Mastodawn

@coderbyheart maybe a Copilot suggestion to solve the npm & Github Actions problem

RE: https://chaos.social/@jacqueline/116560365758303827

The world it looking for a GitHub alternative and the Gitlab CEO shouldn‘t have ask ChatGPT … maybe Perplexity which runs Claude would be better:

Show thread

choas May 12

@lehtimaeki let’s write some „corrected“ dictionary version of Gemini:

choas May 3

Effin' Birds Apr 30

ALT https://effinbirds.com/post/815343393016348672

Show thread

choas May 2

@codepo8 after iPhones, and laptops, I think cars should only be chargeable via USB-C also non-electric cars … and then houses

Show thread

choas Apr 30

@_cirrus_ noch nicht, nur 99,2% https://www.timeanddate.com/moon/phases/

Moon Phases 2026 – Lunar Calendar

Moon phases for 2026 or any year. New Moon and Full Moon calendar with precise times and simulation of the Moon phase today. When is the next Full Moon?

choas Apr 30

Windows 10 Update screens are the new bluescreen
/cc @kevlin

choas Jan 20

Writing software while sleeping to predict NFL games.
An AI agent, a Docker sandbox, and 53 minutes later: a working ML microservice.

Conference Championship predictions:
• Broncos over Patriots (100%)
• Seahawks over Rams (94%)

https://www.larsgregori.de/2026/01/20/nfl-ame-predictor-with-ralph-wiggum/
#VibeCoding #MachineLearning #NFL

Building an NFL Game Predictor While I Slept: The Ralph Wiggum Paradigm in Action

I went to bed. 53 minutes later, I had a working NFL game prediction microservice. The Ralph Wiggum paradigm turned a concept document into a deployed applic...

I'm Lars

choas Jan 8

AI writes code. AI writes tests. What could go wrong?
Mutation testing result: 85% of bugs caught.
After hiding the implementation from the AI: 92%.
Property tests found 11 real bugs all others missed.

https://www.larsgregori.de/2026/01/08/mutation-testing-the-vibes/

choas Jan 6

"Just use a different LLM for tests."

Doesn't work.

The moment any LLM sees your code, it reasons about what it does, not what it should do.

Independence needs different information, not different systems.

https://www.larsgregori.de/2026/01/06/independent-verification/

The T in vibe coding stands for testing (Part 2): What independence actually means

Using a different LLM for testing sounds like it would create independence. It doesn't. The moment any model sees your implementation, it reasons about what ...

I'm Lars