shellbear (@_shellbear) header
shellbear (@_shellbear) profile picture

https://nitter.gq/t.co/8dosS9q6Z6 https://nitter.gq/t.co/Of5gIsmwHL https://nitter.gq/t.co/2PxV3o71w3

/dev/null
Joined January 2015
Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)Photo by shellbear (@_shellbear)
감사합니다!
18
Replying to @marclou
Hold my coffee
199
Replying to @expo @wcandillon
Thank you! 🙏
1
29
Replying to @wcandillon @expo
Thank you for the awesome libs & inspiration 🙌
1
35
Experiment of the day: a cute onboarding inside a Seoul subway car 🚇 for my Korean-learning app. Made with @expo & three.js on WebGPU (react-native-wgpu by @wcandillon).
6
3
18
1,764
This is actually great.
good prompt "find all of the implicit state machines in my app"
41
Replying to @eukaeh
Still really experimental and uncompleted but source code is here: github.com/shellbear/aoe-2-d… Hope to publish soon :-)
4
Ok, getting something. Age Of Empires 2 HD running inside browser fully decompiled by claude and REA. Maybe a working multiplayer directly in the browser 👀
1
1
69
Replying to @jmartinprin
5 chiffres bien évidemment
1
5
1,220
Replying to @levelsio
Why an Airbus A350 is more eco-friendly than average train?
1
13
3,741
Replying to @MisaDev4
Awesome work!! Super curious about the decompilation methods if you have more info!
58
Nice one! Just, the demo slider is broken on Firefox:
1
74
A good news for the Claude Code gang 🤠
Replying to @claudeai
Effective today, we are: 1) Doubling Claude Code’s 5-hour rate limits for Pro, Max, and Team plans; 2) Removing the peak hours limit reduction on Claude Code for Pro and Max plans; and 3) Substantially raising our API rate limits for Opus models.
2
37
Seems like Google is doing it on its side by having up-to-date gemini-pro-latest and gemini-flash-latest variants that automatically update to the latest models. ai.google.dev/gemini-api/doc…
Here's exactly what I mean: On May 15, @xAI Grok will retire grok-4-1-fast-non-reasoning and API requests for them will fail I have 9 days to change the model name in 30+ sites/apps so they keep working It'd make much more sense to me if they'd just update to the latest model with the same pricing, or let me use a model name like 'latest' that just auto updates Although actually people's arguments against this make sense regarding pricing: In this case there is no similar priced "latest" model, pricing goes up from $0.20/input + $0.50/output in Grok 4.1 to $1.25/input + $2.50/output in Grok 4.3 But I'd be fine with that too, I just don't want all my apps/sites to break and keep running forever without me having to change code!
1
1
88
Pour les freelances tech en France, si vous voulez suivre les trends et l'évolutions des offres du marché sur les principaux acteurs (free-work), je collecte des data depuis 2022 et vous les sur mon site. En plus vous avez le droit à un mode Bloomberg Terminal 📈 #freelance
1
1
104