oh well. — We make life easier.
Apologize, decide, vent — we make it easier.
What it does
oh well. was built for the moments when life gets a little too heavy. Three tools, one mission: Sorry Machine — Can't find the words to apologize? Tell us what happened, pick the tone, and we'll write it for you. Simple, detailed, or dramatic. Just Decide — Decision fatigue is real. What to eat, what to wear, what to watch — tell us your mood and we'll choose for you. Pour it Out — Sometimes you just need to get something off your chest. No judgment, no records. What you write here, vanishes.
Does the same job
all alternatives →
- OIosod.im (one sentence, one day - a one sentence journal)2012 · ▲11
I'm trying to get the motivation up to actually finish building out a "real" product, and I found myself needing a "win" to keep my momentum up. So, I hacked out a little one sentence journal app last night. I experimented with a few UI things (e.g.., the autosaving of the sentence for today and so on), so it was a good learning experience also. You can check it out at: http://osod.im
Point this at a decision you regretJun 2026 · afroakito.github.io · ▲4The thing you half-knew but never saw written down.
Benche: End Decision FatigueApr 2026 · benche.app · ▲95 intuitive choices, 6 personalized daily plan suggestions.
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 · 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, 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