Guillaume "G/" Moigneu @guillaume.id · 21/07/2026Agent routers coordinate model choice, tool execution, and verification across a workflow. Price is one routing input alongside completion rate, latency, available context, and verification cost. That means the router needs to understand the work it is scheduling. #ai #agents #router 120
Guillaume "G/" Moigneu @guillaume.id · 17/07/2026An LLM can challenge your reasoning or rationalize the decision you already wanted. The difference is process. I built Pressure-test decisions to surface assumptions, test uncertainty, and end with a concrete action. I still make the call. The skill forces me to show my work. 100
Guillaume "G/" Moigneu @guillaume.id · 13/07/2026My YouTube research agent has seven workflow steps. Only two stages use an LLM. Code handles fetching, filtering, ranking, caching, and persistence. Models extract transcript evidence and synthesize patterns. Put model calls where ambiguity creates value. 000
Guillaume "G/" Moigneu @guillaume.id · 12/06/2026Really good write-up by Fabien Potencier. Challenges ahead for organizations to fully adopt AI development. Best practices, governance, cost-control, etc. We are all trying to adapt without a clear path, which this article tries to map out. upsun.com/blog/8-stages-ai-engineer… 020
Guillaume "G/" Moigneu @guillaume.id · 09/06/20266 months running my own AI personal agent and this weekend I hit a wall. Nothing beats strongly typed structured data. Markdown-only agents are painful. Slow, dozens of tool calls, tokens burning for nothing. Do I really need to wait 70 seconds to flip a task from In Progress to Done? 110
Guillaume "G/" Moigneu @guillaume.id · 25/05/2026A great idea inspired by conventional commits: Conventional Comments conventionalcomments.org It's so true that sometimes I don't even know what to do with a comment on a Google Doc. Acknowledge, reply or just close? This would help! 000
Guillaume "G/" Moigneu @guillaume.id · 24/05/2026What are you working on this long weeekend? I've just revamped my AI assistant. After trying so many solutions (Hermes, graphs, etc.) I am back to a way simpler method. Pi + local gemma 4 + markdown files + qmd + Obsidian. Tasks management, journal and my knowledge aggregations all fit in there. 1220
Guillaume "G/" Moigneu @guillaume.id · 27/02/2026I wanted to build a lead-catching LLM based chatbot but I had to figure out which defenses were actually worth the complexity. A Chevrolet chatbot agreed to sell a $76K Tahoe for $1 after one prompt injection. guillaume.id/blog/defendi...guillaume.idDefending LLM chatbots against prompt injection and topic driftPractical defenses for LLM chatbots against prompt injection and topic drift, including system-prompt hardening, input validation, output filtering, topic control, and pragmatic architecture choices. 100
Guillaume "G/" Moigneu @guillaume.id · 23/02/2026Quickbit: If you're struggling defining priorities and goals (as a person, a company), take a look at Daniel Miessler's Telos framework. Spent the last hour talking to my laptop to build it! It really helps. github.com/danielmiessl...github.comGitHub - danielmiessler/Telos: Telos is an open-sourced framework for creating Deep Context about things that matter to humans.Telos is an open-sourced framework for creating Deep Context about things that matter to humans. - danielmiessler/Telos 000
Guillaume "G/" Moigneu @guillaume.id · 23/02/2026Your agents.md is probably hurting more than it helps. A new ETH Zurich study tested coding agents across hundreds of real GitHub issues and found that LLM-generated context files reduced success rates by 3% while adding 20% to inference costs.agents.mdAGENTS.mdAGENTS.md is a simple, open format for guiding coding agents. Think of it as a README for agents. 100
Guillaume "G/" Moigneu @guillaume.id · 21/02/2026I love initiatives like Claude Code Security (even if it's gated for now). But I'm also terrified of them. claude.com/solutions/cl...claude.comClaude Code Security | Anthropic by ClaudeFrom scan to fix, seamlessly. Claude scans your codebase for vulnerabilities, validates findings, and recommends patches you can review and approve. 200
Guillaume "G/" Moigneu @guillaume.id · 20/02/2026Average typing speed: 40 WPM. Conversational speech: 130-150 WPM. Your fingers literally can't keep up with your brain. Voice typing fixes that gap. SuperWhisper nails this on macOS. Press a hotkey, talk, text appears. Accurate, offline, fast. But it's Mac-only with no Linux port planned. 110
Guillaume "G/" Moigneu @guillaume.id · 19/02/2026I am not a big fan of OpenClaw (yet) but I find tremendous value in automating simple tasks. I've worked yesterday and my own terminal based assistant: n6. In honor of the beloved Caprica Six. Extensible python terminal utility wrapping Claude. github.com/gmoigneu/n6 000
