Hacker News: mihau

Korpo Clicker

mihau — Wed, 13 May 2026 16:56:56 +0000

Article URL: https://app.korpoclicker.pl

Comments URL: https://news.ycombinator.com/item?id=48124473

Points: 1

# Comments: 0

Simple Self-Distillation

mihau — Fri, 03 Apr 2026 14:19:00 +0000

Article URL: https://github.com/apple/ml-ssd

Comments URL: https://news.ycombinator.com/item?id=47626941

Points: 3

# Comments: 0

State of the Art Speech Recognition with MAI-Transcribe-1

mihau — Thu, 02 Apr 2026 18:43:30 +0000

Article URL: https://microsoft.ai/news/state-of-the-art-speech-recognition-with-mai-transcribe-1/

Comments URL: https://news.ycombinator.com/item?id=47618487

Points: 2

# Comments: 0

Voxtral TTS

mihau — Thu, 02 Apr 2026 18:05:43 +0000

Article URL: https://mistral.ai/news/voxtral-tts

Comments URL: https://news.ycombinator.com/item?id=47617990

Points: 3

# Comments: 0

LLM SQL Benchmark

mihau — Thu, 02 Apr 2026 18:02:50 +0000

Article URL: https://sql-benchmark.nicklothian.com/

Comments URL: https://news.ycombinator.com/item?id=47617945

Points: 2

# Comments: 0

Microsoft.ai

mihau — Thu, 02 Apr 2026 17:39:17 +0000

Article URL: https://microsoft.ai/

Comments URL: https://news.ycombinator.com/item?id=47617571

Points: 4

# Comments: 1

Cherri – programming language that compiles to an Apple Shortuct

mihau — Fri, 27 Mar 2026 23:39:44 +0000

Article URL: https://github.com/electrikmilk/cherri

Comments URL: https://news.ycombinator.com/item?id=47549824

Points: 355

# Comments: 74

Show HN: Record manual QA flows, get E2E test code that fits your repo

mihau — Tue, 24 Mar 2026 15:40:01 +0000

TLDR: Desktop app for E2E web test generation, built at JetBrains (closed beta). Record the flow in a built-in browser - the agent matches it with your existing codebase, then writes a test that passes, not a draft to debug.

Devs use AI to ship more code. That code still needs testing. If your team writes E2E tests by hand, you have a problem - same QA capacity, way more surface to cover.

AI agents can write E2E test code, but you're stuck describing flows in text - the agent clicks around via Playwright MCP, takes wrong turns, you re-prompt, retry. 30 minutes for a flow you could click through in 30 seconds.

Qure works differently. You record the scenario in Qure's built-in browser by just using your product. The AI turns that recording into code. No prompt engineering, no MCP setup, no explaining your repo in chat - point it at your project and go. Beyond recording, you can also refactor tests, update them, or write new ones from a description.

What keeps the AI output grounded:

- We match the recording against your codebase - find your page objects, helpers, constants and feed them to the agent instead of hoping it figures out your repo

- When agent runs the test, it reads real failure output, fixes with actual error and app context

This is a closed beta of an experimental product. Web only, works best with Playwright. If your project has a few dozen tests - Claude Code will honestly get you there. Qure makes a difference on larger codebases with existing test infrastructure.

5-min demo: https://www.youtube.com/watch?v=4CZw4bSSDCE

Try the beta: https://quretests.com

Happy to answer any questions about the approach, product, or where it breaks - I'm the dev on the Qure team. Egor (@250xp), who leads the project, is in the thread too.

Comments URL: https://news.ycombinator.com/item?id=47504297

Points: 19

# Comments: 2