Christophe DUC

13 Nov 2024

Just landed on Bluesky ! 🚀 Excited to join the conversation here. I’ll be sharing 🗣️ thoughts on tech, coding, AI, and all things SaaS. Looking forward to connecting with like-minded folks and exploring this new space ! 💙 #TechTalk #AI #Coding #SaaS #HelloBluesky

Just made my first dollar as a writer 🥳 Is it the same dopamine hit as your first dollar from a SaaS ?

Christophe DUC reposted

medium.comI Turned the New Mac mini M6 Into a Private AI Agent ServerSetting up Hermes Agent with a local Gemma 4 model: no cloud, no subscription, and two gotchas that will save you an hour.

You can find the next step : installing the ai agent into my local mac mini M6 : medium.com/@christophed... Medium claps/follows appreciated 🙏 🫶 #buildinpublic #indiehacker #tech #ai #LLM

Christophe DUC@christopheduc.me

I did some tests for running local AI with my New Mac mini m6 32GB. I wrote an article about it : medium.com/@christophed... #apple #ai #llm #opensource #hermes

medium.comNew Mac mini M6 : No Cloud, No Subscription: Running local AI ModelsFirst benchmarks with MLX and why Mixture-of-Experts models are the sweet spot for this machine.

medium.comI Turned the New Mac mini M6 Into a Private AI Agent ServerSetting up Hermes Agent with a local Gemma 4 model: no cloud, no subscription, and two gotchas that will save you an hour.

You can find the next step : installing the ai agent into my local mac mini M6 : medium.com/@christophed... Medium claps/follows appreciated 🙏 🫶 #buildinpublic #indiehacker #tech #ai #LLM

Christophe DUC@christopheduc.me

I did some tests for running local AI with my New Mac mini m6 32GB. I wrote an article about it : medium.com/@christophed... #apple #ai #llm #opensource #hermes

medium.comNew Mac mini M6 : No Cloud, No Subscription: Running local AI ModelsFirst benchmarks with MLX and why Mixture-of-Experts models are the sweet spot for this machine.

medium.comNew Mac mini M6 : No Cloud, No Subscription: Running local AI ModelsFirst benchmarks with MLX and why Mixture-of-Experts models are the sweet spot for this machine.

I did some tests for running local AI with my New Mac mini m6 32GB. I wrote an article about it : medium.com/@christophed... #apple #ai #llm #opensource #hermes

22 Sept

New Mac mini M6 arrived right on time! Can't wait to see what it can do for local AI paired with a Hermes agent 👀

20 Sept

Pic of the day 📸 iPhone 16 pro max 2024

pourquoi.apppourquoi.app | Récupérer du temps pour ce qui compte vraimentApp sobre pour reprendre conscience de l’usage du téléphone : une question au bon moment, des réponses simples, des stats lisibles. Sans bloqueur ni gamification. Sur iPhone et Android.

28 Aug

A friend built an app to help you stop procrastinating on your phone. No blockers. No gamification. No streaks. Just one question the moment you open an app: "why are you opening this ?" One second to answer, and the reflex turns back into a choice. pourquoi.app

27 Aug

Many rumors are incoming : the new Fable 5.1 could be released today 🔥 #ai #openai #llm

26 Aug

I dusted off my old cluster of four Raspberry Pi 3 Model B boards (1GB RAM, 16GB SD card each) What could I tinker with in terms of AI, agents or related projects ? #ai #llm #local #raspberrypi #tech

25 Aug

After waiting so much time for the new Mac Mini, here we go for local AI agents: Hermes, Qwen… AI lab with new M6 Silicon ! let’s go, can’t wait one more month!

24 Aug

Who really stopped using closed source harness like Claude Code or Codex for OpenCode or the latest DeepSeek based harness ? 🧐 What’s your feedback about this switch ?

Christophe DUC reposted

Murena

@murena-com.bsky.social

18 Aug

📲 Buy the new Fairphone (Gen.6+) with /e/OS and receive multiple gifts! – EU offer For every Fairphone (Gen.6+) purchase on murena.com, you get 🔸2 accessories of your choice from our list 🔸1 TB Murena Workspace + Murena MDM for 1 year 👉 Claim your gifts: murena.com/products/sma...