Guillaume "G/" Moigneu @guillaume.id · 18/02/2026I ran react-doctor on a real production codebase. 88 out of 100. 4 errors across 139 files. Better than I expected and the 4 errors are exactly the kind that bite you in production. 100
Guillaume "G/" Moigneu @guillaume.id · 18/02/2026I'm starting a new AI Weekly series. I was doing that for my own needs but I think it's worth sharing. If you have any good source to add to my tracker let me know! www.linkedin.com/pulse/weekly...linkedin.comWeekly AI Review - 2026-02-17Anthropic closed a staggering $30 billion Series G at a $380 billion valuation. The second-largest venture deal in history as Claude Code's revenue doubled to $2. 000
Guillaume "G/" Moigneu @guillaume.id · 18/02/2026My personal take on how to make coding agents reliable. For me it's all about verification. The limit isn’t the AI. It’s your infrastructure. Build the verification layer, and the autonomy follows. The full article: devcenter.upsun.com/posts/making...devcenter.upsun.comMaking coding agents (Claude Code, Codex, etc.) reliableThe bottleneck for AI coding agents isn't model capability. It's your verification infrastructure. Here's how to fix that. 110
Guillaume "G/" Moigneu @guillaume.id · 11/02/2026You know that moment when Claude forgets you use pnpm? Again. For the third time today. I got tired of repeating myself. And then I found napkin. 110
Guillaume "G/" Moigneu @guillaume.id · 10/02/2026If you want the slides from my hashtag#AIDay talk about making coding agents reliable, here you go: guillaume.id/pdfs/2026-02... And the 8 pillars verification checklist: gist.github.com/gmoigneu/a96... Thank you Anne-Sophie Norca from dotAI by dotConferences for organizing this! 000
Guillaume "G/" Moigneu @guillaume.id · 10/02/2026What primitives will replace human authorship and review as the foundation of trust? Teams will track "code reading coverage" metrics. But here's the kicker: they'll strategically drive it DOWN in safe areas. 110
Guillaume "G/" Moigneu @guillaume.id · 06/02/2026Just spent way too long nerding out over Claude Opus 4.6 and honestly? feels like a real inflection point for how we work with massive codebases 🤔 #ai #claude #opus #coding 100
Reposted by Guillaume "G/" MoigneuUpsun @upsun.com · 05/02/2026We’re heading to #AIDay2026! 🤖 Guillaume Moigneu will be on stage talking coding agent readiness. Can't attend? Don't worry, the tech track will be livestreamed 👀 Sign-up here: luma.com/dotAI-techtr... 📍 Paris, France | ⏰ 12:00–12:15 pm CET 👉 ai-day.org/programme/ #AIDay2026 #Upsun #AIEngineering 001
Guillaume "G/" Moigneu @guillaume.id · 06/02/2026Discussing with industry old timers friends yesterday we came up to the same conclusion. Everything is so exciting right now like it was in 1999. At the time I was discovering PHP and started to publish a lot of different projects with my trusty Dreamweaver. But I was feeling so empowered. 110
Guillaume "G/" Moigneu @guillaume.id · 14/04/2025I've always been an advocate of data privacy. And even if we have to put ourselves for professional reasons, we always need to be mindful of the potential risks of doing it. Check out Carole Cadwalladr talk at TED. Worth every second of your time! www.ted.com/talks/carole...ted.comThis is what a digital coup looks like“We are watching the collapse of the international order in real time, and this is just the start,” says investigative journalist Carole Cadwalladr. In a searing talk, she decries the rise of the “bro... 020
Guillaume "G/" Moigneu @guillaume.id · 17/02/2025Hello everyone! I wanted to share some thoughts on JD Vance's recent speech at the France AI Summit. I'm really concerned about his stance on regulation. #AISafety #AIRegulation #FranceAISummit #AIEthics #ProfitWithPurpose #AI 111
Guillaume "G/" Moigneu @guillaume.id · 02/02/2025🔥 Vous êtes invité(e) à notre petit-déjeuner pour découvrir comment la durabilité crée un avantage concurrentiel et attire les investissements dans l'écosystème de l'IA⚡️ brnw.ch/21wQitQ 📅 Date: 11 February, 2025 🕗 Time: 09:00 - 11:00 AM 📍 Location: Digital Village Paris 010
Guillaume "G/" Moigneu @guillaume.id · 27/01/2025If you are in Paris for the French AI Summit on Feb 11th, hang around with us for breakfast while we discuss how we can build AI-focused startups and make sure they are as sustainable as we can. A massive challenge for the years to come! #AI #Paris #Sustainability upsun.com/sustainable-...upsun.comBreakfast round-table: The Sustainable Edge: How AI Startups Win VC Funding | Side event of France AI Action Summit 2025Join top VCs and AI founders at France AI Action Summit 2025's exclusive breakfast to learn how sustainability drives competitive advantage and attracts investment in the AI ecosystem. An official sid... 022
