See more of my talks at raphaeldelio.com/talks

Other upcoming sessions:

Nov 18 (Virtual): events.redis.io/superchargey...

Nov 20 (Eindhoven): www.meetup.com/server-side-...

And this video of my friend capturing a Pokémon

Congrats, Dan! Wonderful to see you thriving!

I thought @bsbodden.bsky.social’s Chat History implementation for Redis was making this release since it was marked with the 1.1 milestone tag. Do you know why it didn’t make it?

I'm building a platform for developer advocates. Myself and my team are the main users right now. So everything I put in are based on our needs. But our needs seem to be insatiable 😅

Thanks for sharing, Simon! I'll check it out! From the little experience I had so far, I had a bit of trouble getting graphs (2D coordinate systems) to work well with them. Do you also use it for more advanced animations and graphics?

I don't believe they're peer reviewed though

transformer-circuits.pub/2025/attribu...

Image: Screenshot from Marijn van Vliet's YouTube Video (Visualization of a fully connected neural network, version 2)

Findings like this show that LLMs might be operating on deeper structures than simple pattern matching. Interpretability research is still in its early days, but it’s starting to reveal that these models could be doing more reasoning under the hood than we’ve assumed.

What this suggests, as Josh Batson concludes, is that even though the LLM has seen during its training that the 6th volume of this journal has been published in 1965 as a fact, evidence shows that the model still "prefers" to do the math for this particular case.

The LLM can correctly predict that the 6th volume was published in 1965. However, when observing which neurons are triggered, they witnessed that the neurons for adding the digits "6" and "9" were also triggered for this task.