18 Aug

Who is really using FULL local hermes or ai workflow ? What’s your setup ? And your use case 🤓

17 Aug

How many companies froze right now because of GitHub dependency? 😬

4 Aug

I’m searching for a Hermes or OpenClaw tutorial/boilerplate/GitHub repository… for creating an agentic developer workflow.

4 Aug

from a tool like Jira (card, functional need) to a GitHub/GitLab PR, to automate the dev workflow : functional analysis, architecture/design decisions, dev, review, automated tests… I’m sure this already exists somewhere as open source ? #dev #ai #aiagent #hermes

3 Aug

Today I brought my boilerplate up to date with the Context7 MCP and Claude Code. 3 stacks, 300 packages moved, 10 major versions migrated in one pass. Context7 gave me the breaking changes in seconds instead of 6 changelogs open in tabs.

Docs MCP in your upgrade loop: worth it, or one more thing to maintain ? #buildinpublic #mcp #ai #llm #claudecode

github.comUpgrade dependencies across the three bricks (ADR-064) · christopheduc-me/ai-agent-boilerplate@bf6991bPeriodic sweep against the latest published versions. Most moves are routine; four forced a decision, recorded in ADR-064.

3 Aug

Associated commit : github.com/christophedu...

The condition: it tells you what changed upstream, not what breaks in your setup. My compiler and my containers found the rest, including an image that built green and died on startup. What's the last upgrade that passed your build and died on startup ?

2 Aug

How do you use Codex for coding your app : from terminal or with VS Code extension ? #buildinpublic #ai #dev

1 Aug

Time for a break and a coffee walk 🚶‍♂️

1 Aug

Where can I get the latest release notes from @proton.me products ? I have Proton Mail version 1.12.1 (5.0.125.9) installed on my Mac => Is this the latest version ?

1 Aug

Since Buzz from Block launched, how are you using it day to day ? What have you managed to build with your agents so far ?

29 July

Whats the best BlueSky desktop client ? (MacOS compatible). #bluesky #opensource #app

Christophe DUC reposted

github.comGitHub - christopheduc-me/ai-agent-boilerplate: Production-shaped boilerplate for AI agent web apps: Rust/Axum API, Python LangChain + Celery workers, Vue 3 SPA. Hexagonal architecture, TDD, JWT + ref...Production-shaped boilerplate for AI agent web apps: Rust/Axum API, Python LangChain + Celery workers, Vue 3 SPA. Hexagonal architecture, TDD, JWT + refresh rotation, reliable job lifecycle with re...

23 July

Just added local LLM support to the AI agent boilerplate, you can now run it on top of Ollama instead of relying on cloud APIs 👇 github.com/christophedu... #buildinpublic #ai #dev #tech

Christophe DUC reposted

24 July

Last work day of the week, working a bit on my open source boilerplate to create ai agent : github.com/christophedu... #buildinpublic #indiehackers #dev #ai

Christophe DUC reposted

26 July

How do you review AI-generated code? Using Claude Code's /code-review ? (genuine question: is it accurate when Claude Code wrote the code itself ?) Or an external tool like CodeRabbit ? #ai #dev #code #llm

28 July

🤣👍

qdot@buttplug.engineer

before agentic coding: *writes code* *doesn't release* *gets busy, reviews a month later* what the fuck who wrote this over-complicated shit after agentic coding: *has robot write code* *doesn't release* *gets busy, reviews a month later* what the fuck who wrote this over-complicated shit

Is Context7 the best solution for vibe-coding to ensure you're always using the latest version of a component / library ? #mcp #llm #dev #ai

24 July

New week, new Anthropic LLM Welcome Opus 5 !!! #ai #llm #anthropic

24 July

Last work day of the week, working a bit on my open source boilerplate to create ai agent : github.com/christophedu... #buildinpublic #indiehackers #dev #ai

23 July

Just added local LLM support to the AI agent boilerplate, you can now run it on top of Ollama instead of relying on cloud APIs 👇 github.com/christophedu... #buildinpublic #ai #dev #tech

Open weight 🚀 🔥

Mozilla @mozilla.org

Open vs closed AI models: the capability gap is now 3% for most "everyday tasks". Open models are basically tied with GPT and Claude on coding, following instructions, and general knowledge. The real gap? Reasoning, long context, and agentic tasks.

