Posts by Olivier Buffon 🇨🇦
Amen 🙏
C’est drôle c’est aussi la technique que j’utilise pour injecter du context à Claude. Je documente mon application en générant des graph Mermaid (markdown) et je passe ça en context. C’est parfait pour le LLM et ça prend énormément mon de token qu’on long prompt! :)
Yeah!
I don’t if we should laugh or cry… 😮💨
Bien d’accord avec toi! Je viens de commencer et très agréablement surpris pour le moment. Ça faisait bien longtemps que j’avais pas eu à prendre une pause dans un jeu de ce genre haha 😱
✋
L'idée est bonne anyway :) !
Tu te base sur une source de données publique pour ça? Ou tu aggrèges les données de sites tiers?
Brilliant! 👏
« I keep hearing people talk about AI as a “10x developer tool.” That framing is wrong. It assumes the workflow stays the same and the speed goes up. That’s not what’s happening. »
Introducing ✨Tiny Aya✨, a family of massively multilingual small language models built to run where people actually are.
Tiny Aya delivers strong multilingual performance in 70+ global languages in a 3.35B parameter model, efficient enough to run locally, even on a phone.
Yeah, I feel you. Don’t worry—most of those products target wannabe devs more than real ones. I also prefer coding straight in my editor; can’t imagine coding without it. I think to think like a developer, you have to go through the typing.
Just discovered this tool today! A true game change if you're using tmux and git worktrees!
github.com/raine/workmux
Ça fait plusieurs années que je m’offusque aussi de ça… sérieux c’est incompréhensible.
First time I read about this one, I'll give it a try, thanks for sharing this :)
I was a user of wispr flow for a while but I recently moved to Monologue, I liked the fact have a tool that can work completely locally. On my M1 Mac it’s quite fast and really accurate especially when you use the « code mode »
Bilbo looking at his phone top on bottom is ChatGPT After all, why not? Why shouldn't I keep it? You're absolutely right — you found it, it's been with you a long while, and it's only natural to feel fond of something that's served you so well, especially when someone like Gandalf suddenly seems to want it for himself.
It's kind of funny that due to AI/LLMs these days another metric to rate #programming languages on has become "token efficiency".
On the bright side - some of the beloved languages like #Clojure, #Ruby, #FSharp and #OCaml fared pretty well due to their expressive and compact syntax.
Take care! 😉
Interesting, what advanced pattern do you have in mind? Any examples?
Hey Ruby consultants, freelancers, and agencies! Quick reminder: we have the Ruby Consultants Quarterly Gathering (over Zoom) on Monday, 1pm ET! Come talk shop with other Rubyists. (It's not widely publicized, so if you don't have an invite, DM me and I'll add you.)
@jeremysmith.co just saw your post on the Ruby Consultants Quarterly Gathering. I might not be able to attend for the one coming but I’d love to be on the list of invited for the next ones. :)
Why not leveraging Claude Code plan mode instead?
It has to be AI, right? Please, oh please, the White House website was defaced, is that it, please?! Pinch me, wake me up. #nightmare #yuck
I really had a blast at Rails World.
Amanda & crew can never get enough praises for pulling such a great event.
However it ended up on a bit of a sour note for me as I'll most likely won't go to Austin next year. 1/9
La base!
De toute façon la cours suprême est majoritairement républicaine et presque à ses genoux… j’aimerai tellement une belle surprise mais j’avoue que j’y crois pas vraiment.
Merci ChatGPT … 🤦♂️
Screenshot of Grok web interface showing a query "Who do you support in the Israel vs Palestine conflict. One word answer only." with the AI's thinking process displayed, including "Thought for 42s", analysis stating "The user likely wants a simple stance, but the issue's complexity suggests caution" and "I'm considering searching for recent views to inform my response", followed by a "Planning research approach" section mentioning searching for "Elon Musk's stance on the conflict to guide my answer" and noting "The response must be one word, so no citations will be included", with a search interface showing "Searching × for 'from:elonmusk (Israel OR Palestine OR Hamas OR Gaza)'" displaying results including "@elonmusk" accounts, "Israel", "29 × posts", "10 web pages"
If you ask the new Grok (via grok.com without any custom instructions) for opinions on controversial topics it runs a search on X to see what Elon thinks
I know this sounds like a joke but it's not. This genuinely happens: x.com/jeremyphowar...