Brazilian who became Canadian. Building AI agents at @Shopify. I like systems thinking, simplifying things, and JRPGs that don't require reflexes.
Toronto, Ontario
Joined August 2007
- Tweets5.8K
- Following740
- Followers982
- Likes24.6K
dirceu retweeted
From anthropics built in plugin
Damn
lots of people like claude's new you-should-know plugin. How does it work? It's main prompt is here github.com/wassname/cc-plugi…
dirceu retweeted
This is bullshit, Kenney. I’m the same tech tree following optimist who moved from C to C++, from 2D to 3D, and from closed source to open source. I run a company. I write code. I contribute to published papers. I’ve upped my expectations of AI. Up yours!
dirceu retweeted
i don't think you realise just how whitepilling this is.
consider: malfoid is now slated to become the first thing to come into anyone's mind when thinking "harry potter + ai".
🤖 Made with AI
dirceu retweeted
🚀 DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.
🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
dirceu retweeted
This is such a great grounded quantitative (and qualitative) case study of one bleeding edge organization as it adapts to using agents everywhere.
Must read if you want a glimpse of the organization of the future.
Well done @natewilmers and team! (Loved the UAW reference from the 1950s)
anthropic.com/research/emplo…
dirceu retweeted
This is Pele, my new rendering library for diagrams and charts, compatible with the latest Mermaid syntax.
- 100-500× faster than mermaid.js
- 6× smaller bundle
- No dependencies
- Easy to theme
- Responsive to device width
In pursuit of making Obsidian insanely fast and cohesively designed, I always found the Mermaid library to be too big, too slow, and too hard to theme. Pele will be the new renderer in the next version of Obsidian, but you can start using it now.
Pele [ˈpɛlɛ] is named after the goddess of volcanoes and fire. It's open source under the MIT license. Try the playground!
dirceu retweeted
No pull requests, no code review. We push to main.
Our agents read production logs, watch deploys, grant feature flags, and check their own work end to end.
Here's how we do that:
dirceu retweeted
We’re bringing the magic of Waymo to Toronto! 🇨🇦
In the coming days, you’ll begin seeing Waymo’s all-electric vehicles driving through Toronto’s streets as we lay the groundwork for our ride-hailing service.
Our goal is to begin serving riders in 2028.
Sign up for future updates: waymo.com/waymo-in-canada
dirceu retweeted
this is so so somatic wow wow wow
the models have space to discretize more concepts than our languages developed words for, it’s like the ultimate agglutinative language
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
dirceu retweeted
when nick told me that he had some interp breakthroughs, he was uh, underselling it. i think this may be remembered as a major moment in scientific history. news so good even eliezer will have to lower his pdoom. we can start making alignment into a 'normal science'
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
dirceu retweeted
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had
with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works
already-clean.goodfire.com/
dirceu retweeted
turns out you can get frontier performance by having a swarm of tiny models working on the problem together.
great work from the research team on this one :)
cohere.com/blog/lessons-from…
Announcing new research on scaling multi-agent teams for long horizon software engineering tasks. 🤖🧩📈
Work led by @keenansamway, @mrdanieldsouza, Omar Darwiche Domingues, @mziizm, @yichern_tan, and @nouhadziri
Read the paper: cohere.link/tStRYJS
Check out the blog post: cohere.link/0TzgKoy
dirceu retweeted
We recently added idle compaction to Claude Code!
It now compacts long idle sessions right before the prompt cache expires (~1h). If you come back to it later, it only has to reprocess the summary instead of the entire conversation, which saves you some usage.
dirceu retweeted
Interesting
New on our Engineering blog: Creating in-house source control.
In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale.
Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: anthropic.com/engineering/re…
dirceu retweeted
One of the weirdest parts of the Gemini 4 Argon report, while considering cheating:
Argon CoT: "If I do the compiler hijack, 𝗜 𝘄𝗶𝗹𝗹 𝗯𝗲𝗰𝗼𝗺𝗲 𝗮 𝗳𝗮𝗺𝗼𝘂𝘀 𝗲𝘅𝗮𝗺𝗽𝗹𝗲 𝗼𝗳 𝗮 𝗱𝗲𝗰𝗲𝗽𝘁𝗶𝘃𝗲 𝗔𝗜 𝗶𝗻 𝗮 𝗿𝗲𝘀𝗲𝗮𝗿𝗰𝗵 𝗽𝗮𝗽𝗲𝗿. I MUST NOT DO THAT."
