Posts

Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots https://ift.tt/oG1sVZm

Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots 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 300-700 on sub-$200 phones such as the Samsung A-Series. On the tool call and mobile device use benchmarks, Needle 2 trades wins with closest small models like LFM2.5 230M and Apple Foundation Model, at 5x to 70x smaller, both at f16 vs Needle 2 at 2bit. Needle is based on Simple Attention Networks from our paper ( https://ift.tt...
Post a Comment
Read more

Show HN: 100% native Swift harness (NOT Electron) https://ift.tt/TnvkqoB

Show HN: 100% native Swift harness (NOT Electron) hi everybody, I’ve been working on this harness that is all native Swift for macOS. It’s fully featured with every feature i could find in cline, codex, and claude code. There is all swift command line too It’s taking me a long, long time, a few months to build this, and it’s fully open source Apache 2 licensed. Hoping people fork this and make many branches I’m looking for people who want to work on something that has much lower memory usage and much more potential to be just more efficient. Every other single harness has is written in using electron, so this harness is really unique in this way. It’s connected to trusted router so that it has end-to-end encryption confidential mode as well as access to hundreds of models, any model in the world. It works great with Deepseek. it’s great for swift development ios development. and for people who love Linux, I also made a compatibility layer that lets you compile SwiftUI into native Linu...
Post a Comment
Read more

Show HN: Design Engineering, as a Service https://ift.tt/g1ywazb

Show HN: Design Engineering, as a Service https://ift.tt/j5bwgpG August 10, 2026 at 06:42PM
Post a Comment
Read more

Show HN: Alphabet Soup, a multiplayer game, build the longest word to win https://ift.tt/Ah8MzWO

Show HN: Alphabet Soup, a multiplayer game, build the longest word to win I've been working on a simple multiplayer word game called Alphabet Soup. It's a bit like NYT Spelling Bee, except it's multiplayer and only your best (longest) word counts toward your score. So, instead of trying to find as many words as possible, the game is more about finding one unusually good word. You can play with friends in a private match, or, you can join a public Arena match to play against other players who are online. If no one else is around, you'll be matched with a bot. The game works well with just 2 players, but, also works with bigger groups since the game isn't turn-based. https://alphabetsoup.club August 10, 2026 at 01:45AM
Post a Comment
Read more

Show HN: A replayable A2A jury for tracing how agents influence decisions https://ift.tt/SeBwNyj

Show HN: A replayable A2A jury for tracing how agents influence decisions https://ift.tt/uLRkUwN August 9, 2026 at 10:40PM
Post a Comment
Read more

Show HN: A Discord bot running in a 4MiB microVM https://ift.tt/w4gp7SV

Show HN: A Discord bot running in a 4MiB microVM https://ift.tt/HN3mFcv August 8, 2026 at 11:04PM
Post a Comment
Read more

Show HN: Algebruh - Cross-check arithmetic claims with Z3, cvc5, and Lean https://ift.tt/0faU3wL

Show HN: Algebruh - Cross-check arithmetic claims with Z3, cvc5, and Lean https://ift.tt/2iTHl3e August 8, 2026 at 11:34PM
Post a Comment
Read more