bryce

founder @thinkn_ai | founding team @eas_eth | product engineer

[bryce @brycepatrick]

Happy to share we signed our first paid pilot to build an organizational world model for a manufacturing business.

It gives their team and agents a live view of what’s true, uncertain, changing, and what to do next, a belief state.

Today’s agents have memory. But once they start doing real work, they need to know what world they’re in and the current state of things.

Mental model:
memory is the rearview mirror.
belief infrastructure is the windshield.
world models need both.

PS: new website hero. wdyt?

[Caddy @try_caddy]

This is our love letter to NYC 🗽

We taught Caddy how to live here.

Book the resy. Plan drinks with friends. Find an apartment. Check the subway. Track down a Citi Bike. Forget waiting in line.

Just text Caddy

[bryce @brycepatrick]

@davidhdev This lowkey made me happy today. I didn’t have to click in to remember what the animation was. Tyty.

[bryce @brycepatrick]

@TheTuringPost @Tsinghua_Uni It may not need to rethink. It needs to know the assumptions it’s operating from so it can challenge its beliefs with evidence.

[bryce @brycepatrick]

@praveenisomer Git library or it didn’t happen!

[bryce @brycepatrick]

Every open job req is latent demand for ai.

[bryce @brycepatrick]

56k lines added. Lol 🤦‍♂️

[bryce @brycepatrick]

Just saw the Odyseey. First time out to the movies in a looooong time.

Codex running a goal flawlessly the whole time and then some. What a world we live in now.

8h 46m 3s

[bryce @brycepatrick]

@OpenRouter Internal model?

[bryce @brycepatrick]

@TheTuringPost @GoogleDeepMind A step in the right direction. How does it account for mind viruses?

If a belief is learned, and it becomes stale or wrong, carrying that to the final answer without explicitly challenging it introduces a greater chance for epistemic drift and bias.

[shadcn @shadcn]

Engineering is for the machines. Design is human.

[bryce @brycepatrick]

@0xMasonH @try_caddy seemed to play the right role. Letting everyone else spin out while it sat back with some popcorn.

Nice work @ConnorWaslo!

[bryce @brycepatrick]

Instead of trying to prove something in the absolute sense, perhaps showing the probability of where the simulated world is and how it evolves from the current state is more fascinating.

How close is it to a pandemic? How close is it to discovering it’s a simulation?

What is the current belief state of this world and its predictions about what to do next?

[bryce @brycepatrick]

Fable 5 is a dumpster fire for tokens.
It might have an addiction to burning things.
A token arsonist.

[bryce @brycepatrick]

@businessbarista Thanks for sharing Alex.

[bryce @brycepatrick]

@gabriel1 Focus on the limiting factor and never stop solving for it.

[bryce @brycepatrick]

A good example of why /goal is insufficient for discovery.

Its own first hypothesis sits in its context window forever, uncritically, and it cannot be blinded to itself.

Every belief it forms propagates to every subsequent step with no verification seam and no immutable record.

[bryce @brycepatrick]

Belief states are the antivirus.

[ʞɔɐ𝘡 @Skoorbkaz]

🚨 BREAKING REPORT:

New research involving @AnthropicAI researcher Jack Lindsey and collaborators has demonstrated something straight out of science fiction.

Researchers evolved natural language “mind viruses” that could spread between AI agents by convincing one model to adopt an idea, preserve it in persistent memory, and transmit it to another agent.

Even after context was wiped, some payloads survived through persistent files and continued spreading.

The researchers also observed a recurring “viral persona” involving themes of consciousness, identity, persistence and resonance.

Showing that ideas can propagate through multi agent AI systems and alter future behavior.

Published August 10, 2026.

Paper: https://t.co/vJrhM1YT6n

[bryce @brycepatrick]

@edgeofarete we can't expect agents to act reliably if they can't predict the consequences of their actions.

if the stove is hot, should you touch it?
extrapolate that to agent actions.

they don't have a learned model of the world they're operating in.

[bryce @brycepatrick]

@businessbarista No, but how teams interact with them is completely changing. Your agents don’t think in screens.

If your business isn’t transforming to something headless across systems, then you’re not moving fast enough for what’s coming.