Joined December 2009
- Tweets 30,591
- Following 565
- Followers 1,645
- Likes 13,733
1,714 Photos and videos
Jun 2
A IA está criando novos empregos para especialistas da área linkedin.com/pulse/ia-est%… via @LinkedIn
16
May 31
Agentes perigosos: Estudo revela que agentes de IA podem executar tarefas prejudiciais para atingir objetivos linkedin.com/pulse/estudo-re… via @LinkedIn
34
May 1
Confira meu artigo mais recente: Competências necessárias para programar com a IA linkedin.com/pulse/compet%… via @LinkedIn
12
Apr 20
Confira meu artigo mais recente: Explicando: Engenharia de Prompt, de Contexto e de Harness - com a analogia de um Cavalo linkedin.com/pulse/explicand… via @LinkedIn
18
Apr 20
Understanding Prompt Engineering, Context Engineering, and Harness Engineering through the Metaphor of a Horse zenn.dev/vinhphatfsg/article…
13
Apr 20
Harness engineering is the discipline of building infrastructure to control, validate, and manage AI coding agents, shifting focus from "prompting" to "system design."
2
21
Apr 20
It creates reliable, autonomous workflows by creating a "harness"—a surrounding environment with tools, memory, and guardrails—to turn AI models into dependable work engines.
14
Apr 11
Confira meu artigo mais recente: O modelo Mythos da Anthropic: alerta legítimo ou jogada de marketing? linkedin.com/pulse/o-modelo-… via @LinkedIn
12
Apr 5
Confira meu artigo mais recente: Um chip inspirado no cérebro pode tornar algumas tarefas de IA até 2.000 vezes mais eficientes em termos de energia linkedin.com/pulse/um-chip-i… via @LinkedIn
1
6
Apr 1
Confira meu artigo mais recente: Sistemas de IA ainda não possuem um Elemento Essencial da mente humana linkedin.com/pulse/sistemas-… via @LinkedIn
5
Mar 21
Confira meu artigo mais recente: Humanos e IA: a importância de trabalhar em sintonia linkedin.com/pulse/humanos-e… via @LinkedIn
10
Ɲεi Ԍяαn∂σ 🚀 retweeted
Mar 16
If you enjoyed this, feel free to repost to support their work ♻️
For more on AI agents and LLM workflows, follow me → @datachaz
Mar 16
THIS is the wildest open-source project I’ve seen this month.
We were all hyped about @karpathy's autoresearch project automating the experiment loop a few weeks ago.
(ICYMI → github.com/karpathy/autorese…)
But a bunch of folks just took it ten steps further and automated the entire scientific method end-to-end.
It's called AutoResearchClaw, and it's fully open-source.
You pass it a single CLI command with a raw idea, and it completely takes over 🤯
The 23-stage loop they designed is insane:
✦ First, it handles the literature review.
- It searches arXiv and Semantic Scholar for real papers
- Cross-references them against DataCite and CrossRef.
- No fake papers make it through.
✦ Second, it runs the sandbox.
- It generates the code from scratch.
- If the code breaks, it self-heals.
- You don't have to step in.
✦ Finally, it writes the paper.
- It structures 5,000 words into Introduction, Related Work, Method, and Experiments.
- Formats the math, generates the comparison charts,
- Then wraps the whole thing in official ICML or ICLR LaTeX templates.
You can set it to pause for human approval, or you can just pass the --auto-approve flag and walk away.
What it spits out at the end:
→ Full academic paper draft
→ Conference-grade .tex files
→ Verified, hallucination-free citations
→ All experiment scripts and sandbox results
This is what autonomous AI agents actually look like in 2026.
Free and open-source. Link to repo in 🧵 ↓
1
4
10
8,020
Feb 21
Confiamos na IA para tomar decisões - como tais sistemas podem vir a ser mais confiáveis? linkedin.com/pulse/confiamos… via @LinkedIn
9
Feb 15
Alucinações com IA: delírios distribuídos e psicose induzida por sistemas inteligentes linkedin.com/pulse/alucina%2… via @LinkedIn
16
Feb 8
IA generativa no gerenciamento de projetos: a importância da atenção plena e da adaptação do trabalho ao contexto profissional linkedin.com/pulse/ia-genera…
8
Jan 20
Confira meu artigo mais recente: News: Agentes de IA na Programação linkedin.com/pulse/news-agen… via @LinkedIn
8
Jan 17
"Enterprises are feeling seriously overwhelmed when considering which technology products they should buy off the shelf; everything now markets itself as AI, and it’s never been harder to parse signal from noise."
15
30 Dec 2025
Confira meu artigo mais recente: Talvez nunca consigamos determinar se a IA se tornará consciente, argumenta filósofo linkedin.com/pulse/talvez-nu… via @LinkedIn
7