foota

Yes, sort of. Generally you can measure the pass rate on a benchmark given a fixed compute budget. A sufficiently smart model can hit a high pass rate with fewer tokens/compute. Check out the cost efficiency on https://artificialanalysis.ai/ (say this posted here the other day, pretty neat charts!)

> On April 16, we added a system prompt instruction to reduce verbosity. In combination with other prompt changes, it hurt coding quality, and was reverted on April 20. This impacted Sonnet 4.6, Opus 4.6, and Opus 4.7.

Claude caveman in the system prompt confirmed?

I found this while looking for a solution for more easily removing some unsafe code from a library that does a lot of C FFI. I didn't end up going with it though, for now I'm taking an approach of mapping valid pointers that I return to the caller and then validating that pointers passed to my library functions are in that valid mapping (and then also using that valid mapping to contain some additional information that doesn't fit in the ABI of the structs that the pointers are for that I use to safely do validation. So e.g., I can store the range of some other valid member pointers as a normal safe rust reference and then index into it with member pointers on the struct, completely avoiding unsafe code despite having this FFI boundary (obviously the FFI boundary itself is still unsafe, but I can take this ugly C struct with a bunch of raw pointers and handle it safely)).

That's curxed

It was admittedly a bit sloppy. The more accurate version (IANAKSPP, I am not a kerbal space program player) would be that the only way to maintain a satelite in one position (without expending an infeasible amount of energy) is to position it above the equator and sync its speed with the Earth's rotation, allowing it to stay in a single position above the Earth. Satelites always have to be moving fast enough such that the centripetal force is sufficient to counteract the Earth's gravitational pull, otherwise they would fall back onto the planet.

I don't believe parent is right, but satelites don't stay in one place unless they're on the equator, because otherwise they have to be moving. This means that you need many satelites to maintain coverage of a single spot.

I don't know how many military satelites China has, but I would have assumed it would be sufficient to cover the pacific sufficiently to find an aircraft carrier. (the obvious caveat here being clouds, which are fairly common over the ocean)

Yeah this wasn't something like "I want to debug a program" but rather I wanted to be able to track mmaping for later cleanup.

Fortunately libc doesn't mmap that much internally so I think I can get away alright with interposing lib's mmap call.

Fun fact, overwatch must have done a similar things because they would let you play back games up until some release when you could no longer replay them unless you'd saved the render.

I think if I remember right there were also funny moments where things didn't look right after patches?

Hah, I've been looking into something amusingly similar to track mmap syscalls for a process :)

More like RAM producers are providing supplies to the highest bidder, no? If this doesn't peter out supply will normalize at a higher but less insane price eventually.

Capital and availability?

Snowpiercer but with data centers? The breeze would help with cooling!

Eh, that doesn't math out. It's the bandwidth per storage density (or ultimately per price) that matters.

If you have great cost per byte but your bandwidth per byte is bad enough that the price per byte doesn't make up for it then you have an issue.

They've started making hard drives with multiple heads because of this issue, they increased density to the point where it's not useful to continue adding density if it doesn't come with more bandwdith.

The cost issues they're seeing (at least from what they've stated) are from users, not internally. Basically, it takes either $5 or $6.25 (depending on 5m or 1h ttl) to re-ingest a 1M context length conversation into cache for opus 4.6, that's obviously a very high cost, and users are unhappy with it.

I think 400k as a default seems about right from my experience, but just having the ability to control it would be nice. For the record, even just making a tool call at 1M tokens costs 50 cents (which could be amortized if multiple calls are made in a round), so imo costs are just too high at long context lengths for them to be the default.

Hey -- I have 0 PHDs so take this with a grain of salt :)

I had thought for a while about a way to store data that makes use of an idea that I had for sub-diffraction limited imaging inspired by STED microscopy.

First an overview of STED. You have a "donut" shaped laser (or toroidal laser) that is fired on a sample. This laser has an inner hole that is below the diffraction limit. This laser is used to deplete the ability of the sample to fluoresce, and then immediately after a second laser is shone on the same spot. The parts of the sample depleted by the donut laser don't fluoresce and so you only see the donut hole fluoresce. This allows you to image below the diffraction limit.

My idea was to apply this along with a layer in the material that exhibits sum frequency generation (SFG). The idea is that you can shine the donut laser with frequency A and a gaussian laser with frequency B at the same spot. When they interact in the SFG material you get some third frequency C as a result of SFG. Then, below that material would be a material that doesn't transmit frequencies C and A.

Then what you'd be left with after the light shines through those two layers is some amount of light at frequency B. The brightness inside the hole and outside of the hole would depend on how much of the light from frequency B converts into frequency C. Sum frequency generation is a very inefficient process, with only some tiny portion of the light participating, but my thinking is that if laser B is significantly less bright than laser A, then what will happen is that most of the light from laser B will participate in sum frequency generation where it mixes with laser A, and that you'll be left with only a tiny bit of laser A outside of the hole, so that you get a nice contrast ratio for the light at frequency A between the hole and the surroundings that then allow you to image whatever is below these layers below the diffraction limit.

