Qwen 3.8 flash is truly impressive, and llama.cpp has been rapidly getting better and better at processing it
columns are: pre-existing prompt, new prompt, generated, input tok/s, output tok/s
This is on my laptop (strix halo). I think we're very close to the point where you can just use local models for a large shar...
1
3
31
Since many people are learning about effective altruism, it's worth learning about Mozi, the ancient Chinese philosopher who was surprisingly close to being a proto-effective-altruist (particularly the global-health-focused variety, not the AI-risk-focused variety).
He valued the twin goals of (i) universal love, lovi...
1
4
22
It's an increasingly common take that AI hacking means cybersecurity is doomed.
I disagree. I think cybersecurity is naturally defense-favoring once people get their shit together. And anyone who continues to hold cryptocurrency (including me, ~90% of my net worth) is implicitly making that bet.
Here's why I am makin...
8
15
60
It's possible that a killer app of adversarial governance mechanism design theory will end up being AI safety.
Compare:
vitalik.eth.limo/general/2020...
aiprospects.substack.com/p/preventing...
There's a deep duality between the two environments. Both ar...
9
23
117
A note on recursive STARK mempools (EIP-8288) eips.ethereum.org/EIPS/eip-8288
This is an EIP that I am hoping we can get included in I-star (the fork after Hegota) that you can think of as the next step after Frames, that would unlock extreme amounts of power. Particularly:
* Ultra-cheap quantum-safe signatur...
7
22
81
One optimistic and still very-non-consensus belief I have about the far future of cryptography:
I think that there is a 33% chance that, for average real-world computation, there exist ways to implement all three of what I call the Egyptian God Protocols (SNARK, FHE, iO) with 1+ε factor overhead (meaning, for large en...
8
24
103
Many years of hard work went into the Poseidon family of hashes, and they have provided great real-world value on Ethereum and elsewhere and will continue to do so for several years. They are the reason why it's fast to generate a client-side SNARK for a modern privacy-protocol.
The fact that we have ultra-fast genera...
3
6
44
One positive consequence of all the recent detailed thinking about transaction formats - not just 8141, also "future of state" discussions eg. UTXOs, PBT, keyed nonces, and also recursive STARK mempool - is that we have a much more explicit understanding of how transactions have "actions" and "dependencies", and we can...
6
32
111
A lot of important progress on Frames (EIP-8141) has been quietly happening over the last few months. Highly recommend reading this, also the updated EIP
5
11
44
My third (and last) post in my series on obfuscation (iO): local mixing
vitalik.eth.limo/general/2026...
Local mixing is a very different philosophy from the other two, no prior background in lattices required, and very different tradeoffs (eg. in terms of computation...
12
22
119
Bitcoiners deserve a lot of credit for pioneering many of these ideas (see Utreexo).
But yes, this is what the current proposed Ethereum scaling strategy looks like in action.
We want Ethereum to have the best of UTXO-style state, dynamic state, and everything in between, allowing the great majority of Ethereum's act...
5
23
145
Impressive work!
For comparison, an H100 can do roughly 100-200 tok/s of Muse 30B for raw inference single-thread, going up to low thousands of tok/s with a large number of threads - and I am sure that for the massively-multi-threaded case they can optimize the prover further.
So we roughly, sort of, have single-digi...
7
11
92