I can fold the paper into origami.

I guess one could extrapolate a programming metaphor as the origami that notepad.exe enables.

No, I don't care about license provenance for all the components of a 30 line script that i'm using in my house, for myself to sync up some folders. No, i'm not going to find and archive the licenses for all the previous projects leading to this for future legal disclosure.

Yes, I own the DVD for the movie i'm transcoding. No I don't want to talk about the legality of rebroadcast.

Deepseek (and most chinese models as a whole) don't care . oAI and Anthropic models want to make it point #1.

... which is extra hilarious knowing the laws broken to create the damn models in the first place.

there's a literal meme about this floating around the harness/AI chats for the past few months[0]

[0]: https://i.ibb.co/SwH4Sgwq/796779070-28483090404651613-920066...

but that's not really how the risk should be considered.

as far as the on rails comment : there's no good way to know the provenance of an LLM output, but the LLM made bots generally look like very small, modular, sometimes functionalized versions of the human equivalents; the difference being that the LLM is calling the funtions often rather than a conditional loop in a main().

a factorio bot I worked on when Astra was first getting previewed was essentially a directory of very small argument-receiving functional and self-supporting programs that had very limited scope, and an agents.md file that directed the LLM to where such capabilities existed to preempt a directory search every compaction/context-swap.

so you'd have things like "python walk.py N 40" for 40 units of northern travel. a watchdog that waited for HP to drop or movement to become inhibited, etc.

My very first experience with LLM driven bot development in the GPT3 days created huge unmaintainmable monoliths that kind of worked due to TDD but were essentially spaghetti. LLMs have been trending away from those paradigms into small self-encapsulated programs. probably because those are less abusive to ctx count and produce better results since they lose/compact less.

at least thee 'hairy egg' one made me laugh; the alternate i've seen lately is a plea to avoid mentioning that they're furry if you're from HN using the HN referrer; that one is a bit more groan-inducing than the full page anti-capitalism nut scree.

and that's totally ignoring the fact that it's only a supremely naive user that hasn't yet refined their filters to exclude dangerous extensions (or, if they're too lazy to do that, rely on one of the many many pre-assembled filter/grabber settings across the net which already do so.)

what fear-mongering and FUD-spread.

You may also want to warn the public about the dangers of having curl, wget, python or gcc installed.

They expose a PLETHORA of attack vectors! you're probably already compromised, realistically!"

... and they're actually more dangerous than a free-floating EXE.

white knight with a sword made of patent lawsuits doesn't exist in my world.

It was good of them to decide to stay away from producing the product they realized they didn't want to exist, they should have stopped there instead of villainizing themselves by self-deputizing.

let's all join a private tracker!

that'll fix the problem, the bad actors won't chase the crowd, and it definitely wont end in a burning of the library of alexandria loss-of-history what.cd style event again and again if the public can't archive it.

/s

how about we just create an exe/bat/com exclusion on our dumb-as-dick media downloaders like sensible people have been doing for 30+ years?

Maybe they don't want to make potential customers aware of competitive alternatives.

the results i've gotten so far have been a little braindead though. still playing around. bad luck with traversing filesystems remotely so far.

it seems to want to make concluding decisions very fast regardless of reasoning levels.

it's kind of a loaded question, this model gets a lot of tok/s but reasoning is forced on; the time-to-answer is really a combination of things like "how much does this thing want to over-reason" and "how much does this thing like tool use?" .

very nice.

I can't speak to the intelligence of it yet.

these small agentic-focused models are a lot of fun to play with if you haven't yet.

either that or fail outright; dont waste my time.

might be a good characteristic for a quantized model to have ..

most of the harnesses are checkpointing most of the data of a git commit aside from the formal release and messaging, anyway; thats why they all have a similar problem with SQL dbs exploding in size after a bit of time.

Right now we're in this weird transition where most of the harness systems are layering git tool use w/ the constant snapshotting AND a memory subsystem often, probably leaves a lot on the table in saving wasted token use to just ditch the vcs all together and rely on the already persistent and existent checkpoints and memories for reconstruction.