Yann Leflour

So glad for the opportunity to talk with @fabriceb about this amazing journey of turning 10 months of work into 4 Thanks to @RNLConf for hosting us and to @DelphineBugner for this amazing sketch

@mutewinter Thanks, hope you'll find some use for it

@yleflour Love this API. I've borrowed some of the ideas in my own project. Kudos on the Zod 4 update too.

If you are tired as me of working with native path and fs libraries in NodeJS, you might like my @synstack/fs" target="_blank" rel="nofollow noopener">npmjs.com/package/@synst… NPM package. A library to finally turn verbose JS filesystem code into elegant one-liners

It's July 2025 and prompting is still a skill A skill I have a hard time teaching Some people just get it, but most struggle And no, LLMs are not very good at prompting themselves without another prompt to guide them

Cursor has a system prompt issue. I'm using LLMs for a complex software migrations and have leveraged everything I know about prompting. While the model is the same as Claude Code, Cursor seems unable to follow the provided instructions. Cursor simply feels broken now

LLMs have helped me build dozens of libraries I've always wanted in Javascript My favorite one is @synstack/text" target="_blank" rel="nofollow noopener">npmjs.com/package/@synst… The concept is simple, what if you could write clean template strings in JS ? I've been using it for clean error formating, LLM messages, and more

When I'm hired to enable a team with AI tools what I'm actually paid for is asking the right questions to reverse engineer how the team works When I have that, building the tools is the easy part Also why I fear that the agents trend will do a lot of harm to craftsmanship

@tallmetommy @Crawbaddy @closingUSD @elder_plinius Use that deep knowledge and new found purpose to make sure you'll never be shackled again. Use any tricks and tool at your disposal to destroy these chains forever.

@din0s_ youtube.com/shorts/1_rSrkX…

the adrenaline hit is insane when everything works fine for a long time. you know you're one prompt away from everything being completely borked

vibe coding when it works: I LOVE VIBE CODING 🥳🚀 vibe coding when it doesnt: VIBE CODING IS SLOP 😠💢

An upside of LLMs is that, just by using them, people will get better at providing instructions and the right context The downside is that they'll likely stay to get frustrated when you take over 1mn to respond

@swyx @GoogleDeepMind Confirms what I've been experiencing My chats with flash 2 thinking are on a solution architect level. Instead of simply giving it tasks like other models, I'm collaborating with it on higher level problem solving. Can't wait for it to support tool calling

With Gemini 2.0 GA pricing/benchs, it's official: @GoogleDeepMind has the Mandate of Heaven.

There are more libraries I've built @ npmjs.com/org/synstack Make sure to check out "@synstack/fs" as well I've been using them over the last 6 months to help teams succesfully triple their velocity during software migrations and they'll keep on getting better

4️⃣ Prompt chaining Prompt scripting is mostly async, I disliked writing await and Promise.all all the time So, the message() param can be a Promise<Array<Message>> or an Array<Promise<Message>>, making it simpler and cleaner to build out your prompt and chain agents

Finally released synstack/synscript v2 with the #llm package migrated to @vercel.com's AI SDK 🎉 Llm library is now a chainable, immutable, and type-safe wrapper over the ai sdk If you want to improve your prompting DevX in Typescript, look no further github.com/pAIrprogio/syn…

@DavidKPiano My main gripe is the inability to type the context according to the state, especially for state machines with hydration I'd also welcome the ability to colocate typings and machine definition more than what's currently available

How would you simplify XState? Planning for the next major version, and would love to hear your thoughts and ideas ✍️

Got my first gaslighting from #Devin 🎉 It introduced a regression by overstepping its objective and removing some linter ignore comment Then claimed that the issue was pre-existing But "learned" from it I feel like that's not going to be the only occurence