AI

I tried SD once and it was pretty good. It was a bit difficult, of course. Now I want to try image generation again. Do you still think I should use SD or a different tool?

I wanted to extract some crime statistics broken by the type of crime and different populations, all of course normalized by the population size. I got a nice set of tables summarizing the data for each year that I requested.

When I shared these summaries I was told this is entirely unreliable due to hallucinations. So my question to you is how common of a problem this is?

I compared results from Chat GPT-4, Copilot and Grok and the results are the same (Gemini says the data is unavailable, btw :)

So is are LLMs reliable for research like that?

I've had a lot of fun making stupid songs using Suno, but one of their biggest limitations -- not being able to use a specific artist or group as an example -- seems intentionally added to escape this kind of lawsuit.

Just a very short context so I was trying to generate images in Gemini on my phone, I replaces assistant with Gemini. It wouldn't work, I had a friend that generated some amazing logos with it and I was impressed.

So I decided to sign up for the trial for a free month and then 27 CAD from every month after and I think you get 2 TB of Google One storage...

I told it to generate images I tried running on all the other models and it instantly gave me exactly what I wanted with the same prompt as I used on other popular models.

Very clean layout as well, I like how it has a "suggest more" button so first round of images didn't make the cut but I hit suggest more 1x and it was much better and then 2x it was bang on what I wanted.

Overall kind of expensive and I think with certain phones they should be giving you access to this for using their flagship device (pixel phones)

Really impressed on usability and results really tops the other ones I've used out of box.

All in all pretty decent sorry I attached a 35 min video but didn't wanna link to twitter and wanted to comment on this...pretty cool tho not a huge fan of mark but I prefer this over what the rest are doing...

The open source AI model that you can fine-tune, distill and deploy anywhere. It is available in 8B, 70B and 405B versions.

Benchmarks

We all use ai in you everyday life. How often do you use it? How you feel about it?

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.

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...

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

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.