mijoharas

so, how are people running these locally? is there a llama.cpp/ollama solution for systemone/jev style apis?

UK too.

not at all, it's nice! solves the composability problem while keeping a trust separation between harness/ai bash calls.

I agree with most of what you said, but wanted to add that another point is there is a different level of trust in code executing from the harness, and code executing from the bash shell by the agent.

I block all network access from bash calls, but want to provide certain tools that can call certain services in a specific way. I can have a tool (or mcp) that does just that, and runs outside of the sandbox.

oh god, you're completely right! nice and obvious on a reread. (I also just learnt about "garden path" sentences.)

I'd googled "bernoulli map" after reading that, and came across this[0], which I wasn't aware of and thought was somehow related so I entrenched my misunderstanding (I didn't dig in.)

Side note: I just wrote the sentence "you're completely right!", and almost changed it because it sounds like slop now. I wonder if we're gonna get an increase in these sentences in human written prose over time as people mimic these sentences, or a decrease as people shy away from them to not sound like AI. :)

[0] https://en.wikipedia.org/wiki/Dyadic_transformation

From Bernoulli maps apparently. I still don't understand why[0].

[0] https://news.ycombinator.com/item?id=49723267 (see parent for reference)

> There is no "initialize a new thing on push" and there never has been

Well, there hasn't ever been a real reason for it, and now there is?

Ooi, can I ask for the reasoning for the new default of fullscreen?

The codemode stuff/mcp has been explained to death at this point but I haven't seen anything around fullscreen.

(I don't have strong feelings either way, just curious)

I was thinking the same in terms of similarity to org-babel (which can make some very nice runnable notebooks).

To be clear, is the issue with org-babel that it's not accessible to other people on the team? or something else that this solves?

I find it pretty handy. I run any bash tools in a restricted sandbox, and so that it cannot hit the network (usually). I don't want any credentials to be available to the agent, and my trust boundary for that is precisely the harness vs. the agent. Harness can touch secrets, agent can't (filesystem is restricted from it being able to read any secrets as well).

that's my one problem with the cli vs mcp debate. I prefer cli, because they're tools I'm familiar with, and they're composable. My problem with it is some cli tools need to use secrets to access things. By making sure they only go to the harness, then I've got my problem solved.

Getting a 502 error. I had to come to the comments to check whether that was the joke.

It is Bernoulli (mentioned in the comment I replied to). I just failed to guess that myself :)

Small request, can we get an explanation of the naming of "noul" in the docs[0]. I tried googling, and searching the docs and didn't understand why it was called that.

(I'd also argue something like p_yes or just probability might be a simpler name, but I'm sure there's a better reason behind Bernoulli maps).

[0] https://docs.typesafe.ai/primitives/noul#noul

I was curious about the choice of an immediate mode rather than retained GUI toolkit.

Could you speak a little more about the trade-offs and decisions there w.r.t. performance.

(Nice work btw, seems very interesting!)

C.f. this comment[0]

[0] https://news.ycombinator.com/item?id=49519099

I was surprised to see an immediate mode gui toolkit.

They're great to integrate into a game loop because you control your loop, (and they're a delight to use) but I thought for perf retained mode was the way to go?

Am I missing something? Then again if the bar needing to be beaten is spotify's existing desktop app maybe it doesn't matter?

So another active attack? Does anyone have any other details?

I thought Ruby Central were/had put this stuff behind them.

why are they still threatening to sue Andre Arko, and reporting him to the fbi?!

When I saw the postmortem or whatever it was called from schneems (and when I heard/saw he was involved and what he was doing) I really thought things were moving in the right direction.

ok, weird. Yeah, I saw this and thought "what's new, isn't that what moonlight/sunshine already is".

Is it just a new implementation? is that it?

[EDIT] all answered here: https://news.ycombinator.com/item?id=48976789

OK, so to clarify, it's Sunshine (game streaming server) but headless for linux.

So if I used sunshine, and streamed a game, the display of the box running sunshine would be showing the game? and this moonshine allows us to do away with that, to be able to run headless, or to run multiple games at once or something?

Is that correct?

Agreed. It's something I've found annoying about a few systems.

It looks like the rust bindings have streaming examples so hopefully there is a nice solution here.

So, I couldn't see it in the readme, apologies if I missed it but why?

It's a very significant speedup in decompression speed (albeit with a compression speed slowdown as a trade-off), but what's the insight that makes it faster? What was the idea or approach behind it?

> Representatives from Springer Nature declined to comment, beyond saying that “detailed information about specific retractions is usually confidential and can only be shared with the relevant authors.”

Was it a bot commenting as well? That's a hilariously tone-deaf response. Guess we'd better bust out the ouija board to ask max plank himself.

I found the thread hard to parse.[0].

Can you explain the reason? from a brief skim he is promoting some project he wants to start in wikipedia from outside wikipedia, is that it or did I misunderstand?

[0] https://en.wikipedia.org/wiki/Wikipedia:Administrators'_noti...

They at least claim that it is greater than Mythos class[0]

[0] https://news.ycombinator.com/item?id=48642254

Do you mean full benchmarks? Because from the article they claim 85.6 for 5.5-Cyber vs. 83.8 for mythos on Cybergym.

Oh! So the new openai model is limited to US residents and they use their existing KYC process to verify it?

That makes sense if both openai and anthropic have export restrictions on their similar models. If they didn't then it seems like the comment you're replying to may be correct.

This was my thought as well. I'm surprised that it's not being used here (afaict)

This article links to a previous one[0] (by Poul) which states:

> I will also state for the record, that there are no hard feelings between Varnish Software and the FOSS project.

I wonder if that is still the case now. (this article is fairly diplomatically written, but I'd imagine it must be pretty frustrating)

[0] https://vinyl-cache.org/organization/20-years.html#years

> That the tech benefits may not be there, but they’re using it for the non-tech benefits

My read of the article is that this is correct, but that the benefits they're using it for are the operational, and organisational.

I think the comment you're replying to is arguing that those benefits don't really matter or outweigh the additional complexity costs when N=2 (engineers). I think I'd probably agree.