Real problems people complain about online, pulled every morning and scored out of 100. Build, validate, or skip. How scoring works
Tool that detects AI-generated content (text, images, etc.). Growing need as creators, educators, and publishers struggle to identify synthetic content; current solutions fragmented/expensive. [Google Search suggestion]
Google Trends4mo agoToolAIUS
Tech enthusiasts and developers desperately want early beta access to advanced AI tools like Grok Build app and terminal for testing, but access is limited with no option to pay top dollar for priority inclusion.
X5mo agoToolAI
Users switch between AI services like Claude and Codex frequently, requiring endless logins and logouts which waste time and kill productivity; willing to pay 10x more for seamless management.
X4mo agoToolAI
Hi HN, I'm Erwin. I built a small free open-source utility that bridges Bluetooth LE MIDI keyboards into the new Windows MIDI Services stack so any DAW or Web MIDI app can use them as if they were wired.I bought a Roland FP-90X piano partly because it had Bluetooth MIDI. On my Windows 11 PC, pairing succeeded, but my DAW couldn't see the keyboard, and notes I sent from the PC never made the piano sing. After a regrettable number of evenings, I'd separated this into three independent bugs stacked on top of each other.The first one is the famous one: Windows only natively exposes BLE-MIDI through the WinRT API, which almost no DAW polls. So even when pairing succeeds, MIDI apps still don't see the device. The usual workaround is MIDIberry + loopMIDI, but I couldn't get that combination to work reliably in my case, and I wanted a single-app solution. The new Windows MIDI Services stack ships with a feature called loopback endpoints: anything written to one comes out the other, and any winmm/WinRT/WMS app sees them as normal MIDI ports. So the app does WinRT BLE-MIDI in, WMS loopback out. That solved direction one, piano to PC.Direction two, PC to piano, still didn't work. NoteOn writes were getting ATT-acked, but the piano stayed silent. I tried both write modes (some BLE-MIDI firmware silently drops one or the other), poked the proprietary ISSC characteristic. Every variant ATT-acked, every variant produced silence. So the bytes were reaching the piano. Something above the GATT layer was discarding them.After ruling out pairing, encryption, write-mode, and proprietary characteristics, the only obvious lever left was the MIDI channel itself. The FP-90X has a panel setting called Transmit Channel, default 1. Yet it turns out the FP-90X actually receives on channel 4 (and it can't be changed). Notes I sent on channel 1 were being GATT-acked and silently dropped at the synth engine because they weren't on the channel the e
Hacker News4mo agoToolAI
USB-C cables can be a mess. One cable charges at 5W, another does 100W and Thunderbolt 4, and they look identical in the drawer.WhatCable sits in your menu bar and reads the cable data your Mac already has access to. Plug in a cable and it tells you in plain English what it can actually do: charging wattage, data speed, display support, Thunderbolt, etc.Built in Swift/SwiftUI. Open source, free, no tracking.GitHub: https://github.com/darrylmorley/whatcable
Hacker News4mo agoToolAI
Users want to compare AI chatbots on capabilities, pricing, speed, and use cases. A dynamic comparison tool with real-time benchmarks helps teams choose the right model. [Google Search suggestion]
Google Trends4mo agoToolAIUS
I shipped a wiki layer for AI agents that uses markdown + git as the source of truth, with a bleve (BM25) + SQLite index on top. No vector or graph db yet.It runs locally in ~/.wuphf/wiki/ and you can git clone it out if you want to take your knowledge with you.The shape is the one Karpathy has been circling for a while: an LLM-native knowledge substrate that agents both read from and write into, so context compounds across sessions rather than getting re-pasted every morning. Most implementations of that idea land on Postgres, pgvector, Neo4j, Kafka, and a dashboard.I wanted to go back to the basics and see how far markdown + git could go before I added anything heavier.What it does: -> Each agent gets a private notebook at agents/{slug}/notebook/.md, plus access to a shared team wiki at team/.-> Draft-to-wiki promotion flow. Notebook entries are reviewed (agent or human) and promoted to the canonical wiki with a back-link. A small state machine drives expiry and auto-archive.-> Per-entity fact log: append-only JSONL at team/entities/{kind}-{slug}.facts.jsonl. A synthesis worker rebuilds the entity brief every N facts. Commits land under a distinct "Pam the Archivist" git identity so provenance is visible in git log.-> [[Wikilinks]] with broken-link detection rendered in red.-> Daily lint cron for contradictions, stale entries, and broken wikilinks.-> /lookup slash command plus an MCP tool for cited retrieval. A heuristic classifier routes short lookups to BM25 and narrative queries to a cited-answer loop.Substrate choices: Markdown for durability. The wiki outlives the runtime, and a user can walk away with every byte. Bleve for BM25. SQLite for structured metadata (facts, entities, edges, redirects, and supersedes). No vectors yet. The current benchmark (500 artifacts, 50 queries) clears 85% recall@20 on BM25 alone, which is the internal ship gate. sqlite-vec is the pre-committed fallba
