Iterate, evaluate, and monitor LLM-products in a Notion-like workspace
Hi HN! I spent the last year traveling and feeling purposeless after shutting down my last startup (Zage YC S’21) in Dec 2022. There were some obstacles I couldn’t overcome and decided to return investors 50% of their capital. To afford (and justify to myself) traveling, I started consulting as an engineer and product designer. I started (https://backspace.nyc) and it was a good time. I (and some friends) built a handful of AI experiences and learned a lot along the way. The hardest thing about running a services business shipping and selling AI experiences powered by LLMs was…
What it does
In the maker’s words, at launch
Hi HN! I spent the last year traveling and feeling purposeless after shutting down my last startup (Zage YC S’21) in Dec 2022. There were some obstacles I couldn’t overcome and decided to return investors 50% of their capital. To afford (and justify to myself) traveling, I started consulting as an engineer and product designer. I started (https://backspace.nyc) and it was a good time. I (and some friends) built a handful of AI experiences and learned a lot along the way. The hardest thing about running a services business shipping and selling AI experiences powered by LLMs was agreeing on when the prompt was good enough and ‘working’. How do we ensure trust and safety? How do we make sure that we can terminate the project, get paid, and our clients trust and ‘kind-of’ know what their users will be served? We ended up building a lot of tooling because the existing tooling (OSS and otherwise) wasn’t as mature as it is today. This tooling became more valuable than _backspace and I started Adaline. Adaline is a culmination of a year of building AI experiences with teams big and small and feeling the pains of iterating, evaluating, and monitoring LLM-powered experiences firsthand. I hope you like it. I built it with the clients from _backspace and now work on it full-time. I’m slowly onboarding new teams building AI experiences. Please let me know if you think you might find it valuable here - https://go.adaline.ai/zjSC1m3. Arsh
Does a similar job
all alternatives →- WUWe used investor tools to find the best startups to work at2022 · joinmaasive.com · ▲29
hey y'all -- can you please tell us if our job search tool sucks? :D we built it using an investor platform called Harmonic.ai to gather startup data, then contextualize it so that job seekers could find out about the most exciting startups hiring first (like if they just raised, growing headcount fast, have an ex-unicorn founder, etc). pretty sure we're the first platform doing anything like this. anyway, let me know what you think. really excited to launch this thing soon! getting feedback from the hn community first is really fun :)
- IBI built a tool to find the best and cheapest LLM models for my projects2024 · viewpointhq.com · ▲5
Hey HN, I've been working on something cool that I wanted to share with you all. It's called Viewpoint, an analytics tool for LLMs like OpenAI, Anthropic models, and Gemini. The idea came from the constant flood of new LLM models and the need to figure out which ones work best for my projects without breaking the bank. With viewpoint, I can track token usage, costs, latency(WIP), and traffic over time, making it easier to compare different models and see which ones perform best and save money. The tool works asynchronously, so it doesn't add any latency to your LLM requests, and you have…
- ICI created an AI board of directors for founders2024 · ryancarson.com · ▲5
Most of us founders won’t publicly admit it: We’re very lonely and stressed. I know from 20 years of building 4 companies (1 failure, 3 acquisitions). We can’t be truly transparent with our team, board, investors, twitter, family or friends. We want to, but can’t. No matter what we’re thinking or feeling, we have to project strength. During my entrepreneurial journey I longed for a group of always-available experts that met these criteria: 1. Experienced 2. Trustworthy 3. Kind yet extremely direct 4. Available and affordable Obviously now with LLMs like gpt-4-1106-preview, we’re unlocking…
- IBI Built a Spreadsheet of Productized Services2019 · ▲12
Hey HN, This weekend I built an excel spreadsheet so that you can come up with your next (scalable) service idea. If you are a consultant / agency and are looking to move from to build a scalable business / valuable asset, this is for you! WHY I built this: - Many people want to start their business but can't find an idea - Many people build stuff / services that nobody want - Ideas are great but execution is what matters: See what others have done successfully, get inspired, and do your own thing! The framework is called the Productized Service Matrix. --- It features in…
- IMI made an interactive LLM Tools guide2025 · readyforagents.com · ▲7
So hard to keep up with tooling and MLOps - I put it all in one place and got some tips from an experienced friend on what to use.
- RARoundtable – A rubber duck that argues with itselfDec 2025 · roundtable.ovlo.ai · ▲6
Hey HN, I'm a founder at Ovlo a supply chain company.I had a problem. After every batch of customer interviews/research/feedback sessions, I'd run ideas through an LLM to help me decide what we should build next. Except it was obvious to my cofounder I wasn't really validating anything. LLMs are incredibly good at agreeing with you in subtle ways, especially when you feed them context that already reflects your thoughts. I'd ask "Does this make sense?" and get a beautifully worded essay about why yes, obviously, this is the best thing ever. I was using AI as an echo chamber without…
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, February 2024
the whole month →
MarketingIdeas.com▲1,230Never run out of marketing ideas ever again
Growth · 2024 · marketingideas.com
