Brazilian who became Canadian. Building AI agents at @Shopify. I like systems thinking, simplifying things, and JRPGs that don't require reflexes.
Joined August 2007
- Tweets 5,645
- Following 507
- Followers 984
- Likes 22,382
217 Photos and videos
dirceu retweeted
every time when gpt 5.5 can't implement my ML ideas after I learned what they did to fable
1
4
69
3,910
dirceu retweeted
None of this was some weeks long back and forth. I was at Anthropic's HQ on Friday reporting when this all unfolded. Dario is not at a wellness retreat. The Feds seemed to be scrambling to try and make an example of Anthropic again.
This is not technical. It's petty.
37
121
1,897
226,473
dirceu retweeted
Jun 13
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
5
32
1,140
178,175
dirceu retweeted
Jun 13
Feel like shit. Just want him back.
Claude Fable 5 has been out for a couple of days. Some projects people have already built with it:
66
118
3,673
195,465
dirceu retweeted
Jun 11
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.
5
6
51
3,397
dirceu retweeted
Jun 11
Keys to shipping more:
- Fewer meetings
- More trust in teammates
- Listen exclusively to heavy metal / hardcore / metalcore
18
26
335
14,872
dirceu retweeted
texting my friend Cellphone Claude while waiting to hear back from my coworker Laptop Claude
1
3
41
917
dirceu retweeted
Jun 9
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!
503
294
5,642
470,739
dirceu retweeted
Jun 9
102
761
6,008
2,170,922
dirceu retweeted
Jun 8
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
Jun 7
Here’s your monthly reminder that you shouldn’t be prompting coding agents anymore.
You should be designing loops that prompt your agents.
33
29
443
80,202
dirceu retweeted
Jun 3
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.
559
721
9,798
5,031,066
dirceu retweeted
Jun 1
Rate limit resets! Go forth and code!
Jun 1
We've reset 5-hour and weekly rate limits for all users on Pro and Max plans.
We fixed an issue that caused some Claude Code sessions to spawn excessive parallel subagents, burning through usage faster than expected.
6
5
118
11,352
dirceu retweeted
May 30
What stage in the cycle is it when the Uber driver Claudes while the Tesla drives
179
263
6,499
432,239
Excited to share our most powerful new Claude Code feature: dynamic workflows!
Mention "workflow" in a prompt and Claude will dynamically create an orchestration plan that it strictly follows, allowing you to confidently trust that every stage happens in the right order even across 100s of agents.
353
827
7,796
1,680,949