devmor

> I don’t think I’ve heard of elegant code leading to discovery on its own.

I’ve not heard of it either, but code is an abstraction of math, so I don’t see why this couldn’t theoretically happen.

Anecdotally, I’ve started spending time advancing my math skills beyond the early college level I stopped at and I’ve frequently found I already know concepts of more advanced math - I just didn’t know what they were called or how to apply them to an equation on paper, but I’ve been using them for years and intrinsically grasped the underlying academics.

Not officially, but the name "Generic TLDs" was coined to differentiate them as for general use, in contrast to country-specific TLDs at the time.

Restricting them to specific entities seems against the spirit to me.

I'm exhausted by all of the new gTLDs at this point, opening them up to specific companies and organizations basically violated the entire purpose of a gTLD in the first place.

Well said. I'm sure a subset of the content that Cloudflare has indexed also has terms like Cloudflares, that they happily ignored.

"Likely Impossible" as in, we would need a revolutionary discovery in how thermodynamics apply to crystal formation.

Why hyperbolize when I am commenting on something it has actually done and the vastly exaggerated claims related to this?

One of the materials is most likely impossible to synthesize. The other already exists, so that may actually be capable of being tested. It's only been synthesized once, 27 years ago though.

You are vastly overestimating what has been achieved here.

This is something a couple of materials science grad students can do in limited time for poor compensation as well. The expensive budget is for the part that comes next.

Depending on the car, how you disable it may not really disable it at all. Connecting your phone via Bluetooth or taking the car in for service will often let the car upload a backlog of data.

You generally have to completely remove the power from the DCU - which can have as many as three different power sources (including a backup battery with days of power in some cases!), and often disables features in your car like the hands free microphone, built in gps, etc.

You absolutely can, that’s what your harness is for. You don’t need your environment to “reason” about things when deterministic tools exist - You have a really fancy hammer, but that doesn’t make everything a nail.

I agree. It’s closer to a jump box than it is a SaaS offering.

I’m not really sure, I can’t say I trust any kind of synthetic AI benchmarks.

> Also I’m very interested in the unique failure cases you’re referring to! What have you noticed?

Permissions issues would be the most common - models collaborating with eachother on a task seem to try to convince eachother they have either more or less permission to do things than they actually do. Especially when transitioning between creating a plan and executing the plan.

Another is deciding that there is a limit to the “loops” they are allowed to run to iterate on something. In many cases I have set an explicit goal, and come back to an agent stopped and reporting that it has hit the “maximum allowable loops of [insert arbitrary number that changes every time].”

Now that I think about it further, I believe the other examples I have also all fall into the models hallucinating the presence of control instructions, or attempting repeatedly to violate permission boundaries that a single model’s harness instructions would usually guide it away from re-attempting.

If that is truly the impetus behind this ridiculous crap, I hope they purge whoever is behind these ideas quickly before they waste any more money.

They already have relevance, they maintain the only browser stack that is not controlled by a data harvesting firm.

I don’t understand why Mozilla keeps doing these odd projects. They maintain the only real alternative browser stack to Chrome and rather than keep it up to date and triage bugs, so many resources keep flowing into random AI hype crapware that no one asked for.

I would like to see this (and any model router, frankly) benchmarked against two things, personally:

1) Claude Code's "advisor mode" (nominally, Sonnet 5.5 with a Fable advisor)

2) Copilot's "HydraFusion" model router/advisor combo.

Specifically I would like to see them compared on architecture planning (both human assisted and hands-off with a draft document) and code review, as these are what I have found the most significant improvement on with multi-model systems.

> our initial hypothesis that an ensemble of models can do better than any single model ever could.

To your hypothesis, anecdotally I find both of these offerings to be far superior to any single model for most tasks of any real complexity, and both to have general frustration/failure cases that single models do not. I would not be surprised that any ensemble approach that utilizes more than one single model meets this hypothesis.

Quite frequently I delegate review and restructuring loops to subagents acting as judges/advisors to tell the primary agent if it met the goal it was instructed to. For some workloads, I will even vet every tool call and user-facing output this way.

Side-tangent, but this reminded me of the health nightmare that the incredibly common “kinetic mist” style humidifiers/vaporizers are.

I think there may be a general lack of understanding to how pollution and bacteria concentrate in our daily environments.

I genuinely don’t understand the point of this product. Anything I could think of for an “always on agent” to do, AI is not yet good enough to do without being supervised.

I think you're operating on a different definition of "work".

The OP is discussing tasks to do, you sound like you are discussing things that need to be done. The OP isn't saying there aren't things to be done, they are saying that no one is going to tell them what needs to be done, so they must discover and formalize it.

"Inventing Work" is a bit tongue-in-cheek.

I used to believe this without a shadow of a doubt, but without the choice to go out on your own accord, I don't know if I do any more after what I saw.

If I had to die like what I saw, to live to 80? I'd take quickly at 45, I think.

Sure, but like - no one wants to die like that. It's horrible. He was begging us to let him die at the end.

No, I don't think most people die in excruciating pain.

I don't think I want to die in excruciating pain and confusion at any age, personally.

I would heavily disagree with this - it depends entirely on the cancer you get. If it's something slow growing that would take a decade plus to kill you, sure - just trying to treat it would be worse than letting it ride.

But my father died of cancer nearing age 80, (most likely mesothelioma, though we didn't do heavy tests as it was discovered late), and it was incredibly painful and miserable for him. He had fast growing tumors in his ribs, forcing bone to spike out and hit his lungs, the tumors that grew in his lungs caused constant pneumonia and kept leaving him unable to get enough oxygen to his brain to communicate for hours at a time.

Exactly what I was thinking.

Or hear me out here… we as a species have developed measuring methodology that is precise enough at human scale but not actually correct and breaks down at larger scales.

Oh, sure yeah I agree with that. I was just making a point about the “big hunk of metal” comment and the fact that emissivity is important because the expense of radiator materials aren’t the problem - the surface area (and mass) of the radiator is.

Emissivity is an important factor here because as I said, and as the sources I linked for you to reference clearly stated convective radiation is not taking place in space.

Both Google and NASA are worried about this for a reason, if you think they are wrong, you should offer your assistance to them, rather than debating me.

> Please stop with this argument. This is one of the easiest problems to solve. Heat dissipation requires a radiator, which is just a dumb hunk of metal.

Convective radiation does not happen in space and this challenge is far more significant than your comment implies. Rather than "a dumb hunk of metal", radiators for spacecraft are often made of ceramics and carbon laminates with higher IR emissivity than convective radiators made of simple metals.

From the article you're commenting on:

> The chips can operate for about 15 minutes in space before needing to be shut down so they can cool off, said Travis Beals, Google’s senior director of product management for Project Suncatcher.

The Thermal Control section on NASA's Small Spacecraft documentation center is quite an interesting read for this subject: https://www.nasa.gov/smallsat-institute/sst-soa/thermal-cont...

ML Infrastructure comes with some pros (larger emissive footprint) and cons (exponentially larger TDP) compared to the concerns there, but if you aren't familiar with the challenges of heat dissipation in space, please give it a read.

There's also a pretty interesting pop-sci article on cooling the Webb telescope, since it needs to be especially cold for its purpose. Not directly related, but may give insight into both challenges and solutions as well as well. https://science.nasa.gov/mission/webb/science-overview/scien...