QBasic Gorillas (Repeeled)
I've found the most engaging way to practice techniques for AI-assisted development and test models is to build fun side projects in vanilla JS. I spent many hours playing (and studying and editing) QBasic Gorillas, and this is a vanilla JS implementation using Fable and Opus. Play 1-on-1 hotseat or against the computer. A bit of extra camera snazz as well.
We hid a backdoor in an LLM
Show HN: We hid a backdoor in an LLM – $51,200 on finding it
A map of cafes that are in the sun
I wanted to sit outside for coffee but there was no way to see which cafes are in the sun right now. So I built a map that shows which cafes, benches, and outdoor seats are in the sun vs. shade at any time of day. It ray-marches building shadows live in a WebGL shader over a MapLibre map. I also pre-index all places from OpenStreetMap into H3 hex cells and serve them as static JSON on Cloudflare R2, so the client just fetches the cells in view and no backend is needed. Feedback welcome, especially on shadow accuracy in your city. Currently only buildings and trees are taken into account when calculating the shadows but I'm planning to add terrain/mountain shadows as well. Try it: https://sunny.coffee
Aproov
Aproov is a marketplace that matches early-stage founders with creators for distribution deals Match with the RIGHT creators for your company, offer whatever you want/have (premium access, cash, revenue share, co-created content, other), gain real distribution, repeat. Aproov verifies each step of the process We created this because with our previous company, distribution was a real pain. So we decided to help other founders so they don't spend as much effort as we did, and they could get better and faster results and focus purely on building
Oodle.ai
Hi HN, we're Kiran and Vijay! Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it's exciting for us to show what we've built on top of that foundation: LLM Agent Observability. Given how non-deterministic agents are, storing all traces without sampling was critical for us. But these traces tend to be in the MBs, sometimes GBs - we needed to store them inexpensively. We also needed the queries and analyses to be fast. To meet both these goals, we store them in S3 in our own parquet-like file format, and query them using AWS Lambda. Since we process each span of every trace, instead of running LLM-based evals on each, we first analyze them using deterministic techniques. We detect tool failures, retries, loops, abnormal token usage, latency regressions, schema violations, sentiment, and other production signals. We've written more about the approach here: https://blog.oodle.ai/you-cant-sample-your-way-to-reliable-a... The combination of our own engine, no sampling, and deterministic processing before LLM-for-evals allows us to price at $10 per million traces, provide sub-second p99 query latency, and have healthy margins. Before building this, we used Langfuse for our own agent observability, which was 6x more expensive. Still super early, and rough around some edges, we would love your questions and feedback!
Benchmark your eng team's AI agent maturity in 5 minutes
we had hundreds of discussions with engineering leaders over the past few months, and everyone's trying to understand where they are in the AI journey. we collected all this data into a benchmark and built a free grader to let you know where you stand. you answer on a 1–5 scale (e.g., autonomy runs from "suggestions only" to "agents own multi-hour workflows across code, infra, and external systems") - takes about 5 minutes. https://agent-benchmarks.com/software-factory/ waiting for your results!
Microphone
If you are an aspiring founder, any VC will ask you this question: “why are you the only person who could solve this”. If you want to generate passive income with your side idea, get ready to enter a crowded market as everyone and their mother is shipping. Unless you have an active X account or you’re a TikTok sensation distribution is going to be tough. I just launched the trie.dev microphone beta to help folks find their edge. You yap into your phone about your ideas; Trie turns the rambling into hypotheses, then prioritizes them based on your experience and your realistic ability to distribute in that idea space — surfacing the problems only you can solve. From there you can generate creative and run Meta ads against your hypotheses straight from your phone, with zero setup, to see how real people respond. I built it initially for myself and friends as an “intake form” for running paid ads to help validate our side gig ideas. Happy to chat about how it works or the stack. Joining the waitlist will send you an email to join via TestFlight.
Adaptive Recall, persistent memory for AI assistants over MCP
Show HN: Adaptive Recall, persistent memory for AI assistants over MCP
English
Construction workers, electricians, couriers: ICE disguises to detain migrants
We beat Gemini Embedding 2 by training only 16M params (open weights)
Show HN: We beat Gemini Embedding 2 by training only 16M params (open weights)
I built a free app for New Yorkers to save money on groceries
I built this because I see that grocery savings are achievable in NYC. People usually just go to the store they're used to going to, and it's rarely worth the effort of combing through card cashback, weekly coupons, CPG rebates. Most people leave real money on the table by not stacking them, and even more don't even know that these deals are out there.... so I built a way to automate it. You can use it for free, no login, currently NYC-only with ~690 stores. I built it so that you just search whatever you want (use commas if you want to search multiple items). Or - use the AI tool to help shop for you. If you're curious, it's powered by a trained LLama model. Honest limitations are coverage and freshness. Id love some feedback on where the data looks wrong or is stale. Question for the room - what to prioritize if you're working with messy, multi-source retail/pricing data? Is freshness or coverage the top priority if you cant get a uniform response from every source? curious on what to prioritize here.
Reviving my 2001 college band with AI
25 years ago, I was approached to join a band called Fading Maize at Ripon College in Wisconsin. We did what we could with what we had. We recorded 3 albums over the next 3 years and played at as many bars and coffee shops as we could. We built a website with Microsoft Frontpage. Then we all went our separate ways, got married, had kids, focused on other things. Earlier this year I had the idea to approach the lead singer who wrote all of the lyrics and melodies to the stuff we played back then and wanted to "reimagine" everything in 2026 using AI. That's the project I want to share here! The site has a before/after player where you can flip between the original dorm-room recording and the 2026 version mid-song without losing your place, so you can hear exactly what changed. The original 2001 website is preserved and browsable at https://www.fadingmaize.com/2001, rough edges intact. On the AI question, since it's the elephant: the songs, lyrics, and arrangements are the original human work from 2001-2003. AI gets a bad rap and I can totally see why, but our case was different. We wrote the lyrics, we created the melodies, we played the parts, it just didn't sound as good as we heard it in our own heads. Being fully transparent about our use of AI, sticking tightly to our original lyrics and melodies, but making full use of AI to give us the studio, session players, and production budget we never had seemed like the right balance of concerns. I'm super proud of how it turned out and the transparency we've used along the way. Happy to discuss the audio pipeline, the site (Next.js), or what it's like to A/B your 20-year-old self!