Skip to content
Sign in
Artwork for State of Agentic Coding
State of Agentic Coding · July 13 · 1 hr 20 min

State of Agentic Coding #8

Recorded in Vienna, Ben and Armin sit down with Mario Zechner to vibe-check Fable and GLM-5.2, unpack how RL and agent harnesses normalize model jank, and ask whether newer models are quietly getting worse. They also debate agent loops, trust and ROI, the rising cost of tokens and compute, and how to stay sane amid AI FOMO.

0:00-1:20:52
Play in

transcript

No transcript — this publisher did not publish one.

show notes

Recorded in Vienna, Ben and Armin sit down with Mario Zechner to vibe-check Fable and GLM-5.2, unpack how RL and agent harnesses normalize model jank, and ask whether newer models

are quietly getting worse. They also debate agent loops, trust and ROI, the rising cost of tokens and compute, and how to stay sane amid AI FOMO.

more episodes

All episodes