A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost
3 comments
- Points567
- Comments142
3 comments
Story details from Hacker News ↗ · linked article on hightouch.com.
A Jev that can ask Opus for help gives Opus accuracy at 4x lower cost was first seen on Hacker News · Front page on Nov 6, 2026. Since then it has appeared in 98 checks on 2 different days. Its best position was #2 of 30, reached on Nov 7, 01:52 UTC. It dropped off the list after Nov 7, 21:09 UTC.
Position on Hacker News · Front page at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by Hacker News.
A few top-level comments from Hacker News, shortened. Read the full thread on Hacker News.
If you use Qwen3.8 27B to manage, to orchestrate, do do shallow research, and then make it ask claude you will notice that Qwen can get out of Haiku, Sonnet and Opus almost as good answers... I was researching how good the model asnswers where, I can't get to work with anything but Fable, but Qwen can get good work…
Everyone is discussing the tech, but you do realize that they made mapping data to real people easier using AI? This is essentially AI-assisted privacy violation, 4 times cheaper. People, please try to understand what you are building. Don't just build it as asked!
Im also planning to combine them. I have haiku hooked up for guardrails in my llm proxy. With the prompts routed to opus or sonnet after they pass the check. I'll replace haiku with Jev and my costs should definitely drop.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 7, 21:09 UTC, after 2 days of trending.
#2 on Hacker News · Front page, on Nov 7, 01:52 UTC. Trendoday checks this list every 15 minutes.
It was first seen on Nov 6, 2026 and has been on the list on 2 days (98 checks) since.
567 points and 142 comments; submitted by theanomaly on Nov 6, 2026.