randall

+1 to this.

wow! i’ve been using deno for a long time, and one of my fav features is compiling a binary. i didn’t see anything about that, but might have missed something… do you all plan to support this?

this isn't strictly true. not that it thinks, but it can reason about the tokens that led to the outcome.

this is "you ship your org chart" not ai.

https://en.wikipedia.org/wiki/Conway%27s_law

Does anyone have a link to the "read more"?

exactly. They probably have unsustainable margins on accident.

sweet.

I've been out of the game for a bit but it's great to hear.

This is the least informed take i've ever seen.

I worked at fb, and I'm 100% certain we sponsored VLC and OBS at the time. It would be strange if we didn't sponsor FFMPEG, but regardless (as the article says) we definitely got out of our internal fork and upstreamed a lot of the changes.

I worked on live, and everyone in the entire org worships ffmpeg.

even marvel villain thanos was given a plausible motivation.

i don’t think if you actually knew him as a person you’d think this was a reasonable perception.

same. this is about losing a negotiation and saving face / exacting revenge.

i don’t get it. what’s his motive in your view? he literally has no shares in openai.

I wanted the AOL one to say "Welcome" before "you've got mail!" lol

The last 3 years of LLM progress, to me, feel like 1994-1998.

this is like irl cryptographic signatures for content lol

thanks for the PR! :)

yaaaaa exactly. You're totally on the same wavelength as me. Let's be friends lol

once your team comes to a consensus on what PII is, you can roughly guarantee it... especially as models improve.

So two things.

1/ crypto signing is totally the right way to think about this. 2/ I'm limiting prompt injection by using chain of command: https://model-spec.openai.com/2025-12-18.html#chain_of_comma...

we have a "gambit_init" tool call that is synthetically injected into every call which has the context. Because it's the result of a tool call, it gets injected into layer 6 of the chain of command, so it's less likely to be subject to prompt injections.

Also, relatedly, yes i have thought EXTREMELY deeply about cryptographic primitives to replace HTTP with peer-to-peer webs of trust as the primary units of compute and information.

Imagine being able to authenticate the source of an image using "private blockchains" ala holepunch's hypercore.

i have a huge theory here that idk when we’ll implement but it has to do with “quorums” and other stuff.

hard to explain… we’ll keep going.

right now yeah we’re just dropping context… sub agents are short lived.

thinking about ways to deal with that but we haven’t yet done it.

yeah the way to do that stuff is through zod schemas… input and output schemas.

you can set up really complex validation.

thanks for checking it out!!

i have a slightly different but related take. the models actually are getting smarter, and now the challenge becomes successfully communicating intent with them instead of simply getting them to do anything remotely useful.

Gambit hopefully solves some of that, giving you a set of primitives and principles that make it simpler to communicate intent.

So I look at something like Mastra (or LangChain) as agent orchestration, where you do computing tasks to line up things for an LLM to execute against.

I look at Gambit as more of an "agent harness", meaning you're building agents that can decide what to do more than you're orchestrating pipelines.

Basically, if we're successful, you should be able to chain agents together to accomplish things extremely simply (using markdown). Mastra, as far as I'm aware, is focused on helping people use programming languages (typescript) to build pipelines and workflows.

So yes it's an alternative, but more like an alternative approach rather than a direct competitor if that makes sense.

thx, i appreciate it, believe it or not. :)

Thx! Happy to help if you need it. :)

thx!

omg thank you so much. We're working on the file system stuff, that's an easier lift for us than the initial work, so we wanted to start with the big stuff and work backward. Claude Code and Codex are obviously really great at that stuff, and we'd like to be able to support a lot of that out of the box.

I think that works out tremendously well for Nintendo, especially when you look at the Wii-U vs the Switch.

I shot a video at CNET in probably 2011 which was a single touchscreen display (i think it was the APX 2500 prototype iirc?) and it has the precise dimensions to the switch 1.

Nintendo was reluctantly a hardware company... they're a game company who can make hardware, but they know they're best when they own the stack.

Nope, apple container just runs a lot more efficiently on apple silicon macs than docker.

i've been using a sort of version like this... using the apple container fw. http://github.com/apple/container

have you looked into that?