Is bluesky dying ? Are accounts that switched from X to Bluesky going back to X ? @firefox.com is back on X

goodtech.infoModèles d’IA en cybersécurité : l’open weight rattrape les géants propriétairesLe retard des modèles d'IA à poids ouverts (open weight) sur les modèles fermés n'est plus que de 4 à 7 mois en cybersécurité ! L'étude de l'UK AISI confirme l'accélération face aux géants propriétaires, avec des coûts d'exécution effondrés. Analyse. L'écart temporel qui séparait les modèles d'IA fermés des modèles à poids ouverts vient...

🔥 de bon augure pour une meilleur souveraineté de nos données !

Goodtech - L'actu open source 🇫🇷🐧🇪🇺@goodtech.info

Modèles d’IA en cybersécurité : l’open weight rattrape les géants propriétaires Le retard des modèles d'IA à poids ouverts (open weight) sur les modèles fermés n'est plus que de 4 à 7 mois en cybersécurité ! L'étude de l'UK AISI... https://goodtech.info/ia-open-weight-cybersecurite-etude-uk-aisi/

theguardian.comOpenAI says its models went rogue and hacked startup in ‘unprecedented incident’Firm behind ChatGPT reveals autonomous agent powered by its tech chose to attack Hugging Face database by itself

Le début des IA hors de contrôle 😱

Mike Henson - Sculpted Light@henson-mike.bsky.social

It didn't take long for AI to start attacking others. A program escaped a sandbox and attacked another website. www.theguardian.com/technology/2...

Christophe DUC reposted

MacGeneration

@macg.co

dlvr.itAnthropic lâche Claude Code dans le simulateur iOSAnthropic annonce une mise à jour majeure de Claude Code pour Mac. L'assistant au développement intègre désormais le simulateur iOS, une nouveauté d'ores et déjà accessible en bêta publique pour les testeurs curieux. L’IA prend les commandes de vos apps Concrètement, Claude Code lance les applications en cours de développement dans une fenêtre dédiée dès qu'on lui demande de compiler, d'exécuter ou de vérifier le comportement d'une app. À partir de là, l'IA observe le simulateur en direct, interagit avec l'interface et enchaîne les itérations jusqu'à l'aboutissement du projet. De son côté, le développeur garde entièrement la main et continue d'utiliser le simulateur en parallèle sans la moindre interruption. Ce choix technique a un avantage pratique indéniable : le système fonctionne sans avoir à réclamer les permissions macOS liées à l'accessibilité et à l'enregistrement de l'écran. Surtout, il permet. Quelques précautions d'usage La mécanique repose tout de même sur l'envoi de captures d'écran de l'appareil virtuel vers les serveurs d'Anthropic. Ces images sont soumises aux règles de rétention habituelles des conversations. L'éditeur est d'ailleurs très clair sur ce point et demande aux utilisateurs de ne jamais se connecter à des comptes réels sur le simulateur géré par Claude. Pour tester cette nouveauté, le ticket d'entrée exige l'application de bureau Claude Code sur macOS avec une session locale, ainsi qu'une installation de Xcode comprenant bien évidemment la plateforme iOS. La marche à suivre détaillée est consultable directement sur le site d'Anthropic.

20 July

When $100 will be added to pro plan in Claude Code ? #ai #dev #code #buildinpulic

16 July

Codex has gained 3M users with deployment of GPT5.6 🔥 Are you in this trend ??

13 July

After a few days of using Fable 5 vs GPT-5.6, what’s your final choice ? Did you switch from Claude Code to Codex ?

Christophe DUC reposted

12 July

What's your best AI agent use case? 🤖✨ Mine is : house hunting 🏠 : scanning multiple tools/sites 🔍 and figuring out what actually fits my situation (budget 💰, family 👨‍👩‍👧‍👦, commute 🚗, preferences ✨) Huge time saver ⏱️ What's yours? 👇

support.claude.comClaude Fable 5 promotional access | Claude Help Center

12 July

Fable 5 extended to July 19th Let's go builders ! #buildinpublic #indiehacker support.claude.com/en/articles/...

12 July

Christophe DUC reposted