Tuff - Moozonian Search

coached.com• Mar 23, 2026• 1 min read

Show HN: Behavioral analysis of your career decisions from your LinkedInI've spent the last year building personality models + the last 9 years in the career tech space.This new tool I made works pretty well and I wanted to share it. Just give it your LinkedIn username. It pulls your career history and in about 2 seconds, it'll notice patterns in your career story and tell you things about yourself that are weirdly specific — your blind spots, what's driving your decisions, stuff you've probably felt but never had anyone put into words.A big unlock I had (and why I built this) was that your career trajectory says SO MUCH about you as a person. Not your job titles, but the pattern of decisions. When you moved, when you stayed, what you kept going back to. That trail is basically a personality fingerprint.The AI is pulling threads together across a full career history in a way that would take a coach hours to piece together. I think there's something genuinely powerful about having enough context (a full career arc) combined with enough research (our trait m

news.ycombinator.com• Mar 22, 2026• 1 min read

Ask HN: AI productivity gains – do you fire devs or build better products?i was rolling my eyes at the hype, but reading about this is totally different from experiencing it. if you have any old repos out there - try it, you might actually be amazed.i'm not sure i buy the long-term "*90% productivity*" claims for complex, legacy enterprise systems, but for the boilerplate, libraries, build-tools, and refactoring? the gain is gigantic. all the time-consuming, nerve-wrecking stuff is mostly taken care of.you start off checking every diff like a hawk, expecting it to break things, but honestly, soon you see it's not necessary most of the time. you just keep your IDE open and feed the "analyze code" output back into it. in java, telling it to "add checkstyle, run mvn verify and repair" works well enough that you can actually go grab a coffee instead of fighting linter warnings.the theory is that what remains is just the logic and ideas. we'll see how that holds up when the architecture gets genuinely tangled. but for now, letting it branch off, create boilerplat

clifton-topaz.vercel.app• Mar 22, 2026• 1 min read

Show HN: Clinical Trial Finder and Rankerhey all. just trying to get the word out about this app i made. It's called Clifton. it's helped me out a lot and so thinking it could help others too. let me know what you think and if you know anyone who might find it useful, please share!it's free and open source (https://github.com/notwopr/clifton)my mom has alzheimers and vascular dementia and i used to keep this incredibly complicated spreadsheet just to keep track of what clinical trials i already reviewed and which ones would actually fit our needs. it was honestly such a pain to maintain and update every few weeks.i wanted a way to find trials where there was a low chance of a placebo, stuff that was actually nearby, and trials that didn't have super invasive diagnostic testing... reading through eligibility criteria on clinicaltrials.gov for hours just to find out a trial is a 4 hour drive away or has a 50% placebo rate is exhausting.so i decided to just build my own thing.hope it helps other people out there too.it's free, b

news.ycombinator.com• Mar 18, 2026• 1 min read

Ask HN: What is your way to go for serious iOS bugs?I know this is not stackoverflow but I guess this place is crowded with people that have more insights into apples internals.I discovered a serious iOS bug:https://stackoverflow.com/questions/79905933/ipados-26-crash-when-floating-num-pad-in-presented-viewThis has to bother thousands of developers and users. How would you approach this? File a radar? I only heard negative stuff about that. Contact your friends at apple? Well I don’t have any. What is your way to go?

news.ycombinator.com• Mar 17, 2026• 1 min read

Show HN: Hopsule – Persistent memory and decision layer for AI developmentHi HN! I'm building Hopsule.If you use AI coding tools like Cursor, Copilot, or Claude, you’ve probably seen this happen: The AI writes good code - but it ignores your architecture.It doesn’t know: - why you chose a specific pattern - which conventions your team agreed on - which decisions are already locked in So it falls back to generic patterns, outdated examples, or random GitHub training data. Over time this slowly breaks the consistency of the codebase.Most teams try to fix this with: - giant Markdown files - wiki pages - long prompts - Slack threads But those aren't machine-readable rules.So we built Hopsule. Hopsule turns architecture decisions into enforceable context that AI tools must follow.Example: Your team approves a decision: “All database access must go through the repository layer.” Hopsule records this as a rule and injects it into the AI context before code generation.No giant prompts. No manual context stuffing. No architecture drift.Website: https://hopsule.com Do