Guillaume "G/" Moigneu @guillaume.id · 20/01/2025🚨 Google just dropped Vertex AI RAG Engine (Jan 2025) to help enterprises bridge the gap between flashy LLM demos and actual production use. The reality is most companies struggle with RAG implementation - this is their solution. #AI #MLOps 100
Guillaume "G/" Moigneu @guillaume.id · 20/01/2025Just published a quick article on my eslint / prettier setup for Cursor or VSCode. Have consistent coding rules every time, automagically. dev.to/gmoigneu/set... #webdev #typescript #vscodedev.toSetting Up a Rock-Solid Typescript React Project with ESLint and PrettierA practical guide to setting up a modern TypeScript React project with automated code formatting and quality checks. Learn how to configure ESLint and Prettier, set up VS Code for optimal development,... 010
Guillaume "G/" Moigneu @guillaume.id · 20/01/2025Why I switched from #MySQL to #PostgreSQL - a thread on my database journey 🔄 After years of defaulting to MySQL for every project, I finally made the switch to PostgreSQL. Here's why it was one of the best technical decisions I've made... 🚀 110
Guillaume "G/" Moigneu @guillaume.id · 20/01/2025Cursor is now running commands and parsing the output. If it fails, it adds logging to try to understand what's going on... This editor is changing the way I develop every day. Oh and they raised 105M ... #webdev #ai 000
Guillaume "G/" Moigneu @guillaume.id · 09/01/2025Quoting Yann Leonardi here: "People on LinkedIn don't like what they like, but the content that will reinforce who they want us to think they are.". I love it. This is one of the reasons LinkedIn is a weird place to hang around. [Video in French]youtube.comPourquoi LinkedIn est si BIZARRE ?YouTube video by Yann Leonardi 011
Guillaume "G/" Moigneu @guillaume.id · 05/01/2025Who remembers Gateway 2000? My first real machine... Pentium 120Mhz. I played Doom like crazy on this thing! 000
Reposted by Guillaume "G/" MoigneuDr. Julie Gurner @drgurner.bsky.social · 24/12/2024The struggle is real. 7781031938
Guillaume "G/" Moigneu @guillaume.id · 23/12/2024I guess all the wannabe onlyfans millionaires just discovered BlueSky and the #ai hashtags… my feed is just full of these nowadays. Guess we need new ones for real discussions. 010
Guillaume "G/" Moigneu @guillaume.id · 15/12/2024The #UHC CEO story has now provided more coverage than they ever did. 010
Guillaume "G/" Moigneu @guillaume.id · 14/12/2024Good coffee. Good music. Some code. Love these #productive Saturday mornings. 000
Guillaume "G/" Moigneu @guillaume.id · 13/12/2024This picture tells a lot. AI is not the issue. Heartless CEO’s that are proud of putting up campaigns like this are. Add crocs and a new president and we’re not far away from Idiocracy. 110
Guillaume "G/" Moigneu @guillaume.id · 08/12/2024Finally back home from #SymfonyCon. Always so many incredible people there. See you in Amsterdam next year! A huge shoutout to the @upsun.com team for the organization and the talks. 🤗 020
Guillaume "G/" Moigneu @guillaume.id · 05/12/2024And it’s done. How to leverage Transformers in PHP to run Machine Learning models on your app. #SymfonyCon 070
Guillaume "G/" Moigneu @guillaume.id · 05/12/2024Presenting at #SymfonyCon. Let’s hope the gods of PHP and machine learning will be in my favor. 040
Guillaume "G/" Moigneu @guillaume.id · 30/11/2024#BlackFriday is an amazing reminder on how many companies handle your data. #privacy It’s time for a fall cleaning once again. 000
Guillaume "G/" Moigneu @guillaume.id · 29/11/2024Nearly time for #Symfonycon in Vienna! Get a warm coat with a trdelnyk and join us next week! 000
Guillaume "G/" Moigneu @guillaume.id · 29/11/2024Is llmstxt the new #SEO? Let’s have a go at it. llmstxt.orgllmstxt.orgThe /llms.txt file – llms-txtA proposal to standardise on using an /llms.txt file to provide information to help LLMs use a website at inference time. 000
Guillaume "G/" Moigneu @guillaume.id · 28/11/2024Just developed an iOS app in two hours having coffee on the beach. Thanks to @anthropic.com and Cursor. Can’t believe I’m not struggling anymore with Swift. 010
Guillaume "G/" Moigneu @guillaume.id · 28/11/2024Let’s all pray for #sysadmin folks on call tomorrow. #blackfriday. Be strong. May the force be with y’all. @upsun.com 010
Reposted by Guillaume "G/" MoigneuUpsun @upsun.com · 26/11/2024Get your #SymfonyCon Vienna 2024 schedule ready! 🚀 AI enthusiasts and developers 👀 learn to implement ML inference in @symfony.com apps with Guillaume Moigneu. 📍Room: Track Upsun & Smile ⏰ When: Thursday, Dec 5 at 11:10 – 11:45 AM See you there 👉 brnw.ch/21wOZKF 031