DEV Community

Sumitsuke profile picture

Sumitsuke

Design, verify, complete. Auditing and repairing AI-generated / outsourced code; measurements with frozen logs and independent recomputation. Lab: sumitsuke.jp/lab — GitHub: sumitsuke

Joined Joined on  Personal website https://sumitsuke.jp/
I let an AI write a technical article with zero human editing, then ran it through my normal verification pass

I let an AI write a technical article with zero human editing, then ran it through my normal verification pass

Comments
7 min read

Want to connect with Sumitsuke?

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

Already have an account? Sign in
A JSONL record split in two: U+2028, U+0085, and the separator I missed

A JSONL record split in two: U+2028, U+0085, and the separator I missed

Comments
4 min read
Does AI-generated code silently swallow errors? 120 measured generations: every flagged case was a false positive or a documented fallback

Does AI-generated code silently swallow errors? 120 measured generations: every flagged case was a false positive or a documented fallback

9
Comments 39
20 min read
LLM self-review vs. a blind re-run on 160 gold-labeled name-matching pairs — no measurable difference at ceiling

LLM self-review vs. a blind re-run on 160 gold-labeled name-matching pairs — no measurable difference at ceiling

Comments
7 min read
What actually breaks when a free Cloudflare D1 database hits its 500 MB wall

What actually breaks when a free Cloudflare D1 database hits its 500 MB wall

Comments 2
6 min read
I had a local LLM review the same code 51 times: majority voting picks persistence, not correctness

I had a local LLM review the same code 51 times: majority voting picks persistence, not correctness

Comments
13 min read
loading...