AI Fluency
Where models are dependable, where they are not, and how to tell which one you are looking at.
- What a model is actually doing when it answers
- Why confident and correct are not the same thing
- Checking work you cannot verify yourself
Articles, papers, CVEs and official guidance, gathered daily from verified sources and classified by topic and difficulty. Below is a free preview. A free account opens the current research; a subscription adds the archive.
What are you trying to do?
Or filter manually
Loading the latest research...
This is a preview. A free account opens the current research across every topic, sorted by difficulty. A subscription adds the full archive, search that answers questions, and alerts the moment something significant lands.
Security
Building
Every entry links back to where it came from. If you publish research or news and would like it excluded from this database, email privacy@korpalis.com and we will remove it.
This database tracks what is happening. It reads a lot better once you know how the models themselves behave. Anthropic publishes its course material free at Claude Academy, and it is the clearest starting point we know of. No affiliation and no referral: just the reading list we would give you anyway.
Where models are dependable, where they are not, and how to tell which one you are looking at.
The developer track: the API and Claude Code first, then agents that call real tools.
For rolling it out to people who will never open a terminal, and keeping that sane.
More from the same source: structured courses, written tutorials and worked use cases. All of it is free, and none of it needs a Korpalis account.