Gioele SL Fierro (@gslf_dev) header
Gioele SL Fierro (@gslf_dev) profile picture

Thinker, Software engineer, UITS Shooter.

Catania
Joined June 2007
Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)Photo by Gioele SL Fierro (@gslf_dev)
MAI contro i modelli di frontiera. Per @AI4Business_it .
33
Replying to @antirez
And we need easy explorable runs, to better understand when, where and how a model is stronger than another.
50
I have released a new version of CWtty, featuring a new Statistics section, several UX improvements, and new training levels for reception. It is available as a PWA on my website, and a TUI installer can be found on GitHub.
🤖 Made with AI
68
I’m fucking sick of hearing this bullshit, so I had to do something.
39
Modelli generativi che non generano. I costi si riducono drasticamente, e per alcune applicazioni specifiche possono essere anche più efficaci di un classificatore tradizionale o di un LLM. ai4business.it/intelligenza-…
27
I have a very specific opinion about markdown-based note-taking tools. A PWA with real-time markdown rendering, cloud sync on Filen, a built-in static site generator, stupidly fast, and it runs on every platform. Want to break it? Go ahead: gslf.it/th-ink
3
1
53
Gioele SL Fierro retweeted
Disengaging from syntax is not disengaging from engineering. I’m working on a significant project at the moment. It’s in a pre-production state so far. More than a prototype, less than ready for real users. I’ve been making multiple passes over the structure for each of the following concerns: Architecture, coverage, race & concurrency, security, API, etc. Each of these requires significant interrogation and review of verification procedures; but not review of the code. At base are the /ub-mode (GitHub.com/unclebob) rules that keep the agents disciplined as far as coding structure and tests are concerned. But above that it’s me making sure that all the bases are covered well enough to keep my client safe from stupid sloppy mistakes. I am the engineer. I am responsible. The agents are just my tools. They are power tools, to be sure. But power tools in the hands of novices result in missing fingers. So I am very careful.
68
80
17
1,177
59,544
Nemotron 3.5 Super is not going into main branch of inferenZ. The port was validated layer by layer but the performances are not enough. Decode: 3.95 tokens/s against Qwen's 7.53 Coding: 27/40 against 33/40 Weight reads per token: ~10 GB against ~6 GB
54
Tried Poolside's Laguna S 2.1 (118B MoE) in inferenZ, my C LLM engine for a 62 GB laptop: 6 tok/s and 26/40 on my coding eval vs Qwen3.8's 7.5 and 33/40, with 17-minute answers on average. Not merging. Bonus: tuning the kernels for it made Qwen 12% faster.
1
29
Tried NVIDIA Nemotron 3.5 Super (120B, Mamba-2 hybrid) in inferenZ, my C engine for 120B MoE models on a 62 GB laptop. NVFP4 weights copied bit-exact (KL 0.003). But 12B active = 10 GB read per token: 4 tok/s and 27/40 on my coding eval vs Qwen3.8's 7.5 and 33/40. Not merging.
33
How much I learned from the latest UNIMATRIx benchmark runs publish.obsidian.md/gslf/nem…
🤖 Made with AI
41
Gioele SL Fierro retweeted
Hyprland 0.57.0 is finally here, with tons of new stuff you don't wanna miss! hypr.land/news/update57/
16
36
3
794
31,251
My @X feed is full of useless shit right now. Why?
1
131
Replying to @Ionkosm
Do you have a definitive definition for AGI, and reliable tools to evaluate it?
16
Minutes? Hours? Days? Weeks? Months? How long for mere mortals?
322
Gioele SL Fierro retweeted
Today we’re introducing Gemini 4 Carbon — our newest frontier model from @GoogleDeepMind. Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities. Built for sustained agentic workflows, it delivers improved performance across domains — with greater alignment, transparency, and follow-through to respond to high-pressure tasks. We’re rolling it out starting this week to cyber defenders through our Fairwind Program, with expanded access as soon as possible.
51
179
36
2,006
62,904
Replying to @PrismML
@PrismML Bonsai is one of the new entries of UNIMATRIx Leaderboard
36
Replying to @Recursive_SI
@Recursive_SI Flint is one of the new entries of UNIMATRIx Leaderboard
49
Gioele SL Fierro retweeted
Credits where credits is due: kudos to @OpenAI in the context of the new scientific releases, for putting the scientists that worked in a given field for a long time at the center of the process of understanding and announcing the new discoveries.
10
9
2
348
22,585