Hacker News · upvotes history

Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questions

SteadyVane has taken 34 readings of Good results fine tuning a local LLM like Qwen 3:0.6B to categorize… since Jun 22, 2026: 24 upvotes at the first reading, 215 at the latest (+191). Its biggest one-day gain was +179 on Jun 22, 2026.

open the story · Hacker News thread

first seen upvotes

215

peak upvotes

215

latest upvotes

observations

first seen Jun 22, 2026 · last seen Jun 26, 2026 · published Jun 21, 2026

Day by day

Day (UTC)	upvotes	Change
Jun 26, 2026	215	+2
Jun 25, 2026	213	+1
Jun 24, 2026	212	+2
Jun 23, 2026	210	+7
Jun 22, 2026	203	+179

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: June 22, 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 →