Douglas Taquary 🇧🇷 (@bluesprogrammer) header
Douglas Taquary 🇧🇷 (@bluesprogrammer) profile picture

Apps creator, SwiftUI, KMP, Researcher of AI-assisted coding methodologies, practices, and governance, surfer 🏄🏻‍♂🌊

São Paulo, Brasil
Joined March 2011
Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)Photo by Douglas Taquary 🇧🇷 (@bluesprogrammer)
Após alguns meses de desenvolvimento, o #CrossFitPR App será lançado em breve! 100% SwiftUI! 🤩📊🏋🏽 Fica ligado pra mais novidades! 📱
Finally, after 3 months of development #CrossFitPR App will be released soon! If there any media resource who wants cover release feel free to contact me to get invitation for the TestFlight. 🤩🏋🏽📊📱
1
Douglas Taquary 🇧🇷 retweeted
you can see how cheap this is. and on top of that it's actually useful an ESP32, a tiny screen, a mic, a speaker and a bulb on a breadboard. you talk, it answers, and even follow commands how it works: 1. a small mic module listens, the ESP32 records your voice 2. the screen shows what it's doing: listening, thinking, speaking 3. the voice goes over wi-fi to an AI model, the answer comes back as speech 4. if the answer is a command, the ESP32 switches the light itself the chip is the ears, the face, the mouth and the hands. the brain is a model it calls. all of the hardware is probably under $20
finally! local AI is accessible to everyone. we replaced our massive smart home server with a single $8 ESP32-S3 chip processing voice commands entirely on-device. now anyone can build this. here is the full guide:
14
89
10
782
43,344
Douglas Taquary 🇧🇷 retweeted
finally! local AI is accessible to everyone. we replaced our massive smart home server with a single $8 ESP32-S3 chip processing voice commands entirely on-device. now anyone can build this. here is the full guide:
53
98
33
988
1,880,572
Douglas Taquary 🇧🇷 retweeted
CocoaPods、いよいよ一区切りですね。 2026年12月2日、公式Trunkが読み取り専用に。新規公開は止まりますが、既存Podは取得できるので、今すぐ使えなくなるわけではないようです。 まだCocoaPodsに依存しているところは、早めにSwiftPMへの移行を進めておくとよさそうですね。 swift.org/blog/whats-new-in-…
19
3
75
5,239
Douglas Taquary 🇧🇷 retweeted
Putain, c'est vraiment dingue. On a demandé à Dario Amodei, le CEO d'Anthropic, ce que devrait faire un jeune qui sort du lycée aujourd'hui. Sa réponse : « L'IA sait faire le boulot d'un juriste débutant. Celui d'un analyste financier débutant. Celui d'un consultant junior On ne peut pas nier qu'elle va aussi supprimer des emplois, et sans doute en grand nombre » En quelques minutes, il cite les métiers qui sauteront en premier et LA compétence qui te garde dans la course Sa propre prédiction : 50 % des postes de cols blancs débutants bouleversés d'ici 1 à 5 ans Prompts → Agents → Collègues IA → Travail des juniors fait par l'IA Passer des champs aux usines a pris des générations. Cette fois, l'IA frappe toutes les étapes d'une carrière en même temps Son conseil tient en une ligne : « Évidemment, apprendre à se servir de l'IA » Ceux qui s'y mettent cette année ne seront pas en concurrence avec l'IA : ce sont eux qui la piloteront Tout ce qui suit est gratuit. Commence aujourd'hui : Anthropic - Prompt Engineering Interactive Tutorial : le moyen le plus rapide d'apprendre à diriger un modèle github.com/anthropics/prompt… Anthropic Courses : de ton premier prompt jusqu'au pilotage d'agents github.com/anthropics/course… Anthropic Cookbook : des recettes concrètes à copier dès aujourd'hui github.com/anthropics/anthro… Microsoft - Generative AI for Beginners : 21 leçons, aucun diplôme requis github.com/microsoft/generat… Microsoft - AI Agents for Beginners : construis des agents qui font le boulot de junior à ta place github.com/microsoft/ai-agen… Hugging Face - Agents Course : gratuit et certifiant, de A à Z github.com/huggingface/agent… Google Cloud - Generative AI : les notebooks pratiques signés Google github.com/GoogleCloudPlatfo… OpenAI Cookbook : du code pour chaque tâche courante github.com/openai/openai-coo… DAIR.AI - Prompt Engineering Guide : la référence que tout le monde partage github.com/dair-ai/Prompt-En… Andrej Karpathy - Neural Networks Zero to Hero : pour comprendre ce qu'il y a sous le capot github.com/karpathy/nn-zero-… CrewAI : fais tourner une petite équipe de travailleurs IA github.com/crewAIInc/crewAI Microsoft - AutoGen : mets plusieurs agents sur une même tâche github.com/microsoft/autogen Awesome LLM Apps : des centaines de projets concrets pour apprendre github.com/Shubhamsaboo/awes… DeepLearning.AI - Short Courses : des cours gratuits d'une heure, par ceux qui enseignent le sujet deeplearning.ai/short-course… Coût total : 0 € Pas besoin d'une année d'études de plus pour apprendre ça. Ce qu'il te faut, c'est commencer à dire à l'IA quoi faire 95 % vont décrocher leur diplôme et se battre contre l'IA pour le même poste junior Les 5 % qui apprennent à la piloter cette année manageront les agents qui font ce boulot Enregistre ce post et envoie-le à quelqu'un qui finit ses études cette année
