Bruno Monteiro

8.7K posts

Bruno Monteiro banner
Bruno Monteiro

Bruno Monteiro

@BrunoMonteiro

Sociologist on paper 📚. Designer by practice 🧑🏻‍💻. Book lover at heart 🖤.

Portugal Katılım Ocak 2007
950 Takip Edilen585 Takipçiler
Sabitlenmiş Tweet
Bruno Monteiro
Bruno Monteiro@BrunoMonteiro·
Pessoas, como gosto de ouvir uns podcasts e gosto de literatura decidi arregaçar as mangas e fazer uma lista com o resultado da intersecção. Enjoy! 🎙️ Podcasts sobre Literatura › buff.ly/2OltyeJ #literatura #podcasts
Bruno Monteiro tweet media
Português
2
2
2
0
Luca Rossi ꩜
Luca Rossi ꩜@lucaronin·
New @tolariamd release! 🔥 This brings native support for Portent.md — you can now just ask your AI agent to audit your knowledge base and suggest improvements! ☘️ Also: • 🧭 Note context menu — right-click notes for faster actions • 🤖 More AI agents — added Kiro, and hardened support for others • 🇧🇾 Belarusian! — added Belarusian translations • ⚡ Faster note windows — opening a note in a separate window is now much faster • 🐛 Bug fixes — just a ton of them! Also merged a lot of PRs from contributors. Thank you for your work guys 🙏
Luca Rossi ꩜ tweet mediaLuca Rossi ꩜ tweet media
Luca Rossi ꩜@lucaronin

Introducing Portent! ☘️ An open-source spec for organizing knowledge bases, for work and life. Since I released @tolariamd, the most recurring questions I have received have not been about the tool, but how to organize information. Portent answers this by providing sane defaults for three things: 1) Types — eight foundational types that fit work and life 2) Relationships — two base types of links, to model ownership and relatedness 3) Lifecycle — how information flows and is operated This is designed to work with or without Tolaria: you can run it on folders, Notion tables, Obsidian, or whatever you like. But of course, all these ideas are first-class citizens in Tolaria. Let me know your thoughts! Website: portent.md Announcement article: refactoring.fm/p/introducing-…

English
5
3
36
4.4K
Bruno Monteiro
Bruno Monteiro@BrunoMonteiro·
@emollick Absolutely. It doesn’t make any sense. I can only atribute it bad product management or talent debt (which is difficult to believe)
English
0
0
0
14
Ethan Mollick
Ethan Mollick@emollick·
The continuing gap between the capabilities of Gemini Pro 3.1 (very good model) and the capabilities of the Gemini app/website is odd. The model can do what Claude/GPT can do, but there is a minimal harness for tools (file creation, research etc), no auditable CoT/actions, manual canvas, etc. The reason this is odd is that Google is trusted by enterprises & has the compute to burn, so a good harness would solve so many of Gemini’s gaps and make it an easier sell to companies. The model can make Office documents, for example, but the harness doesn’t allow it. It could also decide when to use other Google tools (and Google has a lot of very good AI tools) and apply them, taking advantage of the ecosystem, but it doesn’t consistently. I assume something will be coming out here eventually, but the gap with Claude and ChatGPT has only been growing.
English
104
70
1.3K
91.5K
Bruno Monteiro
Bruno Monteiro@BrunoMonteiro·
@rseroter @pwealthydad @geminicli @JackWoth98 You are not only falling back more often to Flash, but unfortunately it can barely be used as a reliable coding tool… it becames IDLE very often, remote function calls that fail… I really want to use it, but it’s impossible.
English
0
0
1
110
Jack Wotherspoon
Jack Wotherspoon@JackWoth98·
Markdown tables in Gemini CLI 🗓️🥇 Just noticed emojis being rendered today! The team has and is making a ton of improvements to the UX in Gemini CLI ✨ A lot more coming and some nice new features too!
English
27
22
253
18.2K
Jean-Marc Denis
Jean-Marc Denis@jmdenisme·
Few updates on Vesper 👇 → Moved to a dedicated site — add it to your homescreen: vesper.pm → Cleaner repo URL: github.com/jmdlab/vesper → Modular clip-based breathing system → Variable-duration assembly (10/15/20 min)
Jean-Marc Denis tweet media
English
1
0
4
2.1K
Bruno Monteiro
Bruno Monteiro@BrunoMonteiro·
@luisjorge Gosto muito de Zweig e, se pensarmos em sentido lato, existe alguma similaridade histórica (pandemia, ruptura na ordem mundial, ascensão do nacionalismo, etc.). A pequena biografia que escreveu sobre Montaigne é um mimo.
Português
1
0
2
178
luis m. jorge
luis m. jorge@luisjorge·
A Áustria do império, a 1ª guerra, Weimar e a ascensão do nazismo, o exílio, relatados por alguém que estava no centro da vida intelectual de um continente e foi um dos seus actores mais tolerantes e humanistas. É um belo livro, que parece ter sido escrito para o nosso tempo.
luis m. jorge tweet media
Português
12
3
90
13.4K
luis m. jorge
luis m. jorge@luisjorge·
Tem oceanos de magma e atmosfera sulfurosa. Chama-se, por enquanto, “L 98-59 d” mas alguns cientistas, por razões misteriosas, estão dar-lhe o petit nom de “Maria João Marques”.
luis m. jorge tweet media
Português
5
0
28
1.3K
Ryan Carson
Ryan Carson@ryancarson·
MY KINGDOM for one agent that can actually do e2e design -> pixel-perfect frontend code (including auth so it can login to the app). I'm currently using @paper + Claude Code + Codex CLI + Codex Mac App + agent-browser + Claude Code Chrome extension + ... It's ridiculous. I really, really, really want one ADE to own all this. Come on people. You literally have billions of dollars collectively in funding to sort this out. I'm working on a @nextjs app - this is literally burned into the weights of the models - not doing something new or novel here. Maybe it's a skill issue on my side. Honestly I doubt it though - I spend 10 hours/day in these tools and I've been coding with agents for 3 years. Part of the problem is that I want the UX to be pixel-perfect, beautiful, and elegant. I'm very opinionated about the design being perfect. Maybe the problem is that I've been a backend developer my whole career, so if I was a front-end developer, maybe all this would be easier. The point is that we need the agents to allow anyone to write perfectly *designed* front end code. Also, to be clear: I have a design system skill. I have clear and concise documentation. I don't have any documentation drift. I don't have bloated agents md files. I'm doing everything correctly, and this is still WAY too freaking hard.
English
40
4
107
14.5K
Bruno Monteiro
Bruno Monteiro@BrunoMonteiro·
@trq212 Hi Thariq 👋 Is there anyone from the Desktop team here? I'm having a really hard time with HTTP 500 errors connecting to claude.ai which make the app unusable
English
0
0
0
13