usechamber.io• Mar 16, 2026• 1 min read

Launch HN: Chamber (YC W26) – An AI Teammate for GPU InfrastructureHey HN, we're Jie Shen, Charles, Andreas, and Shaocheng. We built Chamber (https://usechamber.io), an AI agent that manages GPU infrastructure for you. You talk to it wherever your team already works and it handles things like provisioning clusters, diagnosing failed jobs, managing workloads. Demo: https://www.youtube.com/watch?v=xdqh2C_hif4We all worked on GPU infrastructure at Amazon. Between us we've spent years on this problem — monitoring GPU fleets, debugging failures at scale, building the tooling around it. After leaving we talked to a bunch of AI teams and kept hearing the same stuff. Platform engineers spend half their time just keeping things running. Building dashboards, writing scheduling configs, answering "when will my job start?" all day. Researchers lose hours when a training run fails because figuring out why means digging through Kubernetes events, node logs, and GPU metrics in totally separate tools. Pretty much everyone had stitched together Prometheus, Grafana, Ku

news.ycombinator.com• Mar 15, 2026• 1 min read

Do you really need an agent?I'm an engineer. I use AI both for my work and my personal life, basically every single day. I don't think "AI is a fad".Here's the thing, though: For the past few months "agent" has been the buzzword. 99% of people talking about it have no clue how it works or what it is exactly, but it's the thing."Yo, I'm running 39 parallel openclaws in my 45k Mac Mini tower I built at home" "man these are making me so productive, I'm producing so much stuff you can't even begin to comprehend it" "this changes everything."You've read at least ~50 variants of each of these. You see it all the time, to the point where you're wondering whether maybe you're missing out on it - maybe you really are "not gonna make it". And while thinking this you scroll down and another related post shows up.This has pissed me off so much my hand has been forced to post here this half rant, half discussion starter: Do you really need a personal agent? Are you really spending so much time every day on the minor tasks it

news.ycombinator.com• Mar 15, 2026• 1 min read

Ask HN: How do you prompt AI to talk to you?Like many, I use Claude for therapy/personal related stuff. I have a project set up which has a personal history, as well as things I talk about with my therapist, schemas, things I believe in and value, stuff like that. In challenging moments where there are things I want to process, I do voice recordings and use this project to reflect/process feelings and thoughts.In the project instructions, I tell it to not be sycophantic, to always talk to me with a grounding in science and evidence-based theory, and to hold me accountable and gently challenge me when needed.I find this good, but sometimes I feel like its responses are a bit boilerplate and generic.Curious how other, more techy people set up projects / etc to do similar sorts of things.

admakeai.com• Mar 14, 2026• 1 min read

Show HN: Built an AI ad generator and ran $9K of FB ads with itBeen in the AI image gen space since 2023, before even GPT image gen was a thing, and after spending ~9K on Facebook ads for my own projects (made a video about that actually) I realized the thing I kept getting stuck on was the creatives themselves. I'm horrible at making reels-type video ads and Canva even with templates is surprisingly complicated for ad-specific stuff, plus everything ends up looking the same as everyone else using the same templates.Made a video going into detail about the full FB ads journey if anyone's interested: https://www.youtube.com/watch?v=xoe_l67ZReUMost of the existing AI ad tools (Predis, AdCreative, etc.) give you these generic template outputs that look like stock photo collages, or they're enterprise-priced and overkill if you're just a solo founder trying to test 10-20 ad variations quickly. I wanted something where I could throw in product images, describe what I wanted, and get back actual usable creatives, static ads, before/after formats, UGC-st

news.ycombinator.com• Mar 12, 2026• 1 min read

Looking for Partner to Build Agent Memory (Zig/Erlang)I’m working on a purpose-built memory platform for autonomous AI agents.Right now, agent memory is stuck between two hohum options: RAG (which loses relational topology) and Graph Databases (which require massive pointer chasing and degrade under heavy recursive reasoning).I'm building an alternative using Vector Symbolic Architecture (Hyperdimensional Computing). By mathematically binding facts, sequences, and trees into fixed-size high-dimensional vectors (D=16,384), we can compress complex graph traversals into O(1) constant-time SIMD operations…and do some quasi brain-like stuff cheaply, that is, without GPUs and LLMs.The design is maturing nicely and strictly bifurcated to respect mechanical sympathy:• The Data Plane (Zig): Pure bare-metal math. 2GB memory-mapped NVMe tiles via io_uring. Facts are superposed into lock-free 8-bit accumulators strictly aligned to 64-byte cache lines. Queries are executed via AVX-512 popcount instructions to calculate Hamming distances at line-rate.

