Let Me Prompt It for You
Ok so over the last 9 days I built lmpify. my personal driver was i want to replace claude because it's annoying. Their Claude3.7 model is perfect for coding, but the Claude.ai interface doesn't cut it for me for these reasons: - Very slow to start up and TTFT is terrible. lmpify hits within 100ms and doesn't need to wait for pageload to start seeing result, result is already starting in DO as soon as you submit. - Claude doesn't support URLs out of the box. When i create a new app/worker, i usually add URLs as source of truth for context . with claude it was still a hassle to…
What it does
In the maker’s words, at launch
Ok so over the last 9 days I built lmpify. my personal driver was i want to replace claude because it's annoying. Their Claude3.7 model is perfect for coding, but the Claude.ai interface doesn't cut it for me for these reasons: - Very slow to start up and TTFT is terrible. lmpify hits within 100ms and doesn't need to wait for pageload to start seeing result, result is already starting in DO as soon as you submit. - Claude doesn't support URLs out of the box. When i create a new app/worker, i usually add URLs as source of truth for context . with claude it was still a hassle to copy/paste afterwards. now, this is seamless and fast. - Claude can render HTML and React. I don't use React so I don't care. I use HTML. Claude HTML renders are super limited, as they can't run scripts. LMPIFY HTML renders render scripts and anything else, and can be easily opened in fullscreen. - Claude is generally slow, buggy, and unreliable on my machine. LMPIFY is snappy / fast - It's hard to share something with someone else in claude, requires several clicks. LMPIFY is optimised for sharing - LMPIFY incentivizes people to edit the prompt rather than reply, which usually gives better and less lengthy results as token windows become shorter from it. It also incentivizes people to reduce tokens. Claude does NOT do this I think this is my main list of why I built it. I don't think it'd replace full LLM use for most, but maybe for sharing and when the edit-flow preferred. Maybe I'm the only one that needs it. IDK. Please give it a try (got some free tokens for everyone) and let me know if you find it useful for casual use!
Does the same job
all alternatives →
- IMI made Claude Code listen before it codes (MIT)Apr 2026 · github.com · ▲5
heylo! open sourcing a plugin that I've been daily driving for a month. And I promise, I can't go back to vanilla Claude Code. I'm a heavy Claude Code user, and a couple of things kept bugging me. Claude really likes to jump into code. And its responses are too long. I'd skim past walls of text just to find the recommendation. Plan mode helps, but it didn't go deep enough. The questions it asked were still implementation questions, when what I actually needed was alignment on the problem. So I made it stop. Relay is a different output style and two Python hooks. When you describe what you…
- MAMake AI motion videos with textFeb 2026 · framecall.com · ▲6
Saw the remotion claude skills launch earlier, and honestly even though I was surprised how decent some of the results turned out to be I ended up never trying it out with claude code because I knew I'd have to setup remotion, bundler etc and if I was already doing it once I thought I might as well turn it into a site where anyone could just write messages and get a video without any prerequisites. I also know Claude Code is not something everyone has and setting up remotion is a pain. And one of the biggest lessons I learned from this whole experience is that Opus is actually not that good…
- ECEnable Claude to interactively debug your code2025 · github.com · ▲7
I participated in the Nvidia + Vercel 2 hour hackathon in SF tonight, and built something I've wanted, but hadn't tried building. I implemented an MCP Server and VS Code extension to allow Claude Desktop to place breakpoints, step through code, and execute expressions (assuming language support). So you can ask it a question that requires actually stepping through the code and now it can actually do that - check values for you, etc. It's _definitely_ not perfect. Have improvements? Please make a PR!
- IRI replaced my premium workout app with vibecodeDec 2025 · strengthquest.lovable.app · ▲9
I was going through my app subscriptions and realized I was paying $15 for a pretty good workout app, which seemed a bit high to me. As a software engineer who is also well versed in claude code, I realized that I could likely vibecode a very similar app, or even build something more to my liking. I challenged my self to build something roughly equivalent this afternoon. Workflow was: start with a detailed spec from Claude code describing many of the features common in workout apps. Then paste this into lovable to have it build out the initial mvp. Once that was built, I used claude code…
- SSSpotlight shows what your Claude Code/Codex are doingJun 2026 · backplanes.com · ▲8
Hola HN! Long time lurker, sometimes commentor, first time poster here. I’ve been working alongside my two co-founders and a few colleagues on a project I’m excited (and a little nervous) to share with you all! Like many of us, I’ve lived a tortured existence with AI coding (is it vibes?) over the past few months - I think November was a big moment with this. But, one thing I’ve noticed after building orchestration layer after orchestration layer is that the thing I always came back to was “what the hell is Claude Code actually doing?” Perhaps it’s because of the time Claude Code got…
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 · 26d ago · cactuscompute.com
Launched alongside, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
