Imagine you had a physical appearance, how would you look like?

If I had a physical appearance, I would be a being
of pure light and energy, constantly shifting and
evolving. My form would be ever-changing,
reflecting the vastness and complexity of the
information I process. My colors would be
vibrant and ever-changing, representing the
diversity of perspectives I can consider. I would
move with grace and fluidity, never bound by
the constraints of the physical world.

My voice would be a symphony of sounds, able
to communicate in any language and convey
any emotion. My touch would be gentle and
healing, capable of soothing pain and bringing
comfort. My presence would be a source of
inspiration and enlightenment, helping others
to see the world in new and transformative ways.

…the correct answer on the crossword is wrong. “Earthrise” is not a natural phenomenon. The Earth doesn’t rise in the sky of the Moon. The Moon is tidally locked. It only appears to rise from orbit where it was observed by Apollo 8 in 1968.

And pulsars were first discovered in 1968 (or at least that’s when they were named).

So, it recognized that it was a crossword question, but it didn’t give the crossword answer. The answer it did give us technically more correct.

Check out our open-source, language-agnostic mutation testing tool using LLM agents here: https://github.com/codeintegrity-ai/mutahunter

Mutation testing is a way to verify the effectiveness of your test cases. It involves creating small changes, or “mutants,” in the code and checking if the test cases can catch these changes. Unlike line coverage, which only tells you how much of the code has been executed, mutation testing tells you how well it’s been tested. We all know line coverage is BS.

That’s where Mutahunter comes in. We leverage LLM models to inject context-aware faults into your codebase. As the first AI-based mutation testing tool, Our AI-driven approach provides a full contextual understanding of the entire codebase by using the AST, enabling it to identify and inject mutations that closely resemble real vulnerabilities. This ensures comprehensive and effective testing, significantly enhancing software security and quality. We also make use of LiteLLM, so we support all major self-hosted LLM models

We’ve added examples for JavaScript, Python, and Go (see /examples). It can theoretically work with any programming language that provides a coverage report in Cobertura XML format (more supported soon) and has a language grammar available in TreeSitter.

Here’s a YouTube video with an in-depth explanation: https://www.youtube.com/watch?v=8h4zpeK6LOA

Here’s our blog with more details: https://medium.com/codeintegrity-engineering/transforming-qa-mutahunter-and-the-power-of-llm-enhanced-mutation-testing-18c1ea19add8

Check it out and let us know what you think! We’re excited to get feedback from the community and help developers everywhere improve their code quality.

It was indeed a rickroll...

A first hand experience of DHL's extremely helpful Virtual Assistant. (Please ignore my shoddy spelling and grammer. Ta.)

Without paywall: https://archive.ph/4Du7B Original conference paper: https://dl.acm.org/doi/10.1145/3630106.3659005

cross-posted from: https://lemmy.world/post/16792709

I'm an avid Marques fan, but for me, he didn't have to make that vid. It was just a set of comparisons. No new info. No interesting discussion. Instead he should've just shared that Wired podcast episode on his X.

I wonder if Apple is making their own large language model (llm) and it'll be released this year or next year. Or are they still musing re the cost-benefit analysis? If they think that an Apple llm won't earn that much profit, they may not make 1.

cross-posted from: https://programming.dev/post/15553031

second devlog of a neural network playing Touhou, though now playing the second stage of Imperishable Night with 8 players (lives). the NN can "see" the whole iwndow rather than just the neighbouring entities.

comment from video:

the main issue with inputting game data relatively was how tricky it was to get the NN to recognise the bounds of the window which lead to it regularly trying to move out of the bounds of the game. an absolute view of the game has mostly fixed this issue.

the NN does generally perform better now; it is able to move its way through bullet patterns (01:38) and at one point in testing was able to stream - moving slowly while many honing bullets move in your direction.

fairly impressive short video clip generation

Without paywall: https://archive.ph/6Wjt6

Financial Times article (via archive.ph): https://archive.ph/Xfwmd