134
1,215
48
5,501
806,123
Douglas Taquary 🇧🇷 retweeted
When we decided to rebuild one of our biggest apps natively, we went back to the drawing board with a basic question: how should a mobile app be built when agents write most of the code?An agent can write code in seconds, but it takes several minutes to test whether it works. So we built Reflex: an agentic-first architecture that lets agents build and verify app behavior across iOS and Android without needing devices or simulators. shopify.engineering/reflex
14
36
1
401
18,302
Douglas Taquary 🇧🇷 retweeted
Replying to @sergedoub
Yes, you can essentially see and interact with the same simulator that River is using on its remote machine. You can see what the it is doing, take control, share it with others, etc. More details here: shopify.engineering/remote-d…
4
34
2,565
Douglas Taquary 🇧🇷 retweeted
The coding interview is dead, at least for my team at Anthropic. I've seen enough to know that it no longer provides signal. I removed it from loops this month. I have a spicy, optimistic take - I think there's an opportunity for junior engineers: felixrieseberg.com/hunger-be…
646
1,561
752
15,617
2,860,385
Douglas Taquary 🇧🇷 retweeted
感谢 github.com/seedds/nxnative 项目。从此,switch 游戏自由了。
67
297
17
3,605
222,083
Douglas Taquary 🇧🇷 retweeted
又找到一个做游戏的开源项目 这个开源项目提供了 74 个游戏开发 Skills,角色移动、关卡设计、存档、打击感都有 而且支持 Godot、Unity、Unreal、Phaser、PixiJS、three.js、Bevy、pygame、LÖVE 和 Roblox 等多平台 武器到手,这下高低得做个游戏试试了 github.com/gamedev-skills/aw…
最近在折腾微信小游戏 用到了部分SKIll 整理了链接,也分享给同样在做小游戏的朋友 AI 游戏生成 /玩法逻辑:higgsfield-game-generation github.com/higgsfield-ai/ski… 游戏引擎:game-engine github.com/github/awesome-co… 多人联机:multiplayer-game github.com/rivet-dev/skills/… 游戏开发:game-developer github.com/Jeffallan/claude-… 界面设计:game-ui-design github.com/omer-metin/skills… 玩法设计:game-design-theory github.com/pluginagentmarket… 操作手感:game-feel github.com/gamedev-skills/aw… 界面交互:game-ui-ux github.com/gamedev-skills/aw… 3D 界面:threejs-game-ui-designer github.com/majidmanzarpour/t… 网页游戏:develop-web-game github.com/openai/skills/tre…
28
322
25
2,146
329,195
Douglas Taquary 🇧🇷 retweeted
Prompt, launcher source and the gotchas I hit are all here. works on any Android TV / Google TV, everything is reversible and feel free to tweak it to your needs :) github.com/Gathin23/tv-vibeh…
110
335
31
6,593
703,963
Douglas Taquary 🇧🇷 retweeted
Vibe coded my parents' TV this afternoon! It was showing a sponsored ad before you could even get to Netflix. Gave Claude Code the model number, it found the TV on wifi, removed 25 Xiaomi packages and wrote a new launcher. Looks like an Apple TV now lol
975
1,698
835
35,926
8,768,345
Douglas Taquary 🇧🇷 retweeted
This is great news again. Swift on the server rocks! 🤘
Google: “[Swift] has matured into a viable systems and cloud language, pairing Rust-like data-race safety with predictable, reference-counted performance.” Announcing their Swift-based cloud SDK for backend services: cloud.google.com/blog/topics…
3
16
164
17,442
Douglas Taquary 🇧🇷 retweeted
FYI Evergrow is fully open source, done with Astra (high) and all on my personal Codex subscription. You can follow along on Github. github.com/Dimillian/Evergro…
13
6
236
30,262
Douglas Taquary 🇧🇷 retweeted
My full talk at the Three.js Conf in Paris! 🇫🇷 24 minutes of Three.js, WebGPU and performance optimization ⚡️
14
38
2
423
15,219
Douglas Taquary 🇧🇷 retweeted
29
115
5
2,407
92,852
Douglas Taquary 🇧🇷 retweeted
I spent 1.6 billion tokens building a full game with GPT-6 ASTRA. Not a demo. A FINISHED, playable game. Here's exactly how to make almost any game with it:
Everything I learned building a full game with GPT 5.6 Astra, start to finish. Long read.
839
509
256
6,722
3,461,015
Douglas Taquary 🇧🇷 retweeted
This is how I work now. Actually it's how almost everyone at @every works. Every workstream has an ongoing thread in Codex. I never make one off chats and I never worry about compaction. There's SO MANY THINGS OpenAI can do to make this better. A few ideas: 1. Folders. Let me group chats together 2. Emoji selector. It's a design bummer but it's visually so much more appealing and easier to find pinned threads 3. Remove the chat bubble icon ya'll just launched. Nothing in the UI should be repetitive like that IMO. 4. Enable me to fork convos much more easily. Those should be worktrees that live inside of each chat like a folder would work. 5. SHARED CHATS with easily forked convos that all have the same context. Killer feature and makes Codex multiplayer. 6. Make HQ a feature. It's my ongoing to-do list but it's just not built for chat. I need a kanban board or something that i can kickoff codex sessions from.
68
18
17
559
93,836