The Self-Testing Layer
8bitconcepts Research
A researched white paper on why agentic businesses need self-testing, self-improving systems: artifact scoring, feedback loops, evaluator calibration, audit trails, and regression infrastructure.
evaluation
Building Agentic Outcome Loops with an Open-Source Stack
adelzaalouk
I use LLMs to draft product specs (we call them RFEs). The output is usually *fine*, but rarely first-draft ready. Customer evidence is missing. Architecture decisions leak into what should be a business need. Three features get bundled into one. I wanted a way to automatically score drafts...
🔗 @karpathy on having models collaborate on complex projects
Andrew Cove
Andrej Karpathy discusses applying multiple AI models to the same task, then having them each review and evaluate the combined results.Another technique for getting more out of LLMs, which each have their own approaches and personalities and quirks. Have more than one perform the same task, then...
CISC320 Second Self-Evaluation
Austin Cory Bart
I just got back my Spring 2019 teaching evaluations, so I wanted to do a second self-evaluation on how the CISC320 Algorithms course went. I wrote the first draft of this blog post without referring to my previous self-evaluation. After re-reading that post, I went back and added a comment to...