Bob's Workshop
Your AI team that learns, thinks, and builds with you
What it does
AI coding tools can write snippets, but they don’t work like a real team, you still prompt, fix, re-explain, and build alone. Bob’s Workshop introduces a new way to build: a cognitive AI team that learns, thinks, and builds with you. These aren’t one-off responses, but AI teammates with memory, reasoning, and context who collaborate across your workspace to plan, code, review, and ship together.
Does a similar job
all alternatives →
- BDBlocks – Dream work apps and AI agents in minutesSep 2025 · blocks.diy · ▲13
Hi HN, We just launched Blocks - an AI platform where anyone can build custom work apps and AI agents in minutes, no coding required. We’re seeing a shift in how software is built and used. With AI, software isn’t just about tracking processes anymore - it can actively help people get work done. The problem is that most teams still face 2 options: either buy off-the-shelf tools that never quite fit, or invest a lot of time and money into custom development. Neither works well. Blocks is the third option. It’s an AI-native platform where teams can create apps and AI agents for their workflows…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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, November 2025
the whole month →
- IB
Life & fun · Nov 2025 · bitsnpieces.dev
- BBoing▲782
Life & fun · Nov 2025 · boing.greg.technology