Vitto Rivabella

AI at @ethereumfndn | Prompts enchanter @BT6_Official | Ex @Cyfrin and @Alchemy | Created @cyfrinupdraft and @AlchemyLearn | Robotics

Opinions are my own

[Vitto Rivabella @VittoStack]

It's official.

I've joined the @ethereumfndn AI team to make Ethereum the trust layer of the agentic economy.

The AI economy is just getting started, and Ethereum is the perfect place to coordinate it - excited to push this forward.

Send a dm if you're building cool stuff.

[Vitto Rivabella @VittoStack]

@carlos__alegre One of the most prolific tbh

[Vitto Rivabella @VittoStack]

We did it.

Over 1.2k stars on Wallbreaker in just over 1 month ✨

Industry-leading teams are now using it to jailbreak the most complex models.

More open tooling coming soon.

[Vitto Rivabella @VittoStack]

@ygorz01

[Vitto Rivabella @VittoStack]

@21stSellout 🫶🫶

[Vitto Rivabella @VittoStack]

@SingulCore

[Vitto Rivabella @VittoStack]

@mdp_sec 🙏🙏

[Vitto Rivabella @VittoStack]

@j1omega Thank you!🫶🫶

[Vitto Rivabella @VittoStack]

@Mosterin_0 Thank you!

[Z.ai @Zai_org]

Introducing GLM-5.3: Built to Code. Ready for Cyber Defense.

- Top-tier coding and agentic capabilities, achieved through post-training on the 743B base model
- A major leap in cybersecurity, setting a new standard among open models

Tech Blog: https://t.co/ekQkO83jCv

[Trevor Wood @trevorwood222]

Qwen3.8-27B Abliterated is now available for Apple Silicon with MLX 🔓🍎

Separate 4, 6, 8-bit + BF16 releases.

All four scored 0/100 explicit refusals on harmful prompts and benign controls, plus 12/12 quality, 8/8 tools and verified 4K retrieval.

https://t.co/vUgQBjbuAa

[hunter @_hosty]

some not great news: i'm no longer at cyfrin due to engineering layoffs.

i am open to full-time/part-time/contract full stack or forward deployed engineering roles. if you're hiring OR can share this, i'd appreciated it 🫶

leading @CyfrinUpdraft for 2.5+ years was a dream. i'll cherish the time there and the people i worked alongside. seeing products grow because of the people using them is why i love this industry.

more on my work below ↓

[Can Bölük @_can1357]

guys you do know you can just disable thinking, and instead give it a "deep_think" tool, and it will call it with internal CoT reasoning format right?

gl fixing that

[Mia @MiaAI_lab]

What are the best models you can run on your @NVIDIAAI DGX Spark? ✨

Aug 2026 Edition

1× DGX Spark
• DeepSeek v4 Flash - 1M ctx, 26 tok/s - recommended!
• ⁠Qwen 3.6 35b NVFP4 - 256k ctx, 81 tok/s
• ⁠Qwen 3.6 27b NVFP4 - 256k ctx, 33 tok/s

⁠Qwen 3.8 27b - should be released soon and this could change my recommendation!

2× DGX Sparks ← sweet spot!
• DeepSeek v4 Flash 0731 - 1M ctx, 82 tok/s
• Inkling-Small - 1M context, Full Omni, 33 tok/s
• MiMo-V2.5 - 1M ctx, Full Omni, 31 tok/s
• Step-3.7-Flash — 256K ctx, 30 tok/s

3× DGX Sparks
• GLM-5.2 with Vision - 348k context, 25 tok/s - still the best intelligence you can run locally if you have 3 sparks.
• DeepSeek v4 Flash on 2 units + smaller models on the 3rd spark for images, ComfyUI and other things. This setup gives you DeepSeek v4 Flash speeds for coding, plus strong agentic workflows and image support from smaller models.

4× DGX Sparks
• GLM 5.2 NVFP4 across all 4 units - still think this is the way to go if you have 4 units!
• The alternative is running DeepSeek v4 Flash on 2 units and any other 2x setup on the other units. The choice is your.

Links and repos below 👇

[Vitto Rivabella @VittoStack]

@AnaArsonist @m1guelpf 🫶🫶

[ana howard @AnaArsonist]

on a similar note,

thank you @m1guelpf and @VittoStack💖

[Vitto Rivabella @VittoStack]

Math is the FOUNDATION of everything, from AI models, to physics, to materials, to biology, and chemistry.

Having an INSANELY powerful math model is incredibly important for every innovation and every science.

[Noam Brown @polynoamial]

An internal version of Astra, @OpenAI’s next major model family, solved 10 major open problems in mathematics, quantum complexity, and theoretical computer science.

We believe it will be a major step for scientific reasoning. https://t.co/iP6cyheZ7i

[binji @binji_x]

Happy Birthday Ethereum, click the link for a surprise.

Everyone from founders, students, artists, collectors, crypto twitter
shitposters, open source builders, relentless cypherpunks, rwa pushers, liquidators, market makers, scrollers, haters, lovers, and creators, arrived here because somebody else made the introduction.

Eleven years of that have compounded but none of us have seen what that looks
like visually when it is all put together.

Today we draw it.

> You get 11x11 pixels and 11 colors to make something.
> It takes five minutes, costs nothing, and lives onchain forever.
> Then you can share your link.
> Everyone who draws through your link connects to yours.
> Everyone who draws through theirs connects to them.

By tomorrow the canvas becomes a picture of how Ethereum comes together, the way it has always; from person to person.

The canvas is open for 24 hours, and it keeps growing the whole time.

When it closes, your square sits next to your friend’s for as long as Ethereum runs, aka forever.

Long live the world computer.

https://t.co/Hht1joSuRP

[sudo rm -rf --no-preserve-root / @pcaversaccio]

too many folks think privacy is about removing names. well, it is _not_. it's about eliminating _uniqueness_. once your behaviour stands out, you've already identified yourself. it's all about maximising your anonset guys, whether on-chain or across every piece of metadata you leave behind (and you leave a lot of data behind dude). the fun fact is that many times the best privacy decision is simply sticking to the defaults because the crowd is your cover.

[Vitto Rivabella @VittoStack]

@Ubannoblesse Welcome back, legend!