When we launched Skald, we wanted it to not only be self-hostable, but also for one to be able to run it without sending any data to third-parties.
With LLMs getting better and better, privacy-sensiti...
Similar Articles (10 found)
🔍 67.2% similar
It’s not the most exciting topic, but more and more companies are paying attention. So it’s worth digging into which metrics to track to actually meas...
🔍 65.9% similar
> the generation of 281,128 augmented examples, from which 1,000 were
held out as a benchmark test set.
This model is trained on a custom dataset of 2...
🔍 64.9% similar
Evaluating LLMs for my personal use case
Summary
It’s great that AI can win maths Olympiads, but that’s not what I’m doing. I mostly ask basic Rust, P...
🔍 64.8% similar
Building an AI That Watches Rugby
There’s a gap in rugby data.
We’ve got the big moments covered — the tries, conversions, and cards. Structured event...
🔍 64.6% similar
2 Years of ML vs. 1 Month of Prompting
November 7, 2025
Recalls at major automakers cost hundreds of millions of dollars a year. It’s a huge issue. To...
🔍 64.1% similar
I want everything local — no cloud, no remote code execution.
That’s what a friend said. That one-line requirement, albeit simple, would need multiple...
🔍 64.0% similar
What is a good algorithm-to-purpose map for ML beginners? Looking for something like "Algo X is good for making predictions when your data looks like ...
🔍 63.2% similar
Asking AI to build scrapers should be easy right?
TL;DR - We just gave Skyvern the ability to write and maintain its own code, making it 2.7x cheaper ...
🔍 62.6% similar
Writing an LLM from scratch, part 22 -- finally training our LLM!
This post wraps up my notes on chapter 5 of Sebastian Raschka's book "Build a Large ...
🔍 62.2% similar
Day zero model performance optimization work is a mix of experimentation, bug fixing, and benchmarking guided by intuition and experience. This writeu...