Sources · Twitter/X

@ivanfioravanti

Active

ivanfioravanti

Linked items 105
Errors 69
Last fetched 2026-05-13 02:19
Priority P3

Edit

Human-friendly label. Leave blank to fall back to the identifier.

Drives ingestion cadence and the default ranking weight applied to items from this source.

How often the watch loop polls this source. Minimum 5 min. Leave blank for the per-type default.

Optional. Pin a specific summarization model for items from this source.

Cancel

Recent items

The 15 most-recently-ingested items from this source, newest first.

Title Type Fetched
@ivanfioravanti: Interesting video of M5 Max, on impact of Low, Automatic and High power modes on inference. - No ext... article 2026-05-12
@ivanfioravanti: Why in the Apple MLX ecosystem, is everyone building a new engine copying from others, instead of co... article 2026-05-12
@ivanfioravanti: oMLX is powerful! Give it a try! Jun Kim (@jundotkim) oMLX 0.3.9.dev2 released. Highlights: - Gem... article 2026-05-12
@ivanfioravanti: ds4 Metal Tensor kernel is fast on paper (ds4-bench here), but with some logprob drift issues still ... article 2026-05-12
@ivanfioravanti: Apple MBP 16" M5 Max is a great and you can push it beyond its limits using High Power mode, but be ... article 2026-05-12
@ivanfioravanti: No please, no! Don't push people to think that a cluster of 4 M5 Max is a viable solution. If you se... article 2026-05-12
@ivanfioravanti: I don't want to be too excited for this because it's still experimental, but I have been able to fin... article 2026-05-12
@ivanfioravanti: Reachy Mini ready to go! Audio on 🔉 Cleary I'll connect it to Local AI services and to my Hermes Age... article 2026-05-11
@ivanfioravanti: Look who’s just arrived! Reachy Mini Wireless! 🚀 article 2026-05-11
@ivanfioravanti: Logprob drift solved and performance still good! Tomorrow mega benchmarks 🚀 article 2026-05-10
@ivanfioravanti: M5 Max in Automatic instead of High Power is much slower, I see at least a 15% difference. So when ... article 2026-05-10
@ivanfioravanti: "Here's to the crazy ones." 💪 Keep dreaming, keep building, keep pushing. Always. Guido (@Full_Met... article 2026-05-10
@ivanfioravanti: Problem of testing micro optimizations on a single M5 Max is that you have to do this sequentially a... article 2026-05-10
@ivanfioravanti: I don't trust my technical Co-Founder 100%, but it's surely faster than me in many tasks. article 2026-05-10
@ivanfioravanti: I'm back to the AI world after a session in the gym 💪 Let's keep having a lot of fun experimenting ... article 2026-05-10