BiteTube
No more AI or algorithmic junk - Get feed curated by people
What it does
As you know, these days most of the Youtube recommendations suck. Not because there aren't good quality content/creators, but because Youtube only pushes videos which drives them a lot of ad revenue, whether that be AI slop or fast paced brainrot. BiteTube is a platform where you get videos served by the people, not the algorithm. Everything here is manually checked and accepted and then shown on the feed. Furthermore, we have filters and collections to help you find best videos under a minute.
Does the same job
all alternatives →
- IBI Built a Site That Curates Weird YouTube Rabbit Holes Daily2025 · yourabbit.com · ▲59
I built Yourabbit.com — a site that curates hand-picked YouTube rabbit holes grouped by themes like quirky psychology, obscure tech, weird facts, and binge-worthy oddities. It’s not driven by the YouTube algorithm — every collection is themed and curated manually (for now), with a backend I’m automating to fetch and organize new rabbit holes daily. Built as a hybrid Astro + Next.js project, optimized for static generation and speed. I’m also pairing videos with custom summaries and commentary (using AI), and would love feedback from the HN crowd on: Content model (too wide? not specific…
- RWRealTube – Watch YouTube with filters for AI-generated contentJun 2026 · realtube.io · ▲6
More work this month
the category →
The app store for voice native apps that lives in your notch
Work · 29d ago · voiceos.com
Launched alongside, May 2026
the whole month →
Parallel agents, diff reviewer, and multi-model comparisons
Dev tools · May 2026 · kilo.ai
- NW
Hey HN, Henry here from Cactus. We open-sourced Needle, a 26M parameter function-calling (tool use) model. It runs at 6000 tok/s prefill and 1200 tok/s decode on consumer devices. We were always frustrated by the little effort made towards building agentic models that run on budget phones, so we conducted investigations that led to an observation: agentic experiences are built upon tool calling, and massive models are overkill for it. Tool calling is fundamentally retrieval-and-assembly (match query to tool name, extract argument values, emit JSON), not reasoning. Cross-attention…
Life & fun · May 2026 · github.com
- FM
Dev tools · May 2026 · github.com