Hacker News · upvotes history

How well do agents use test/verification techniques?

SteadyVane has taken 35 readings of How well do agents use test/verification techniques? since Sep 8, 2026: 49 upvotes at the first reading, 191 at the latest (+142). Its biggest one-day gain was +121 on Sep 8, 2026.

open the story · Hacker News thread

first seen upvotes

191

peak upvotes

191

latest upvotes

observations

first seen Sep 8, 2026 · last seen Sep 13, 2026 · published Sep 8, 2026

Day by day

Day (UTC)	upvotes	Change
Sep 13, 2026	191	0
Sep 12, 2026	191	+2
Sep 11, 2026	189	+1
Sep 10, 2026	188	+2
Sep 9, 2026	186	+16
Sep 8, 2026	170	+121

Each day's last reading. Change: against the day before (after days with no reading: since the last day that has one); the first day shows the change within that day.

Featured on 1 day: September 8, 2026.

More rising on Hacker News

Goldman Sachs is pulling Claude Code from its bankers and traders+712159 → 871 upvotes
Tell HN: Gemini trains on chat history, even for subscribers (personal accounts)+69143 → 734 upvotes
Ask HN: What's your current AI agentic setup?+5644 → 568 upvotes
OpenAI seems to be silently re-enabling model training on Codex chats+5286 → 534 upvotes
Gemini Omni 1.2 Flash+236120 → 356 upvotes
OpenAI raises $11B at a $1.25T valuation+1818 → 189 upvotes
Basically no one is using AI agents for their DoorDash orders+13345 → 178 upvotes
AI-generated posters don’t have to be horrible+1,78453 → 1,837 upvotes

Everything rising on Hacker News →