Feed aggregator

Article URL: https://twitter.com/auxten/status/2025957620994199690

Comments URL: https://news.ycombinator.com/item?id=47124094

Points: 1

# Comments: 0

Article URL: https://github.com/mixpeek/amux

Comments URL: https://news.ycombinator.com/item?id=47124064

Points: 1

# Comments: 0

Article URL: https://github.com/koala73/worldmonitor

Comments URL: https://news.ycombinator.com/item?id=47124040

Points: 1

# Comments: 1

Article URL: https://www.theguardian.com/business/2026/feb/23/ai-how-will-we-be-fed

Comments URL: https://news.ycombinator.com/item?id=47124025

Points: 1

# Comments: 0

Article URL: https://lunnova.dev/articles/rocm-711-you-can-not-build/

Comments URL: https://news.ycombinator.com/item?id=47124020

Points: 2

# Comments: 0

Article URL: https://blog.alcazarsec.com/tech/posts/portable-secret

Comments URL: https://news.ycombinator.com/item?id=47124008

Points: 1

# Comments: 1

Article URL: https://www.codastory.com/disinformation/first-they-came-for-the-journalists/

Comments URL: https://news.ycombinator.com/item?id=47124007

Points: 2

# Comments: 0

Article URL: https://spaceygames.itch.io/cyber-blast-x

Comments URL: https://news.ycombinator.com/item?id=47124004

Points: 2

# Comments: 0

Article URL: https://oxc.rs/docs/learn/performance

Comments URL: https://news.ycombinator.com/item?id=47124003

Points: 2

# Comments: 0

SpecterQA is an open-source CLI for behavioral testing. Instead of writing test scripts with selectors, you define personas (YAML) and journeys (goals). The engine launches a real browser via Playwright, screenshots the page, sends it to Claude's vision model, and the AI decides what to click/type/scroll. Loop until done or stuck.

The idea: test scripts break when markup changes. Vision-based tests break when the UX actually breaks.

Personas have attributes like technical comfort, patience, and role that shape navigation behavior. A "frustrated non-technical admin" navigates differently than a "power user developer."

pip install specterqa specterqa init specterqa run -p demo Cost: ~$0.30-$3.00/run depending on journey length. Built-in budget caps. Requires Anthropic API key.

Previously called GhostQA — we rebranded after discovering ghostqa.com exists as an AI testing company. Clean break, no confusion.

GitHub: https://github.com/SyncTek-LLC/specterqa

MIT license. Alpha (v0.3.0). Feedback welcome.

Comments URL: https://news.ycombinator.com/item?id=47124000

Points: 1

# Comments: 0

Article URL: https://groups.google.com/g/syzkaller/c/EOcnMJmX9NI

Comments URL: https://news.ycombinator.com/item?id=47123988

Points: 1

# Comments: 0

Article URL: https://alexwlchan.net/2026/perceptual-colour-headers/

Comments URL: https://news.ycombinator.com/item?id=47123982

Points: 2

# Comments: 0

Article URL: https://instadeq.com/blog/posts/no-code-history-peridot-uis-by-example-visual-programming-constraints-1987/

Comments URL: https://news.ycombinator.com/item?id=47123981

Points: 3

# Comments: 0

I built TTSLab — a free, open-source tool for running text-to-speech and speech-to-text models directly in the browser using WebGPU and WASM.

No API keys, no backend, no data leaves your machine.

When you open the site, you'll hear it immediately — the landing page auto-generates speech from three different sentences right in your browser, no setup required.

You can then try any model yourself: type text, hit generate, hear it instantly. Models download once and get cached locally.

The most experimental feature: a fully in-browser Voice Agent. It chains speech-to-text → LLM → text-to-speech, all running locally on your GPU via WebGPU. You can have a spoken conversation with an AI without a single network request.

Currently supported models: - TTS: Kokoro 82M, SpeechT5, Piper (VITS) - STT: Whisper Tiny, Whisper Base

Other features: - Side-by-side model comparison - Speed benchmarking on your hardware - Streaming generation for supported models

Source: https://github.com/MbBrainz/ttslab (MIT)

Feedback I'd especially like: 1. How does performance feel on your hardware? 2. What models should I add next? 3. Did the Voice Agent work for you? That's the most experimental part.

Built on top of ONNX Runtime Web (https://onnxruntime.ai) and Transformers.js — huge thanks to those communities for making in-browser ML inference possible.

Comments URL: https://news.ycombinator.com/item?id=47123980

Points: 1

# Comments: 1

The Everest ransomware group has taken credit for a hacker attack on Vikor Scientific, now called Vanta Diagnostics.

The post US Healthcare Diagnostic Firm Says 140,000 Affected by Data Breach appeared first on SecurityWeek.

Article URL: https://ionanalytics.com/wp-content/uploads/2026/02/The_Wrong_Apocalypse.pdf

Comments URL: https://news.ycombinator.com/item?id=47123180

Points: 1

# Comments: 0

Hi HN, I published a small open-source wrapper for Kiro CLI that prevents it from accessing your project's sensitive files (secrets, credentials, properties) at the OS level. Feel free to test it, share feedback, or contribute!

Comments URL: https://news.ycombinator.com/item?id=47123175

Points: 1

# Comments: 0

Pay attention to the snow on your roof. If you don't clear it off in a timely manner, you're asking for trouble.

Article URL: https://www.0xsid.com/blog/accelerated-ai-fomo

Comments URL: https://news.ycombinator.com/item?id=47123163

Points: 1

# Comments: 0