Sources · Twitter/X

@ivanfioravanti

Active

ivanfioravanti

Linked items 435
Errors 79
Last fetched 2h ago
Priority P3
Must-read No

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.

Includes every eligible item from this source in the must-read section, even when the normal item cap or duplicate grouping would skip it.

Automatic import processes at most 50 historical items per burst. Full history continues in resumable chunks and may incur transcription/LLM cost. Older items are never silently dropped.

Progress: 0 processed · 0 remaining · 0 skipped · status none

Optional day window for classification drain when using Latest 50.

Cancel

Recent items

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

Title Type Fetched
@ivanfioravanti: I bet DeepSeek V4 Flash 0731 mxfp4 will go faster than 80 toks/s on M5 Ultra without MTP/DSpark. L... article 2026-08-08
@ivanfioravanti: Wan Animate 2! Ready to try it! NVIDIA RTX Spark (@NVIDIARTXSpark) Congratulations to the @Alibab... article 2026-08-08
@ivanfioravanti: The real beauty of using a Chinese LLM stays in the ability to read the real thinking of the model. ... article 2026-08-07
@ivanfioravanti: Just a reminder that Grok 4.6 is imminent. 🔥 Elon Musk (@elonmusk) Try Grok Build X.ai/build Li... article 2026-08-07
@ivanfioravanti: WOW look at the status of MLX Fast challenge! Tomorrow I'll give it another try! 160%... UNBELIEVA... article 2026-08-07
@ivanfioravanti: Family is out for the weekend, now sushi and then TOTAL ULTRA DEEP DIVE on Local AI embeddings. I n... article 2026-08-07
@ivanfioravanti: ~1900 tok/s! I need a GB300! @NVIDIAAI I'll come to visit you in SF in October 🤣 Mitko Vasilev (@... article 2026-08-07
@ivanfioravanti: MTP no MPT 😖 Maybe I should use AI a little to lean my posts. article 2026-08-07
@ivanfioravanti: Super @antirez I'm trying to apply something to M5 kernel. I will see results and then open PR in an... article 2026-08-07
@ivanfioravanti: I forgot to mention that I've used prime-agent by @PrimeIntellect for this kernel research and it wa... article 2026-08-07
@ivanfioravanti: Where there's a will, there's a way 😎 DwarfStar DeepSeek V4 Flash 0731 mxfp4 on M3 Ultra single requ... article 2026-08-07
@ivanfioravanti: You know how much they just offered me for one of my Apple Mac Studio M3 Ultra 512GB, which I paid a... article 2026-08-07
@ivanfioravanti: Prime-agent is a beast! Stay tuned for some real results! Great job @PrimeIntellect 🚀 article 2026-08-07
@ivanfioravanti: It's incredible how using multiple models on the same problem can lead to multiple unexpected ideas ... article 2026-08-07
@ivanfioravanti: 16.8B$ is just the initial investment to create the new Terafab chip factory in Texas, can't imagine... article 2026-08-07