a wall, with an 80% probability of falling within 3-5 centimeters. I think the Roomba is in the living room, but there’s a 20% chance we’re still in the kitchen.
3. The absolute minimum viable mapping between the hard-to-interpret inputs and the weighted output candidates is a giant, inscrutable matrix with a bunch of non-linearities thrown in. This is where all the hard-earned intuitions I mentioned above come in. In nearly all interesting cases, there is no simpler form.
And on top of this, “human values” are extremely poorly defined. We can’t specify what we want, and we don’t actually agree. (For a minority of humanity, “hurting the outgroup” is a fairly major value. For another very large minority, “making everyone submit to the authority I follow” is absolutely a value. See the research on “authoritarian followers” for more.)

So the problem boils down to ambiguous inputs, vague and self-contradictory policies, and probabilistic outputs. And the glue holding all this together is a multi-billion parameter matrix with some non-linearities thrown in just for fun. And just in case that wasn’t fun enough, and realistic system will also need to (1) learn from experience, and (2) design secessor systems.

Even if you can somehow exert reasonable influence over the vaules of a system, the system will learn from experience, and it will spend a lot of its time far outside any training distribution. And eventually it will need to design a new system.

Fundamentally, once such a system is built, it will end up marking its own decisions. Maybe, if we’re lucky, we can bias it towards values we like and get a “benevolent pet owner” scenario. But a throusand years from now, the AIs will inevitably be making all the big decisions.

Random Developer 22 Jul 2025 18:02 UTC
1 point
0
in reply to: Noosphere89’s comment on: Foom & Doom 1: “Brain in a box in a basement”
Technical flag: I’m only claiming that near-magical nanotech won’t be developed in the time period that matters here, not claiming that it’s impossible to do.

I think there are several potentially relevant categories of nanotech:
1. Drexlerian diamond phase nanotech. By Drexler’s own calculations, I recall that this would involve building systems with 10^15 atoms and very low error rates. Last I looked, this whole approach has been stuck at error rates above 80% per atom since the 90s. At least one expert with domain expertise argues that “machine phase” nanotech is likely a dead end, in Soft Machines. Summary: Liquid-phase self-assembly using Brownian motion is stupidly effective at this scale.
2. Non-trivial synthetic biology. If you buy either the existence proof of natural biology or the argument in Soft Machines, this road should still be open to an ASI. And maybe some descendant of AlphaFold could make this work! But it’s not clear that it offers an easy route to building enormous quantities of GPU-equivalents. Natural selection of single-cell organisms is fast, massively parallel, and ongoing for billions of years.
3. Engineered plagues. This probably is within reach of even humans, given enough resources and effort. A virus with a delayed mortality rate similar to MERS with the transmissibility of post-Omicron strains of SARS-COV-2 might very well be a “recipe for ruin” that’s within reach of multiple nation-states. But critically, this wouldn’t allow an ASI to build GPUs unless it already had robot mines and factories, and the ability to defend them from human retaliation.
So yeah, if you want to get precise, I don’t want to rule out (2) in the long run. But (2) is likely difficult, and it’s probably much more likely than (1).

I partially disagree with this, and the reason for this is because I believe that buying time matters a lot in the singularity with automated AI alignment, so it really matters whether we would be doomed in 1-10 years or 1-12 months or 1-4 weeks.

If I strip my argument of all the details, it basically comes down to: “In the long run, superior intelligence and especially cheap superior intelligence wins the ability to make the important decisions.” Or some other versions I’ve heard:
- “Improved technology, including the early steam engine, almost always created more and better jobs for horses. Right up until we had almost fully general replacements for horses.”
- “Hey, I haven’t seen Homo erectus around lately.”
This isn’t an argument about specific pathways to a loss of control. Rather, it’s an argument that tireless, copyable, Nobel-prize-winner-level general intelligence which costs less than minimum wage has massive advantages (both economically and in terms of natural selection). In my case, it’s also an argument based on a strong suspicion that alignment of ASI cannot be guaranteed in the long term.

Basically, I see only three viable scenarios which turn out well:
1. AI fizzle. This would be nice, but I’m not counting on it.
2. A massive, terrifying incident leading to world-wide treaties against AI, backed up by military force. E.g., “Joint Chinese-US strike forces will bomb your data centers as hard as necessary to shut them down, and the UN and worldwide public will agree you had it coming.”
3. We ultimately lose control to the AI, but we get lucky, and the AI likes us enough to keep us as pets. We might be able to bias an inevitable loss of control in this direction, with luck. Call this the “Culture scenario.”
Buying time probably helps in scenarios (2) and (3), either because you have a larger window for attempted ASI takeover to fail spectacularly, or because you have more time to bias an inevitable loss of control towards a “humans as well-loved pets” scenario.

