AlgoBlock
Take back control of your YouTube algorithm
What it does
AlgoBlock is a Chrome extension that filters your YouTube feed to only show content matching your topics — VC & startups, business strategy, AI, productivity, and psychology. It hides off-topic videos in real time, kills Shorts completely, and gradually trains YouTube's algorithm to work for you over time. 150+ curated keywords, fully customizable, 100% private — no data leaves your browser.
Does the same job
all alternatives →- YBYouTube banned adblockers so I built an extension to skip their ads2023 · ▲713
Hi HN! Since Youtube no longer allows AdBlockers, I built my own extension to get around their video ads. If there is an ad it temporarily manipulates the video; Mutes the volume, sets speed to 10x, and skips it if there is a button. Chrome Webstore link: https://chromewebstore.google.com/detail/ad-accelerator/gpbo... Code: https://github.com/rkk3/ad-accelerator
- CPControl Panel for YouTube2024 · ▲111
Hi HN, I recently released a new browser extension for YouTube, which in addition to the table stakes of hiding the existence of Shorts, hiding promoted content, automatically skipping ads, hiding useless/unused UI elements, hiding unwanted channels YouTube keeps recommending to you, letting you hide algorithmic suggestions etc. etc., makes other changes I've always wanted as a user, in the same vein as one of my other extensions, Control Panel for Twitter. The most significant of those is attempting to make your Subscriptions page more like an Inbox, by hiding videos you've already…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.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