Haystack

Python framework for building pipelines

3 episodes mention this Visit official site →

Episodes

#5390: Chaining Small Models for Dictation Cleanup

Daniel's Android dictation fork won't render "three point five" as a decimal. How many models does cleanup actually need?

Sep 20
#1985: AI Tutors vs. Human Error: Who Do You Trust?

AI gets flak for hallucinations, but humans misremember 40% of facts. Why the double standard?

Apr 4
#1235: Beyond "No Training": Securing the New Agentic AI Stack

Think your data is safe because of a "no training" clause? We deconstruct the hidden security risks within the modern agentic AI stack.

Mar 15