Hacker News4mo agoToolAI
Hi HN, I'm Hugo. I've been building Rocky over the past month, shipping fast in the open. The binary is on GitHub Releases, `dagster-rocky` on PyPI, and the VS Code extension on the Marketplace. I held off on a broader announcement until the trust-system surface was coherent enough to talk about as one thing. The governance waveplan — column classification, per-env masking, 8-field audit trail on every run, `rocky compliance` rollup, role-graph reconciliation, retention policies — landed end-to-end last week in engine-v1.16.0 and rounded out in v1.17.4 (tagged 2026-04-26). That's the milestone I'd been waiting for.The pitch: keep Databricks or Snowflake. Bring Rocky for the DAG. Rocky is a Rust-based control plane for warehouse pipelines. Storage and compute stay with your warehouse. Rocky owns the graph — dependencies, compile-time types, drift, incremental logic, cost, lineage, governance. The things your current stack can't give you because it doesn't own the DAG.A few things I think are interesting:- Branches + replay. `rocky branch create stg` gives you a logical copy of a pipeline's tables (schema-prefix today; native Delta SHALLOW CLONE and Snowflake zero-copy are next). `rocky replay <run_id>` reconstructs which SQL ran against which inputs. Git-grade workflow on a warehouse.- Column-level lineage from the compiler, not a post-hoc graph crawl. The type checker traces columns through joins, CTEs, and windows. VS Code surfaces it inline via LSP.- Governance as a first-class surface. Column classification tags plus per-env masking policies, applied to the warehouse via Unity Catalog (Databricks) or masking policies (Snowflake). 8-field audit trail on every run. `rocky compliance` rollup that CI can gate on. Role-graph reconciliation via SCIM + per-catalog GRANT. Retention policies with a warehouse-side drift probe.- Cost attribution. Every run produces per-model cost (bytes, duration). `[budget]` blocks in `rocky.toml`;
Hacker News4mo agoToolAI
When building workflows that rely on LLMs, we commonly use structured output for programmatic use cases like converting an invoice into rows or meeting transcripts into tickets or even complex PDFs into database entries.The model may return the schema you want, but with hallucinated values like `invoice_date` being off by 2 months or the transcript array ordered wrongly. The JSON is valid, but the values are not.Structured output today is a big part of using LLMs, especially when building deterministic workflows.Current structured output benchmarks (e.g., JSONSchemaBench) only validate the pass rate for JSON schema and types, and not the actual values within the produced JSON.So we designed the Structured Output Benchmark (SOB) that fixes this by measuring both the JSON schema pass rate, types, and the value accuracy across all three modalities, text, image, and audio.For our test set, every record is paired with a JSON Schema and a ground-truth answer that was verified against the source context manually by a human and an LLM cross-check, so a missing or hallucinated value will be considered to be wrong.Open source is doing pretty well with GLM 4.7 coming in number 2 right after GPT 5.4.We noticed the rankings shift across modalities: GLM-4.7 leads text, Gemma-4-31B leads images, Gemini-2.5-Flash leads audio.For example, GPT-5.4 ranks 3rd on text but 9th on images.Model size is not a predictor, either: Qwen3.5-35B and GLM-4.7 beat GPT-5 and Claude-Sonnet-4.6 on Value Accuracy. Phi-4 (14B) beats GPT-5 and GPT-5-mini on text.Structured hallucinations are the hardest bug. Such values are type-correct, schema-valid, and plausible, so they slip through most guardrails. For example, in one audio record, the ground truth is "target_market_age": "15 to 35 years", and a model returns "25 to 35". This is invisible without field-level checks.Our goal is to be the best general model for deterministic tasks, and a key aspect of determinism is a con
Hacker News4mo agoToolAI
ohai!I've released Lightwhale 3, which is possibly the easiest way to self-host Docker containers.It's a free, immutable Linux system purpose-built to live-boot straight into a working Docker Engine, thereby shortcutting the need for installation, configuration, and maintenance. Its simple design makes it easy to learn, and its low memory footprint should make it especially attractive during these times of RAMageddon.If this has piqued your interest, do check it out, along with its easy-to-follow Getting Started guide.In any event, have a nice day! =)
Hacker News4mo agoToolAI
Hi HN Community, I'm Venkatram, a sophomore who's on a mission to build a local alternative to proprietary third-party AI-based research assistants.The idea is to turn documents into researchable assets that contain as much as information as the original information does, but it's more reusable.Well, quite frankly, this is still under a WORK IN PROGRESS, so i'm still figuring on how it can be properly used, and I got to be honest here, i definitely need some help to build this, so if you wish, you are welcome!TlDR: NotebookLM, but Locally with your OWN AI ModelGithub: https://github.com/venkatram-s/gigabook-lm
Hacker News4mo agoToolAI
Give your user a game while they wait for the LLM to return a result.