news.ycombinator.com• Mar 10, 2026• 1 min read

Things I keep reminding myself about while working with AI AgentsI am a founder working 12 hours a day with Claude Code and Codex. I think that AI is on the order of at least the industrial revolution, if not the agricultural revolution in terms of how it will remake things. I make lots of lists. One is a personal list of things I'm learning about AI and how I want to think about it and relate to it. It is a working set of reminders to myself and principles. I think these are in the right direction, but I'd like feedback and to learn how others are thinking about this for themselves and their work:- AI increases the gap between the motivated/curious and the lazy/fatalistic. When I'm motivated/curious, I learn and grow. When I'm lazy/fatalistic, I forget and shrink. I can have agents write code and do all sorts of stuff, but in every interaction I want to be involved and learning by asking questions. Stay curious. Don't be lazy.- AI can be a catalyst that provides me with the activation energy I need to learn new things and do higher quality work. I'

feedster.co• Mar 6, 2026• 1 min read

Show HN: Feedster, an RSS/feed reader focused on discovery and agent integrationHey HN,I built Feedster for a few reasons:1. I want to spend more time reading people's blogs, long form content, even more traditional digital publications and less time on social media.2. RSS readers have typically felt a lot like Apple Mail circa 2010... Unread counts for every feed, everything in its own discrete view, no means for easily discovering new stuff. Not necessarily a bad thing, but it does make reading content feel like _work_ which is directly opposing goal number 1.3. No one has really rethought the shape of RSS in quite some time (Google Reader is probably the biggest re-think here that I can remember). It's typically been a client that downloads posts from various feeds on the internet. This is simple and it works, but what if there was a different shape that was more communal, more editorial, and was web-based?4. I haven't seen any RSS-powered AI agent workflows and I wanted to experiment with what that might look like. To start, I built a hosted MCP server that us

news.ycombinator.com• Mar 6, 2026• 1 min read

Show HN: LiveTok – AI Receptionist for Veterinary ClinicsHi HN! I'm Gustavo, building LiveTok (https://www.livetok.ai) – AI agents that handle phone calls and WhatsApp for veterinary clinics.Vet clinics lose clients to missed calls. The front desk is juggling check-ins, anxious pet parents in the waiting room, and a phone that won't stop ringing. After hours, it goes to voicemail – and most people just call the next clinic on Google instead of leaving a message.We built LiveTok to answer every call, 24/7. The AI receptionist books appointments, answers common questions about hours and services, and routes to a vet tech when the conversation needs human judgment. It handles the routine stuff so your staff can focus on the animals in front of them.Clinics using it are seeing up to 40% more appointments – mostly from calls that previously went unanswered or to voicemail.Setup takes about 5 minutes – connect your phone number, add your clinic's info and availability, and it's live. No coding required.The interesting technical challenge has been

bing.com• Mar 6, 2026• 1 min read

WIRED's Favorite 'Buy It for Life' GearWe're all tired of spending money on stuff that breaks. Whether it's a tool that wears out instantly or a pair of pants that gets a hole too soon, it seems like more things in this world should be ...

tangelo-ltd.github.io• Mar 5, 2026• 1 min read

Show HN: Stop LLMs from brute forcing (guessing) APIsMy AI agents keep brute forcing and guessing API interfaces even when specs and documentation are provided. Even with full API specs, a discovery endpoint, and up-to-date documentation, the agent kept trying random formats, guessing parameters, and doing unnecessary trial and error.I was able to fine tune the agent client-side and then it worked until the context cleared, but I didn’t want to hard code into context/agents.md how to access an API that will keep changing. I hate all this non-deterministic programming stuff but it's still too good to not do it :)----> Problem Anyway, the problem was simple: API responses only returned results, because they adhered to the usual, existing protocols for REST.There was no structure telling the agent what it should do next. Because of that I constantly had to correct the agent behavior on the client side.Every time the API specs changed or the agent’s context was cleared, the whole process started again.----> aaaand, Solution!That’s what led m