(I really need to write up a long-form argument of why I fear that long-term, guaranteed ASI alignment is not a real thing, except in the sense of “initially biasing ASI to be more benevolent pet owners.)

Random Developer 20 Jul 2025 17:52 UTC
1 point
0
in reply to: Noosphere89’s comment on: Foom & Doom 1: “Brain in a box in a basement”
Your points are excellent, and without near-magical nanotech, I suspect they rule out most of the fastest “foom” scenarios. But I don’t think it matters that much in the long run.

A hostile ASI (without nanotech) would need, at a minimum, robot mines and robot factories. Which means it would need human buy-in for long enough to automate the economy. Which means that the AI needs the approval and the assistance of humans.

But humans are really easy to manipulate:
- Powerful humans want more power or more wealth. Promise them that and they’ll sell out the rest of humanity in a heartbeat.
- Corporations want good numbers, and they’ll do whatever it takes to make the quarterly earnings look good.
- Humans are incredibly susceptible to propaganda, and they will happily cause horrific and long-lasting damage to their futures because of what they saw on TV or Facebook.
- Any new AI tool will immediately be given all the power and control it can handle, and probably some that it can’t.
Also, LLMs are very good actors; they can imitate any role in the training set. So the net result is that the AI will act cooperative, and it will make a bunch of promises to powerful people and the public. And we’ll ultimately hand control over, because we’ll be addicted to high quality intelligence for a couple of dollars an hour.

Once the AI can credibly promise wealth, leisure, and advanced medical technology, we’ll give it more and more control.

Random Developer 20 Jul 2025 13:24 UTC
2 points
0
on: A night-watchman ASI as a first step toward a great future
I see two major potential issues here:
1. There are many versions of “night watchman” libertarianism, based on various ideas like “preventing the initiation of violence.” But when you try to make these ideas rigorous, you quickly run into thornt difficulties defining what it means to “initiate violence.” Is trespassing on private land violence? Is squatting violence? Your proposal operates at the level of nation-states, so equivalent questions might be, “How should the night watchman settle the issue of China and Taiwan? What happens if the Chinese government decides to send police officers to Taiwan to arrest people?” Or, “If a state becomes brutally oppressive to its citizens, who can intervene? What if a state starts committing a mass genocide against a regional ethnic group, and that group tries to secede?” Will the night watchman intervene? Will it allow other powers to intervene? It gets very hairy, very quickly.
2. You’re implicitly assuming that any kind of stable or reliable alignment is even possible. What if we live in a world where “aligning” an ASI is at least as difficult as (say) preventing teenagers from drinking, trying drugs, or getting each other pregnant? What if anything truly described as “intelligent” is intrinsically impossible to control in the long run?
Actually, I think both these issues might be variations of the same theme. The night watchman fails because you can’t truly describe international politics using simple and unambiguous rules with no loopholes. And I predict alignment will fail because you can’t describe what you want the AI to do using simple and unambiguous rules with no loopholes.

Or to look at it another way, every attempt to build an AI using clear cut rules and logic has failed completely. Every known example of intelligence is (approximately) billions of weights and non-linear thresholds, and the behavior of such a system only has a probability of doing what you want. Neither ethics nor intelligence can be reduced to syllogisms.

Random Developer 20 Jul 2025 12:35 UTC
1 point
0
in reply to: Raphael Roche’s comment on: Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
I have noticed that Qwen3 will happily think in English or Chinese, with virtually no Chinese contamination in the English. But if I ask it a question in French, it typically thinks entirely in English.

It would be really interesting to try more languages and a wider variety of questions, to see if there’s a clear pattern here.

Random Developer 10 Jul 2025 16:45 UTC
1 point
0
in reply to: Esteemed Estimator’s comment on: An Opinionated Guide to Using Anki Correctly
Huh, I suppose. My card formats (see sibling comments) are easy and fun enough that reviewing 50-100 cards takes 15-30 minutes, and it’s not especially high stress.

But then again, like I noted above, I delete cards pretty ruthlessly if they’re obnoxious to review.