DEV Community

Sergei Parfenov profile picture

Sergei Parfenov

AI Engineer and CTO. Building products, thinking about what's next in software and AI. Writing about things that actually matter.

Location Barcelona Joined Joined on  Personal website https://github.com/P0rt github website

Education

Stanford

Work

CTO at Aliwio

4 Week Community Wellness Streak
2 Week Community Wellness Streak
1 Week Community Wellness Streak
Writing Debut
Seven Year Club
Six Year Club
Five Year Club
Four Year Club
Three Year Club
Two Year Club
One Year Club
My Strawman Baseline Beat My Own Scheme on Half the Gate Classes

Prose summaries vs structured compaction

My Strawman Baseline Beat My Own Scheme on Half the Gate Classes

10
Comments 10
12 min read

Want to connect with Sergei Parfenov?

Create an account to connect with Sergei Parfenov. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
Your Provenance Vector Dies at the Storage Boundary

Type-level gates and memory compaction

Your Provenance Vector Dies at the Storage Boundary

13
Comments 18
8 min read
Trust Isn't a Scalar: Typed Provenance for Agent Chains

Co-authored by the article's comment section

Trust Isn't a Scalar: Typed Provenance for Agent Chains

13
Comments 27
9 min read
The Most Powerful Model on the Market Got Pulled by the Government in 3 Days. Is It Real, or a Hype Bubble?

The Most Powerful Model on the Market Got Pulled by the Government in 3 Days. Is It Real, or a Hype Bubble?

9
Comments 2
4 min read
You Fixed the Rate Limits. Now Your Agent Fails Quietly.

Uptime versus correct uptime trade-offs

You Fixed the Rate Limits. Now Your Agent Fails Quietly.

13
Comments 36
8 min read
Your AI Coding Speedup Is a Loan, Not a Gift — and the Interest Is Coming Due

Your AI Coding Speedup Is a Loan, Not a Gift — and the Interest Is Coming Due

7
Comments
6 min read
I distilled a 7B vision model into a 2B one for screenshots — and the 7B teacher scored worse

Metric bias against descriptive thoroughness

I distilled a 7B vision model into a 2B one for screenshots — and the 7B teacher scored worse

30
Comments 7
9 min read
loading...