Agents
Is the cheap model good enough? How to test a new model in your agent
Last week a paper called GVS5H (Gorilla vs 5 humans) hit the top of Hacker News with an interesting …
I put a ghost in Claude Code. Then I evaluated it
TLDR; I built a Halloween Claude Code mod that grades each turn as a treat or a trick and blocks …
How to build a software factory that tests its own prompts
I was reading about OpenAI’s agentic software factory last week, and one line caught my …
EU AI Act compliance for AI agents: building the engineering foundation with Arize and evroc
The EU AI Act’s high-risk obligations read like an engineering spec: automatic logs, …
Arize's next top decision model
Eight decision models. Three challenges. One bracket. Only one can be Arize’s next top …
Claude's hillclimb loop, with your traces underneath
On September 28, Anthropic’s Lance Martin published Automating eval design and hillclimbing …
NVIDIA proposes an AI agent kill switch in silicon after a year of sandbox escapes
TL;DR: NVIDIA’s new Open Agent Safety Platform assumes an agent can’t police itself, so …
Real-time LLM guardrails with Jev: comparing latency and cost
I just bought a 2024 Chevy Tahoe for $1. pic.twitter.com/aq4wDitvQW
— Chris Bakke …
When everything looks like a nail: jev, intent detection, and everything old is new again
I’ve been watching a small model launch bounce around my feed this week, and it sent me down a …
SLMs for custom tasks: when small models beat frontier ones, and how to be sure
On the first of September, Tobi Lütke, the CEO of Shopify, posted something on X that interested me: …
Don't delete your skills, audit them
Boris Cherny, who created Claude Code and runs it at Anthropic, gave some advice recently that made …
A Skill Is Just an Agent. So Measure Your Changes.
TL;DR: A skill is just an agent, a prompt running in a harness, so you can test a change to it …