Mastodawn

I'm not a conspiracy theorist at all but.... it certainly feels like we're in full cover up territory...
https://www.npr.org/2025/12/20/nx-s1-5650758/epstein-files-doj-trump-photo

Ryan J. Yoder 5d ago

Wonder of Science 5d ago

Relative rotation speed and axial tilts of the planets.

Credit: Dr James O'Donoghue

Show thread

Ryan J. Yoder Nov 6

@helix @aires @kepano
A filter of email addresses might catch this specific edge case, but are you confident you'd be able to think of all similar class of bugs and write tests to catch them?

Show thread

Ryan J. Yoder Nov 6

@aires @kepano
Seems like this would be really hard to catch in QA, since there'd be no way to reproduce it reliably.

Ryan J. Yoder Nov 6

kepano Nov 3

When you email issues to Obsidian Entertainment (the video game company) their AI support hallucinates and tells you to email Obsidian (the note-taking company) instead.

The perils of trusting an LLM with your customer support.

Show thread

Ryan J. Yoder Nov 6

@linuxmatters
How is it possibly three years? I'm pretty sure last year it was still the Ubuntu podcast.

Show thread

Ryan J. Yoder Oct 23

@fesshole
This is not a confession. It's just something that happened.

Show thread

Ryan J. Yoder Oct 20

@BeamsAndBows
How are you connecting the cubes together?

Ryan J. Yoder Oct 18

Jason Gorman Oct 18

A helpful explanation of why LLM performance degrades rapidly with increasing context size, and why the *effective* maximum context size is orders of magnitude smaller than the one they sold you.

https://www.ashisharora.ai/post/the-hidden-science-behind-llm-token-limits-and-how-million-token-models-actually-work

The Hidden Science Behind LLM Token Limits (And How Million-Token Models Actually Work)

Introduction"Why can't I just paste my entire company's documentation into ChatGPT?"If I had a dollar for every time I've heard this question in my two years as a Generative AI consultant, I could probably afford the GPU cluster needed to answer it. (I wish!)Last week was no different - another meeting we discussed if context sizes were just "another controllable parameter." After all, if our laptops can open a 500MB text file instantly, so why can't a powerful AI model handle it?This misconcept

ashisharora.ai

Show thread

Ryan J. Yoder Oct 17

@sinituulia
I agree you shouldn't be repeating yourself in the post and alt text. I disagree you should be putting important information in the alt text that is not visually apparent in the image. Not all applications display the alt text visually, so you should expect a user to either view the image OR read the alt text. But this is just my opinion.