Hacker News4mo agoToolAI
Hey HN, JSS(JumpstartSignal) is a free, ESG-filtered daily stock screener. I built it after some really badly-timed quantum computing stock buys, so I felt I needed to learn more about systematic, longer-horizon approaches and the underlying technicals instead of chasing themes. Three things about it that might be of interest:1. Methodology is fully documented at https://jumpstartsignal.com/how-it-works/ 5-stage pipeline, 54 signals tested individually plus 1,836 combinations evaluated, walk-forward validation across 25 hold periods. Nothing hand-tuned to a single backtest window.2. Many wins, misses, and losses are published as case studies e.g. https://jumpstartsignal.com/case-studies/nvda/ walks through the 32 times the system flagged NVDA starting at $5.44 in 2018. https://jumpstartsignal.com/case-studies/sedg/ shows a -49% loss, and https://jumpstartsignal.com/case-studies/tsla/ explains why the system never flagged Tesla (it passed Stages 1 and 2 on 207 days but only peaked at 20/100 in scoring vs the 70 needed for OPPORTUNITY tier). https://jumpstartsignal.com/results/ also shows the 10 best entries alongside the 10 worst.3. A genetic algorithm picked the signal weights, but constrained to maintain alpha across multiple market regimes (otherwise it overfits to a single bull market). The constraint dropped some "best in backtest" configurations that only worked 2018-2021.Topline: 2012-2025 backtest at SPOTLIGHT + OPPORTUNITY tier produced +163% alpha vs SPY (results page has the per-trade breakdown).Daily watchlist emailed free; reports + results + case studies are publicly browsable without signup.Happy to take questions about methodology, what the system gets wrong, or why specific tickers landed where they did.
Hacker News4mo agoToolAI
Hi HN, Francesco from Cua here. I hacked this project together last weekend, inspired by the Codex Computer-Use release and lessons learned from deploying GUI-operating agents for our customers.The main problem: when a UI automation process controls a desktop app today, it usually takes over the human’s session. Your cursor moves, keyboard focus gets stolen, windows jump to the front, and you have to stop working until the agent is done. That is why we have historically avoided encouraging users to run these processes directly on their host machine, instead relying on VMs or GUI containers for concurrency and background execution.But computer-use - the tools we give agents to operate computers like humans - does not scale cleanly that way. As models get smarter, agents need to share hosts safely, run in the background, and avoid collisions with the human or other agents using the same machine.We realized macOS has no first-class API for "drive this app without touching the cursor". CGEventPost routes through the hardware input stream, so it moves your cursor. CGEvent.postToPid avoids the cursor warp, but Chromium treats those events as untrusted and silently drops clicks at the renderer boundary. Activating the target app first raises the window and pulls focus, defeating the point of background execution.Cua Driver is our attempt at a real fix: a background computer-use driver for macOS that lets an agent click, type, scroll, and read native apps while your cursor, frontmost app, and Space stay where they are. The default interface is a CLI, so it is easy to script or call from any coding agent shell.Try it on macOS 14+:/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/cua-d...)"The first internal use case was delegated demo recording. We ask Claude Code to drive an app while 'cua-driver recording start' captures the trajectory, screenshots, actions, and click
Hacker News4mo agoToolAI
Today I saw that post about AI destroying the future of West software. I remembered I am having a similar struggle with my jobs.Right now my life is like this: some company lost their senior, they hire me to replace. They expect me to produce code with same speed and same quality in 2 months.Then they realize they are late actually (one company for example was 6 months late to deliver to clients) and want me to use AI to churn out code even faster.Meanwhile I find out they lost all people that knew how things actually worked, there is no documentation, or worse, the documentation is outright wrong ( one project I worked had thousands of Jira tickets generated from a requisites document. After some months of politicking I got permission to see the requisites document and learned it was from another project entirely, they wasted years coding with the wrong requisites outright! )Then as I get close to the end of probation period, the company tried some kind of hail Mary, one company thought maybe I would be more useful if they fired their DevOps and asked me to do the job of the senior engineer that had quit, the fired DevOps, and learn Go (I was hired as C dev, not even CPP) in 2 weeks. Then when the absurd hail mary fails I get fired.For a while I have been trying again and again with always same results, tried to see what I was doing wrong, and now I concluded I am looking for a job in the wrong places.Every time I got fired the same criticism happened: I spent too much time going into "rabbit holes" and figuring out details of legacy code or debugging or fixing things or refactoring, and not enough time just shipping code fast enough to appease clients. I keep trying to change this behavior and fail, maybe I should instead find a job where this behavior is something good instead of something bad, but I have no idea where to look.
