Skim
A second pair of eyes on the papers you'll never reach
What it does
Keeping up with a field stopped being about access as papers ship by the thousand each week, and became about attention. Skim is a second pair of eyes on your reading queue: it walks the backlog while you work, scores each line against a reader profile you control, and surfaces only what matters to you: into your notes, linked back to PDF#page+line, a rare alert for the truly critical. You read deep where it counts and trust the triage everywhere else.
Does the same job
all alternatives →
Skim Recap19d ago · skim-recap.vercel.app · ▲79Recaps what you skipped and explains where you get stuck
- SASummarize and save web articles in one place2014 · skim.it · ▲6
Hi guys, Just letting you all know that i've just launched the beta version of Skim.it The smart way to save, sort and share the best of the web. We are trying to solve the problem over information overload on the web and not being able to fins the time to read and remember useful content you discover online. The reason why we started it is because our lives looked like this : http://skimitblog.tumblr.com/image/87300804866 (this is actually my skype account) Anyway id love to get some feedback on the product as its still early stage and look forward to making something…
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