In my idea the final layer is some kind of optical storage medium that can be be read/written by the laser below the diffraction limit. Obviously aiming this would be hard :) My idea was that it would be some kind of spinning disk, but I never really got to that point.

Late to reply, but.. yes, hence my reply that it would need to be integrated all the way down the stack.

But also, LLMs (or their current implementation) rely heavily on print caching for efficiency, without this costs are much higher. You can do neat tricks with it, but generally you're limited to playing with the end of the context to avoid breaking things.

I think some agents do add small context snippets to the end of the conversation that get used by the agent. You can do things like: conversation messages + context snippets + new message and then once the agent replies make the next turn conversation + new message + reply + ... This breaks the cache only for the latest message (not too bad) and let's you give the model current up to date information. This is how stuff like the "mode" or "what time is it now" are handled I believe.

I would go for out of touch, not cynical. A lot of people really think AI is the devil.

Some others mentioned pijul, but I will put in my two cents about it. I have been looking to make use of it because it seems really nice for working with an agent. Essentially you get patches that are independently and can be applied anywhere instead of commits. If there is ambiguity applying a patch then you have to resolve it, but that resolution is sort of a first class object.

Not really, because the LLM loop doesn't have the ability to get updates from the agent live. It would have to somehow be integrated all the way down the stack.

And they are doing better.

So.. it sounds like they're doing a lot better to me? 19 cases in the fall, 4 between the recall in Novemberish and Jan, and 1 between them and now that occurred in Jaunary?

Also lol at this quote in the article "Six vehicles passed the school bus while it was stopped, the agency said. It is still investigating." What it doesn't note is that the other 5 seem to have been human driven passenger vehicles. From the NTSB report: "located in Novi, Michigan, replied “No” to the prompt. The ADS-equipped vehicle then resumed travel and passed the school bus while its stop arms were still extended. A passenger vehicle following the ADS-equipped vehicle similarly passed the school bus. In total, six vehicles passed the school bus while it was stopped. A crash did not occur.", so it sounds to me like 4 people passed it, waymo was like wtf I'm pretty sure that's a stopped bus, a human incorrectly identified it as not a bus, waymo passed it, and then one more person passed after the waymo.

I don't think this checks out. Would the model do the same thing when presented with the exact same inputs? Yes. Is it more likely to do the same thing at the same intersection? Probably. But if you repeat a similar setup somewhere it might not. Bad behavior still exists and should be fixed, but it doesn't mean they're bad drivers in general.

Somewhat unrelated, but if I have downloaded node modules in the last couple days, how should I best figure out if I've been hacked?

Hah, I did the same exact thing and came here to say that :) I was looking at wiring diagrams and telling myself I could wire up some arduino circuits for it but gave up when when I realized I could just press the button!

edit: although mine was an ancient system from the early 90s. It was just replaced with a modern system a couple months ago. At my previous apartment I had wanted to set up a system that would allow either my then partner or I to activate the callbox and have it set for a VOIP number since we could only put one number on the box.

I added a super cheap and bad embedding database in a project that allows the agent to call a tool for searching all the content it's built, it seems to work pretty well! This way the agent doesn't need to call a bunch of list tools (which I was worried would introduce lost of data to the context), and can find things based on fuzzy search.

It would be fascinating if someday you could implement parts of the browser using WASM modules.

I realize this comes up every so often, but I was just looking at this the other day :) A related idea is wang tiles, which are a way to construct a tileset such that you can place them without ever running into a contradiction.

Could it be because nuclear is highly centralized? I would expect that something like solar/wind power would be better for decentralization (in a war).

Even if you don't blow up a nuclear plant, it seems like cutting the power from one would be relatively easy.

Copyright for me not for thee? :) That's a good point though. Maybe they could round trip things? E.g., use the model trained only on internal content to generate training data (which you could probably do some kind of screening to remove anything you don't want leaking) and then train a new model off just that?

> I don't think this would qualify as clean room (the Library was involved in learning to generate programs as a whole)

Hm... I mean this is really one for the lawyers, but IMO you would likely successfully be able to argue that the marginal knowledge of general coding from a particular library is likely close to nil.

The hard part here imo would be convincingly arguing that you can wipe out knowledge of the library from the training set, whether through fine tuning or trying to exclude it from the dataset.

> But what about training without having seen any human written program? Coul a model learn from randomly generated programs?

I think the answer at this point is definitely no, but maybe someday. I think it's a more interesting question for art since it's more subjective, if we eventually get to a point where a machine can self-teach itself art from nothing... first of all how, but second of all it would be interesting to see the reaction from people opposed to AI art on the basis of it training off of artists.

Honestly given all I've seen models do, I wouldn't be too surprised if you could somehow distill a (very bad) image generation model off of just an LLM. In a sense this is the end goal of the pelican riding a bicycle (somewhat tongue in cheek), if the LLM can learn to draw anything with SVGs without ever getting visual inputs then it would be very interesting :)