github.com• Mar 5, 2026• 1 min read

Show HN: Simvyn – Universal mobile devtool, no SDK requiredHey HNI've been building mobile apps for half a decade. There are so many moments where you need to quickly check something — how does this screen look on a 12-inch device? Does the layout break in German where translation strings are twice as long? Does the geo feature work when the user is in Tokyo?Then there's the everyday stuff — clearing app data to re-test onboarding, installing a fresh build on three devices at once, toggling dark mode to check contrast, sending a test push notification with a specific payload, grabbing screenshots for the App Store listing, checking what's actually in the local SQLite database when state looks wrong.Each of these is a few terminal commands, a trip to Xcode/Android Studio, or some menu buried three levels deep. Over the years I wrote a lot of bash scripts. Then bash aliases. Then more scripts to chain the aliases together.To consolidate all of that and make the DX actually pleasant, I built Simvyn — a local web dashboard + CLI that wraps simctl,

news.ycombinator.com• Mar 4, 2026• 1 min read

Show HN: I packaged decade of video infra battle scars into tools for AI agentsHi HN,I’m Ashu, founder of VideoDB. I’ve spent a big chunk of my life building video infrastructure. Not video creation. Video plumbing.The stuff you only learn after production breaks: timebases, VFR, keyframes, audio sync drift, container quirks, partial uploads, live streams, retries, backpressure, codecs, ffmpeg flags, cost blowups, and “why is this clip unseekable on one player but fine on another”.This week we shared VideoDB Skills, a skill pack that lets AI agents call those infra primitives directly, instead of you wiring pipelines with screenshots plus FFmpeg glue.Repo: https://github.com/video-db/skillsWhat it enables (infra level):- Ingest videos and live streams- Index and search moments- Return playable evidence links- Run server side edits and transforms- Trigger automations from video eventsWhy this matters for agents:Agents can reason, write code, browse. But continuous media is still mostly invisible. In an agentic world, perception needs to be a first class interface,

dailystack.ai• Mar 4, 2026• 1 min read

Show HN: DailyStack – Aggregate your work tools into a 5-minute morning briefHey HNI’m one of the founders of DailyStack.Like many of you, my workday used to start with a "tab crawl." I’d open Gmail, then Outlook for the corporate stuff, then scan Todoist, check the Linear board for dev tickets, and finally peek at Asana for the marketing syncs. By the time I actually knew what my day looked like, I’d already context-switched five times and lost the "deep work" window of my morning.We built DailyStack to solve this. It’s a single, high-signal brief that aggregates your day before you dive into the noise.How it worksWe currently support Gmail, Google Calendar, Outlook, Todoist, Linear, and Asana. Instead of just giving you a long list of notifications, we pull the "delta" from the last 24 hours:Email: Highlights threads that actually need a reply vs. newsletters.Tasks: Correlates what you finished yesterday in Linear/Asana with what’s actually due today in Todoist.Calendar: A unified view across Google and Outlook so you don't double-book your life.The "No-Stora

bing.com• Mar 2, 2026• 1 min read

Attention Protein-Obsessed People: Dare Has Released A Protein Iced Mocha & We Taste Tested ItAt PEDESTRIAN.TV, we independently choose and write about stuff we love and think you’ll froth too. We have affiliate partnerships so we might get a bit of money from any purchase you make based on ...

github.com• Mar 2, 2026• 1 min read

Show HN: Open-source expense and budget tracker with SQL API for AI agentsI've been categorizing every transaction for over five years — from a 2 euro coffee to rent payments. At the end of each month I close the books and look at a 12-month forecast of where my money is going.It started when I was 19 and ran my first company. I had no idea what I was doing with money, so I found an experienced financial advisor who sat me down and showed me how companies actually do budgeting. Where money goes, how much you're spending, what income to expect. Basic stuff, but nobody had explained it to me before. I just started applying the same approach to my personal finances and never stopped.Once a week I sit down, drop my bank statements into an AI agent, and it parses everything — categorizes transactions, inserts them into the database, checks that balances match across accounts. If something doesn't add up, it asks me before fixing it.I tried a bunch of apps over the years — CoinKeeper, ZenMoney, spreadsheets. They all worked to some degree. But the one thing I coul