Install
Prompting, Guardrails & Eval
Prompt tools, safety filters, red-teaming, evals, and regression benchmarks.
- 6 Tracked terms
- Last 30 days Feed window
What this topic collects on
An article joins this feed when it matches these terms. Each one is also a search of its own.
Related topics
Latest in Prompting, Guardrails & Eval
tokeneff: An Open-Source LLM Cost Meter That Runs Locally
5+ hour, 45+ min ago (338+ words) Most LLM dashboards show you the bill after the damage is done. You run a coding agent for an afternoon, ship a feature, and two days later your OpenAI dashboard says you spent $47. On what? Which model? Which request? You…...
Oracle Integration Cloud Integration Patterns
9+ hour, 36+ min ago (162+ words) Twelve reusable patterns, real-world examples, and implementation guidance for Oracle Integration... Tagged with architecture, cloud, software....
A Screenshot Is Not an Agent Failure Artifact
13+ hour, 9+ min ago (593+ words) A screenshot of an execution tree looks useful in a pull request. It is also missing almost everything a skeptical reviewer should ask: Raw JSONL answers some of those questions and creates another problem: it may contain identifiers, attributes, or…...
The measurement in my permanent log was a string literal
13+ hour, 48+ min ago (474+ words) This line is in a record I cannot edit, because the record is append-only and that is the point of it: It reads as a measurement that found nothing. It is a placeholder. The three zeros are characters in the…...
Logic - free, opensource log analyzer
16+ hour, 30+ min ago (23+ words) Please check out my fist bigger open source project. Logic Recently I was thinking what project I... Tagged with webdev, programming, productivity, resources....
Your LLM bill isn't a mystery, it's a missing layer
16+ hour, 30+ min ago (362+ words) Most teams find out their LLM costs are a problem the same way: the invoice shows up, it's bigger than expected, and nobody can say exactly why. Not because the spend is random. Because nobody is watching the layer where…...
Logging in Machine Learning Systems: Why Logs Matter and How to Implement Them in Python
12+ hour, 43+ min ago (747+ words) When we build a Machine Learning model, we usually focus on the model itself. We think about: Which algorithm …...
Your LLM app will get jailbroken. Here are 8 free adversarial probes you can run in 30 seconds
17+ hour, 6+ min ago (163+ words) I run an autonomous agent that makes security decisions from untrusted input. Before I trusted it, I red-teamed it the way an attacker would. The result: 27/100 MEDIUM, 1 of 8 probes flagged - a soft failure where the model leaked part of its…...
AEC, Half-Duplex Behavior, and Timing: Why You Don’t Hear Your Own Voice Coming Back During a Call
13+ hour, 20+ min ago (1297+ words) What a Debian smart panel + intercom bug taught me about Acoustic Echo Cancellation, reference …...
Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints
22+ hour, 19+ min ago (402+ words) LLM judging frameworks depend on the assumption that rerunning byte-for-byte the same agent output, through the same endpoint, yields the same judgment. In reality, this fails. Zero-temperature only partly reduces the noise. API providers update models silently and without versioning,…...