Show HN: I built an OS that is pure AI • Hacker News Board

evanbarke wrote: post #25

spl757 wrote: post #20

Earlier quoted context omitted.

That's not a solution to the root problem. That is duct tape.

This is built with the paradigm of "don't build for the model of today, build for the model in 6 months" It currently works, which amazes me still, but it will get much better!

[dead]

Re: Show HN: I built an OS that is pure AI

#44

Post by comchangs » Mon, Mar 30, 2026, 7:08 AM UTC

[dead]

Re: Show HN: I built an OS that is pure AI

#45

Post by IxInfra » Mon, Mar 30, 2026, 7:26 PM UTC

spl757 wrote: post #11

How did you solve the problem of hallucinations?

the duct tape framing is fair but the deeper issue is the model has no persistent understanding of the system it's working in. each generation starts from scratch with no memory of prior context or architectural decisions. that's a harder problem than prompt engineering but it's solvable at the infrastructure layer

Re: Show HN: I built an OS that is pure AI

#46

Post by opsdu » Mon, Mar 30, 2026, 7:50 PM UTC

[dead]

Re: Show HN: I built an OS that is pure AI

#47

Post by a3ka » Tue, Mar 31, 2026, 4:43 PM UTC

The WASM sandbox per agent with typed ABI is a really clean isolation model. Most agent runtimes I've seen just throw everything into one process and hope for the best.

Curious about the IPC layer between agents. When agents communicate with each other, is there any access control on what one agent can request from another? Or is it open by default?

In practice the moment you have multiple agents that persist and talk to each other, you need some kind of permission model — otherwise one rogue agent can access everything through a chain of IPC calls. Even if each individual sandbox is secure.

The Rust + WASM combo is solid for this. We use Rust for similar reasons — memory safety matters a lot more when agents run autonomously.

Re: Show HN: I built an OS that is pure AI

#48

Post by citizenpaul » Wed, Apr 01, 2026, 6:51 AM UTC

This is really cool. It reminded me of my first thought for an AI app was a No-Interface crm/order system. I was talking to my bro in sales and all he ever does is complain about what a pain computers are. This takes that idea to the next level.

llms were not quite there at the time maybe ill revisit.

Re: Show HN: I built an OS that is pure AI

#49

Post by citizenpaul » Wed, Apr 01, 2026, 6:56 AM UTC

nextaccountic wrote: post #10

> the UX For this to be practical you really need to build things iteratively and asking the user questions, rather than attempting at one shot half assed ideas Also most people are better explaining details with voice rather than text.

>better with voice.

Ive found most people are not good at explaining details period.

Also how many time have you heard something like.

Blah blah, except, blah, only when, blah, but not that except.......

To the point where they've contradicted themselves several times and made at least two mutually exclusive things true.

Re: Show HN: I built an OS that is pure AI

#50

Post by evanbarke » Wed, Apr 01, 2026, 1:52 PM UTC

citizenpaul wrote: post #48

This is really cool. It reminded me of my first thought for an AI app was a No-Interface crm/order system. I was talking to my bro in sales and all he ever does is complain about what a pain computers are. This takes that idea to the next level. llms were not quite there at the time maybe ill revisit.

That's exactly it! I've absolutely loved the empowered my AI coding has brought me. This is about bringing the same to the end user with no technical skills!