dummydummy1234

I have started to wonder if anti-heros are generally bad at a social level. If you train people to believe that bad people are not that bad and good people are not that good, and you should never believe the name on the tin, then people start carrying over those lessons to the real world, and encouraging antipathy since anyone who esposes good ideals is lying, and anyone who esposes bad ideals is playing 4d chess, or is not that bad - so what's the difference?

So can you not do structured output and get the log probs across all your allowed output classes? Then use that relative measure of how confident it is?

Codex is written in rust, fyi... Not that I disagree.

We're all project managers now...

Why are v8 isolates bad, I see speculative execution hacks, but are there others?

I remember looking into Bitcoin in 2012, and thinking:

"This will never work as a currency, because of the max number of bitcoins it will inherently be deflationary, and the value will go up, which means that there will be a disincentive to spend it, because the value will just go up..."

Yep... Did not buy any.

The thing with starlink is that there are a lot of them. It is not a single satellite to take out it is a bunch.

Ahh, OK

Thanks!

So this means that every node in the graph has to be a fully fledged agent runtime with the smarts to handle an arbitrary filesystem.

I guess there is some sort of tool call that the agent has to tell the runtime 'I am done, and I succeeded go to the success node in the parent state machine'

---

I think I have been trying to approach a slightly different problem where you have a mostly deterministic control flow of steps/ nodes in the graph, but individual nodes can be pretty stupid/ small models, so having a more constrained universe should be more reliable. (My intuition)

My example is a citation checker for an essay -

1. generate a list of claims in a paragraph, For each claim: Read the attached citation, validate that it backs up that claim.

The output is a nested json structure with a list of claims with a explanation+binary classification of whether each one is supported.

This is not really agentic, and the nodes would be claim identification > validate claims (in parallel) > deterministically merge the validated claims into a unified module.

It should be very token efficient, and since it is so constrained I think I can get away with tiny models, and small context.

At least that is my hope... But I think I need typed IO/state so that the llm that writes the graph can deterministically say that the individual nodes complete the problem wholly.

How are you thinking about state management when you handle things? I have been playing around this and the state gets messy fast.

Was just in south America, everyone uses it.

For context, I read Claude output every single day, I know what it is reliable with and what it is not. Or at least I have a feel for how much I can trust it.

It may not be clear to a non-english first language person, but when I read Claudes documentation, my brain immediately picks up claude-speak. Therefore, I expect the code to be generally correct, maybe, depending on how specific I was during my prompting. In no way shape or form do I really trust it, at least until i dig into the code and validate my mental model. And query the review for edge cases etc...

By writing your documentation with Claude, my brain immediately associates the quality of the project with the quality of unreviewed Claude output.

To a degree this is unfair, as it is like judging the quality of someone's work based on their accent.

But Claudes accent, has a high correlation with Claude, so unlike with people, where an accent has no bearing on technical ability, Claude being Claude does.

I would much rather read a typo ridden sentence than claudism, even just as a forward, explaining what you did vs the ai, and telling the users how much we should trust it.

Also, If you really insist on using AI to write, have another model rewrite docs/comments into regular English (opus 4.6 for example is much better than 4.7, 4.8, or 5.

It is open source so you can do whatever you like, but people (especially native English speakers) will discount your work, because Claude, especially opus 5 writes very very badly.

The people who say they would rather see a typo infested mess of a readme are serious. Or even just write in your native language and then have Claude translate.

Both of those are better indications of proof of effort than a Claude readme.

Out of curiosity what state are you in?

I think the question is how do you keep track of the ideas that the agent is pursuing - like I was working on this for implementing a fft, and doing the optimizations, but I held its hand and was like - hey let's go back and retry this older thing you discounted because of a 3 % slowdown.

From my perspective it does not tell me how it works, or the give examples of why you would use it?

Is it a actual Linux kernel + filesystem under the hood?

Or did you just use the standard utilities compiled for wasm,

how does network access work (assume it doesn't because of coors)

Can you run non-wasm programs? How do entry points work - what about ctrl-c and interrupts for long running programs.

You do not discuss any of this and it seems half baked.

(This coming from someone who has explored how to do this for a vscode in browser editor playground)