Hacker News: yt1998

New comment by yt1998 in "Show HN: Jev-pages – Building landing pages real time with Jev"

yt1998 — Mon, 05 Oct 2026 15:04:09 +0000

Why do you use Jev to choose different items? I don’t believe Jev or any LLM today knows how to create an attractive landing page with great CTR and conversion. Jev can only speed up selection, but little performance upgrades to final outcome.

New comment by yt1998 in "Show HN: Pi pod – Run your pi coding agent in sandboxes on your own server"

yt1998 — Sun, 04 Oct 2026 14:08:02 +0000

Maybe not a sandbox or VM I want, but a cloud computer. In this way, I don’t need to worry about storage, permissions and so on. It is for agents only.

New comment by yt1998 in "Show HN: AI search for every photo and every frame of video on macOS"

yt1998 — Sun, 04 Oct 2026 13:59:22 +0000

Why chose CLIP to do this. Have you tried small VLMs like Qwen-VL? I believe those models have video encoders can better perform at this scenario.

New comment by yt1998 in "Kev: Tiny Jev-like family of decision models built on top of Qwen3.5"

yt1998 — Tue, 22 Sep 2026 12:17:08 +0000

Do you have task completion numbers alongside the reduction in tool calls? I’d be interested in whether narrowing the tool set ever removes something the agent needs later in a task. I’m building Gear, an open-source framework for evaluating and improving agent harnesses. One result that made aggregate metrics less reassuring: a harness change took our pass rate from 36% to 40%, but underneath that were 14 tasks improving and 10 regressing. I’d want to see that breakdown alongside the tool-call savings. The experiment is documented here: https://github.com/rsi-gear/gear/blob/main/docs/guide/en/exa...