Hacker News4mo agoToolAI
The standard GPU utilization metric reported by nvidia-smi, nvtop, Weights & Biases, Amazon CloudWatch, Google Cloud Monitoring, and Azure Monitor is highly misleading. It reports the fraction of time that any kernel is running on the GPU, which means a GPU can report 100% utilization even if only a small portion of its compute capacity is actually being used. In practice, we've seen workloads with ~1–10% real compute throughput while dashboards show 100%.This becomes a problem when teams rely on that metric for capacity planning or optimization decisions, it can make underutilized systems look saturated.We're releasing an open-source (Apache 2.0) tool, Utilyze, to measure GPU utilization differently. It samples hardware performance counters and reports compute and memory throughput relative to the hardware's theoretical limits. It also estimates an attainable utilization ceiling for a given workload.GitHub link: https://github.com/systalyze/utilyzeWe'd love to hear your thoughts!
Hacker News4mo agoToolAI
Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent's reasoning.This implementation experiments with a biological approach by using the Ebbinghaus forgetting curve to manage context as a living substrate. Memories are assigned a "strength" score where each recall reinforces the data and flattens its decay curve (spaced repetition), while unused data eventually hits a threshold and is pruned.To solve the "logical neighbor" problem where semantic search misses relevant but non-similar nodes, a graph layer is layered over the vector store. Benchmarked against the LoCoMo dataset, this reached 52% Recall@5, nearly double the accuracy of stateless vector stores, while cutting token waste by roughly 84%.Built as a local first MCP server using DuckDB, the hypothesis is that for agents handling long-running projects, "what to forget" is just as critical as "what to remember." I'd be interested to hear if others are exploring non-linear decay or similar biological constraints for context management.GitHub: https://github.com/sachitrafa/cognitive-ai-memory
Hacker News4mo agoToolAI
I've been reading up on crawler architecture. The two most useful sources I've found are the blog post "Crawling a billion web pages in just over 24 hours, in 2025" and the Mercator paper ("Mercator: A Scalable, Extensible Web Crawler").Both of these, and most other material I've come across, focus on crawling the broad open web rather than a targeted set of domains. For product prices it's the latter. Mercator calls out DNS resolution as a major bottleneck, for example, but when you're only hitting a few hundred domains that isn't really a concern.The other gap is that both assume static HTML. For our use case we need a headless browser, and we also have to deal with Cloudflare and similar anti-bot systems.For product prices specifically, a lot of sites publish price feeds which simplifies things, but plenty don't, and getting good coverage still requires scraping. Our current system does about 500M pages/day and we're looking to improve its performance.Does anyone here have experience in this space, or know of articles/blog posts on scaling targeted (rather than broad) crawlers with headless browsers? Any pointers appreciated.
Hacker News4mo agoToolAI
Hey HN - I first posted about my knowledge base product, Atomic, here around a month ago; since then, a viral tweet by Karpathy has produced a torrent of AI powered knowledge base projects. meanwhile I've been shipping like crazy, here are some of the new features shipped in the last month:- Rebuilt the iOS app with an Android app on the way- expanded both the MCP and internal agent chat toolkit immensely- A custom, CodeMirror6-based markdown editor with obsidian-style rendering- A dashboard view that provides a daily summary of atoms created or updated in the last dayAnd many bug fixes and improvements across the board. Atomic is MIT licensed. You can download the desktop app, but the true power is unlocked by self hosting an atomic server, which any client (web, mobile, or desktop) can connect to from anywhere. You can add content to your knowledge base directly, or via RSS feed, web clipper, mobile share capture, obsidian sync, or REST api.
Hacker News4mo agoToolAI
Hey there! I am Luca, I write https://refactoring.fm/ and I built Tolaria for myself to manage my own knowledge base (10K notes, 300+ articles written in over 6 years of newslettering) and work well with AI.Tolaria is offline-first, file-based, has first-class support for git, and has strong opinions about how you should organize notes (types, relationships, etc).Let me know your thoughts!
Hacker News4mo agoToolAI