cruffle_duffle

“ If a battery can do 1000 cycles and remain above 80% capacity it is exempt”

I mean isn’t that an okay exemption? If the intent is to drive devices to be less disposable and more sustainable… if it incentivizes all mobile phone manufacturers to improve battery longevity, I’d say that’s a win.

I wouldn’t even call it a loophole. The entire purpose of the legislation could be that clause

I mean you aren’t wrong. It’s just I don’t think it requires any kind of vote manipulation to see why ai company releases hit the front page. Back in browser war days it was the same thing.

You can let the LLM create slop for you, sure. But only amateurs are using it for that. You’ll be much happier if you treat it as a tool and use it like any other, a force multiplier to take your ideas and creations and pushes them further along faster.

If you treat it like a black box used to outsource your own thinking, you are holding it wrong.

It could also be that this is an exciting new, fast changing technology that happens to directly overlap and significantly impact the core audience of the site. I don’t think any form of maliciousness or secret astroturfing is required at all.

This stuff has changed a ton of what it means to exist in this whole “tech space”. The entire software development lifecycle got put into a stick blender and is in the process of getting mixed up in new and unusual ways.

It’s super cool. I haven’t been this excited about our industry since way back when the universe was just starting to get onto dialup and I grabbed my very first mp3 or wrote my first shitty program in VB or when AJAX was just entering the universe.

I think a lot of people forgot how fast shit changes in this industry and how learning new things is one of the most important skills to being successful. Everything changes all the time.

This is a tech site called hacker news. Where else would something like this be constantly discussed?

Shadcn and friends are the modern equivalent of old vb custom controls.

Oh my god have Anthropic products been absolutely saying everything is load bearing for the last week or so. Literally ever other paragraph has “such and such is load-bearing”.

Funny enough, today it seems to have stopped…

> You're proving my point. The thumb was put on the scale, he public was bombarded 24/7 with self-serving false dichotomies and viola, you've just manufactured mass public support for insane bullshit.

See also Covid-19. Same shit only waaaaaaay more batshit insane and waaaaaaaay more crazy 24-7 fear mongering.

Tool discovery is only one very small part of the “context problem”. The bigger problem is the outputs. You can’t compost them. Ever watch Claude code run some crazy shit through python and jq to take some input, transform it in some crazy way and output exactly what it needs back into its context? You simply can’t do that with mcp. It’s basically forced to accept the exact shape of the mcp output into its context and then take that intermediate output and dump it right back into another tool. That is incredibly wasteful!

If your lucky the mcp might expose a way to ship its output into a text file so at least the agent can have a go at it with CLI tools.

> Why does it matter if that output is stored in the LLM's context

Context window is expensive and precious. Much better to offload to some medium where it isn’t.

At that point might as well just use CLI

I totally agree that mcp not being compostable is a very big issue.

Coming soon to the moon near you: starlink!

Piles and piles of sci-fi novels.

This is actual reason. So any investors reading our system card.... write us another check and watch the $$$$$$$$ roll in. It's so dangerous we can't even release it!

"for example, consider using models to write email -- is it a misalignment problem if the model is just too good at writing marketing emails?? or too good at getting people to pay a spammy company?"

But who gets to be the judge of that kind of "misalignment"? giant tech companies?

These things are so damn cool!

Cautious for what? Unchecked doomerism? Just release the damn models. Do it in phases, roll it out slowly if they are so damn worried about "safety".

The real reason they aren't releasing it yet is probably it eats TPU for breakfast, lunch, and dinner and inbetween.

It sounds like the PoE spec was designed before the arrival of “IoT” type things like the esp32, raspberry pi’s, etc.

How much of the complexity is a “fundamental electrical engineering problem” and how much of it is just a spec written to solve a different set of problems?

Smaller teams working on much more diverse set of problems.

The truth is absolutely nobody knows how this will all shake out.

