Sign in

Simone Civetta

@viteinfinite.bsky.social
90 followers 16 following 57 posts
PostsRepliesMedia
Simone Civetta @viteinfinite.bsky.social · 24/06/2025
Installed Beta 2 on my iPhone. The Liquid Glass effect is nice, but too present in such a small screen estate. It feels somehow “baroque”. As screens are larger, I find it much more pleasant on iPadOS and macOS.
010
Simone Civetta @viteinfinite.bsky.social · 17/06/2025
Foundation Models framework is beautiful. I had the opportunity of grabbing a WWDC lab, and here’s a bunch of info you might find useful. 🧵
111
Simone Civetta @viteinfinite.bsky.social · 14/06/2025
Thinking about Dia (and @perplexity_ai’s Comet - which I haven’t tried yet). But in an AI-first world, apps who have the most potential are IMO those like @raycastapp, offering a deep integration with the system that goes way beyond browsing. And they’re far from being sherlocked
000
Simone Civetta @viteinfinite.bsky.social · 12/06/2025
macOS Beta is usable as a daily driver on my MBPro M1. And by usable, I mean "usable". It's not perfect, but it doesn't crash. Mean issues so far: far from buttery smooth (esp. Safari, which is sluggish to say the least) + quick battery drain. The UI is not radically different, but it's pleasant.
000
Simone Civetta @viteinfinite.bsky.social · 11/06/2025
As much as I loved “Letter to Arc members” by @browsercompany I feel that for my own personal use, Dia is a step in the wrong direction. I find that features like command bar (with actions) or the swipe to change the profile were true productivity enhancers.
000
Simone Civetta @viteinfinite.bsky.social · 11/06/2025
At this point the most disappointing Apple product is the Apple Watch. Sure they sold millions of it but it now sits in a purgatory between being too power hungry to have a long lasting battery life and but too constrained to run a SLM or proper background tasks.
000
Simone Civetta @viteinfinite.bsky.social · 11/06/2025
I’m glad to see such a feature-rich Foundation Models framework and its API so pleasantly “swifty”. A simple inference API would have already been good, but FMf goes way beyond that.
010
Simone Civetta @viteinfinite.bsky.social · 10/06/2025
The ChatGPT integration in Xcode will certainly useful at some point. But at the moment is still ages behind Cursor (via the xcode-build-server integration, cf @dimillian.app‬'s tutorial).
130
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
Swift Assist DOA?! #WWDC25
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
Not sure Background Task APIs are the right answer but it's certainly a step in the right direction. #WWDC25
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
Ok, I lied. I was also hoping for these new iPad features! #WWDC25
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
Shortcuts looks neat, even as a Raycast user. #WWDC25
010
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
To me the only meaningful update to watchOS would be a truly minimal version that would allow the battery to last at least 4 days.
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
Screen Visual Intelligence hopefully available (in Europe) before Winter 2029. #WWDC25
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
Ok, translations. But just give me multilingual Siri for putain sake. #WWDC25
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
Not entirely sure that widgets in CarPlay are the safest idea. Looking forward to seeing how it works in real life. That said, Siri is still, by FAR, the biggest irritant while using CarPlay. #WWDC25
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
That Liquid Glass shader is giving me shivers. #WWDC25
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
Spoke too soon. The *only* API I was actually waiting for, "Foundation Model framework" is official!
000
Simone Civetta @viteinfinite.bsky.social · 09/06/2025
\#WWDC is starting now, and the fact that it’s kicking off with an #F1TheMovie promo brings back painful memories of that Apple Music-focused WWDC.
000
Simone Civetta @viteinfinite.bsky.social · 23/05/2025
Lately, I’ve been using Roocode more and more in my AI coding workflow—so much so that I miss it when working in Cursor. My preferred workflow now starts with a planning phase before letting the AI touch a single line of code. 🧵
101
Simone Civetta @viteinfinite.bsky.social · 16/05/2025
Coding with AI brings lots of challenges. Two I keep running into: – Reading – Memorisation Let’s talk about them.
100
Simone Civetta @viteinfinite.bsky.social · 02/04/2025
🤯 @piaskowyk.bsky.social showing JS code running faster than C++!
031
Reposted by Simone Civetta
Software Mansion @swmansion.com · 13/02/2025
It’s time for the Llama generation speed benchmark! 🚀 We’ve compared quantized Llama 3.2 1B QLoRA and the full precision model. Results: ⚡Quantized model: 9.56s ⌛Full precision model: 19.14s It’s 2x faster with quantization! 📈 Try it yourself with our example app ⭐ github.com/software-man...
0134
Simone Civetta @viteinfinite.bsky.social · 11/02/2025
Choosing the right engine is key in local LLM/LMM inference; it can significantly impact speed, quality, docs, compatibility and portability. Here's a comparison among the most starred ones as of Geb 2025: llama.cpp, MediaPipe, MLC-LLM, MLX, MNN - PyTorch ExecuTorch.
001
Reposted by Simone Civetta
Delphine Bugner @delphinebugner.bsky.social · 06/02/2025
apps.apple.com/us/app/le-ch... play.google.com/store/apps/d...
apps.apple.com
‎Le Chat by Mistral AI
‎Le Chat combines powerful AI with extensive information on the web to help you rediscover the world. Enjoy natural conversations, real-time internet search, comprehensive document analysis, and much ...
2345
Simone Civetta @viteinfinite.bsky.social · 01/02/2025
🤯 This is DeepSeek R1 Distill—a Llama-based model distilled from DeepSeek R1, running LOCALLY in your browser, at a decent ~12 tok/sec on my M1 Pro. A project by MLC LLM (Guess where they are from?) huggingface.co/spaces/mlc-a...
000
Simone Civetta @viteinfinite.bsky.social · 31/01/2025
I've been talking more about On-Device Inference on Mobile with friends lately. I created a short blog post to review the main challenges in this domain. 🇬🇧 viteinfinite.com/2025/01/on-d... 🇫🇷 www.hymaia.com/blog/8-defis...
viteinfinite.com
8 On-Device Inference Challenges - viteinfinite
One of the trends I find the most exciting these days, is the local inference of LLMs on mobile. That’s for sure related to my time as a mobile- (or, rather ...
010
Simone Civetta @viteinfinite.bsky.social · 20/01/2025
And guess who joined our Content Team this year? @delphinebugner.bsky.social — Mobile Lead at Mistral and one of the most passionate and enthusiastic people you’ll ever meet in this community!
071
Simone Civetta @viteinfinite.bsky.social · 17/01/2025
This is your friendly reminder that we’re just 2 days until the end of the CfP! 👉 reactnativeconnection.io/cfp
073
Simone Civetta @viteinfinite.bsky.social · 16/01/2025
🎉 We’re finally thrilled to announce that Manuela Sakura Rommel is joining our lineup! Manuela is Women Tech Makers Ambassador and co-org of the Berlin Flutter meetup. She has notoriously been featured in the Observable Flutter podcast by @labenz.dev. 👉 flutterconnection.io
051
Simone Civetta @viteinfinite.bsky.social · 08/01/2025
I’m testing stuff!
000
Reposted by Simone Civetta
React Native Connection @reactnativeconnect.bsky.social · 28/11/2024
Rumours were true: we are now on Bluesky! But, mainly: React Native Connection returns in 2025! Join us in Paris on April 1-2, 2025 for the third edition of your Frenchiest React Native event! 👉 More info on reactnativeconnection.io
reactnativeconnection.io
React Native Connection Conference
React Native Connection - The French React Native Conference - Paris, April 2025. The first French conference entirely dedicated to React Native developers.
084