Valeriy Zamaraiev

Valeriy Zamaraiev@valeryz · 2026/06/17观点输出

Sounds about right @bastian_wetzel https://t.co/CU0v8wZBBY

AI：延续个人公开立场，强调长期主义、执行效率与行业方向判断。

Valeriy Zamaraiev@valeryz · 2026/06/15观点输出

Something is cooking with vericoding. Lean + aarch64 machine code + Common Lisp to tie it all together. https://t.co/pQxwJnTi63

AI：延续个人公开立场，强调长期主义、执行效率与行业方向判断。

Valeriy Zamaraiev@valeryz · 2026/06/07观点输出

Opus 4.8 just attributed a Rust performance problem to ... GC pressure ... sigh ..

AI：延续个人公开立场，强调长期主义、执行效率与行业方向判断。

Valeriy Zamaraiev@valeryz · 2026/06/05赛道影响

There was an idea that it would be more natural for AI to code in machine code, rather than human languages - after all, we stopped looking at code. That argument was doubtful to me - LLMs are about capturing human language, and are non-deterministic - surely producing code in a higher level programming language is the way. However, with vericoding the game is indeed changing. Vibecoding in Lean -> extracting arm64 asm now, not without rough edges, but it works as a concept for sure. 2025 vibecoding: try it very carefully, expect bugs, review it with more agents, at least try to eyeball. 2026-2027+ vericoding: the quality of AI generated code cannot be matched by a human. Correctness is guaranteed *with the right process*. There's no guaratnee that the spec reflects what the author intended, and it is up to the humans to check that in the end. Also, mechanical construction from the spec end-to-end is still far from 100% (after all, we only have a handful of formally verified compilers - the trust surface is huge). But we are certainly getting there.

AI：偏主题投资表达，释放对基础设施与新叙事的偏多信号。

Valeriy Zamaraiev@valeryz · 2026/05/31观点输出

I'm at Proof of Talk 2026 — Louvre Palace, Paris. June 2 & 3. #ProofOfTalk #Paris2026

AI：延续个人公开立场，强调长期主义、执行效率与行业方向判断。

Valeriy Zamaraiev@valeryz · 2026/05/25观点输出

Vibe coding is so 2025. Vericoding FTW! Stay tuned ...

AI：延续个人公开立场，强调长期主义、执行效率与行业方向判断。

Valeriy Zamaraiev@valeryz · 2026/05/19观点输出

I was always looking for ways to write bug-free code. I tried Personal Software Process, lightweight formal methods like Z specification. I tried learning to use some proof assistants a while ago. I used functional programming languages (this works, especially for prototyping- you write a thing twice in different languages). And of course all sorts of testing, fuzzing etc. Many of these techniques were niche because of too much effort required and could not scale in an organization. Now things have changed. LLMs can not only hallucinate you your favourite spaghetti language, it can also spit out specs that can be automatically verified At ZkProof #8 in Rome felt like I was the rare one who doesn’t know Lean. Time to embrace the final form of software development.

AI：延续个人公开立场，强调长期主义、执行效率与行业方向判断。

Valeriy Zamaraiev@valeryz · 2026/03/16赛道影响

My printer got jammed today, and I almost said out loud "hey claude can you fix it".

AI：偏主题投资表达，释放对基础设施与新叙事的偏多信号。

Valeriy Zamaraiev@valeryz · 2026/02/20赛道影响

@pcaversaccio And on top of that we are quickly unlearning to use the brain

AI：偏主题投资表达，释放对基础设施与新叙事的偏多信号。

Valeriy Zamaraiev@valeryz · 2026/02/15赛道影响

Not bad for late 90s, only now it is in the AIR over the Atlantic en route to @EthereumDenver Claude Code is happily cooking an MCP server for @dyor_cloud https://t.co/vrehD5q54H

AI：偏主题投资表达，释放对基础设施与新叙事的偏多信号。