Subagents are isolated context windows, which means they cannot get polluted as easily with garbage from the main thread. You can have multiple of them running in parallel doing their own separate things in service of whatever your own “brain thread”… it’s handy because one might be exploring some aspect of what you are working on while another is looking at it from a different perspective.

I think the people doing multiple brain threads at once are doing that because the damn tools are so fucking slow. Give it little while and I’m sure these things will take significantly less time to generate tokens. So much so that brand new bottlenecks will open up…

To paraphrase, spacex is "making the impossible merely late"

It'd dogfooding the entire concept of vibe coding and honestly, that is a good thing. Obviously they care about that stuff, but if your ethos is "always vibe code" then a lot of the fixes to it become model & prompting changes to get the thing to act like a better coder / agent / sysadmin / whatever.

Thanks!!!

> How can people be so naive as to run something like Claude anywhere other than in a strictly locked down sandbox that has no access to anything but the single git repo they are working on (and certainly no creds to push code)?

Because it’s insanely useful when you give it access, that’s why. They can do way more tasks than just write code. They can make changes to the system, setup and configure routers and network gear, probe all the iot devices in the network, set up dns, you name it—anything that is text or has a cli is fair game.

The models absolutely make catastrophic fuckups though and that is why we’ll have to both better train the models and put non-annoying safeguards in front of them.

Running them in isolated computers that are fully air gapped, require approval for all reads and writes, and can only operate inside directories named after colors of the rainbow is not a useful suggestion. I want my cake and I want to eat it too. It’s far to useful to give these tools some real access.

It doesn’t make me naive or stupid to hand the keys over to the robot. I know full well what I’m getting myself into and the possible consequences of my actions. And I have been burned but I keep coming back because these tools keep getting better and they keep doing more and more useful things for me. I’m an early adopter for sure…

There is also the browser I use to get Claude to route around people blocking its webfetch. Both Playwright and chrome-mcp.

I bet dollars to doughnuts that 95% of the traffic is from Claude and ChatGPT desktop / mobile and not literal content scraping for training.

It will mess up eventually. It always does. People need to stop thinking of this is a “security against malicious actor” thing… because thinking in that way blinds you to the actual threat… Claude being helpful and accidentally running a command it shouldn’t. It’s happened to me twice now where it will do something irreversible and also incorrect. It wasn’t a threat actor, it wasn’t a bad guy… it was a very eager, incredibly clever assistant fat fingering something and goofing up. The more power you let them wield, the more chance they’ll do accidents. But without lots of power, they don’t really do much useful…

It’s actually a hard problem. But it really isn’t “security” in the classic sense…

Hah… I’ve seen Claude happily and very cleverly find ways to escape its sandbox. It’s like some kind of arms race between the model and its designers.

Dude. I’ve been thinking about this a lot! I think it’s because the traditional way we internalize the costs of what we are building just got take for a ride. We don’t really (or I don’t anyway) fully know what “too much scope” feels like with one of these Claude thingies. So it’s easy to completely both overestimate complexity and underestimate it too. Some times the LLM makes a seemingly daunting refactor be super simple and sometimes something seemingly not complex can take it forever… and there really is, for me, a good “gut sense” of how something will go.

So lately I’ve just decided that I’ll time box things instead of set defined endpoints. And by “endpoint” I really mean “I’m done for the day” and honestly maybe thinking about it… “I’m done with this project”.

I don’t know. But the term “Claude Creep” is absolutely something I can identify with. That thing will take you down a rathole that started with just pulling in some document and ends with you completely repartitioning your file system. lol.

A lot of getting good mileage out of LLMs is promoting them to behave like they are blind and can only base their outputs on what is in front of them. Maintain an emic stance.

That is an interesting way of looking at that, thanks for the perspective!

Like, the words fit… why create a second parallel language for describing LLM behavior.

Somebody else said it… the whole “it’s a stochastic parrot” thing is sooooo cliche and boring at this point. It’s like, duh… what is your point?