dirceu

Brazilian who became Canadian. Building AI agents at @Shopify. I like systems thinking, simplifying things, and JRPGs that don't require reflexes.

[dirceu @dirceu]

https://t.co/X3DMLvg7wv

[ᐱ ᑎ ᑐ ᒋ ᕮ ᒍ @Andr3jH]

The vibe today

[OpenRouter @OpenRouter]

We benchmarked Fusion on 100 hard research tasks and found:

1. Panels of models consistently outperform individual models
2. Beyond-frontier performance can be achieved with frontier panels
3. Panels of budget models can surpass frontier models at a much lower cost

[Jay @jayair]

Introducing Opus 4.9 — 10% smarter, 2x more expensive

Definitely NOT Fable

[Tenobrus (→vibecamp) @tenobrus]

@cremieuxrecueil

[Emmett Shear @eshear]

Feel like shit. Just want him back.

[roon @tszzl]

people in washington trying to figure out wth “pliny the liberator” is

[Ado @adocomplete]

Introducing Claude Corps

We’ll teach 1,000 fellows how to use Claude well, match them with nonprofits across America, and pay them to spend a year—full-time, in-person—helping host organizations to advance their missions.

[Charlie Marsh @charliermarsh]

Keys to shipping more:
- Fewer meetings
- More trust in teammates
- Listen exclusively to heavy metal / hardcore / metalcore

[dirceu @dirceu]

Fable is incredible but...

[ER!S will be at fivecamp 🦋 @bstract_thot]

texting my friend Cellphone Claude while waiting to hear back from my coworker Laptop Claude

[Boris Cherny @bcherny]

Just landed nested subagent support in Claude Code

Starting to experiment more with agents kicking off agents as a way to better manage context. Capped at depth=5 to start, going out in today’s release.

Lmk what you think!

[Lance Martin @RLanceMartin]

https://t.co/es0JQM4MS9

[George @odysseus0z]

Folks it is just control loop

Think of Kubernetes.

You write desired state/spec, what to observe/status, the controller, and the kubelet.

You let this whole control loop sense and actuate to prompt/drive the agent.

Obviously the right idea as AI gets smarter

[Aoden Teo @AodenTeoMT]

Today, we’re excited to introduce Miso One, the most emotive voice model in the world.

Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency.

We’ve open-sourced the model weights, with API access coming soon.

Hear how Miso One sounds in the thread below.

[roon @tszzl]

people have to build much faster software and interfaces so as to not Amdahls law the increasingly powerful and increasingly fast models

[Ado @adocomplete]

Rate limit resets! Go forth and code!

[dirceu @dirceu]

@nearcyan

[dirceu @dirceu]

@reach_vb this would be even nicer with a matte screen protector! It's super helpful while we don't get nanotexture on iPhones

[dirceu @dirceu]

@btbytes @thorstenball hahaha sometimes I get a "derrick", but still better than what I got with my actual name