EPISODE · Jul 13, 2026 · 1H 20M
State of Agentic Coding #8
from State of Agentic Coding · host Armin Ronacher and Ben Vinegar
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.
Embed this episode
Ready to play
State of Agentic Coding #8
No transcript for this episode yet
Similar Episodes
No similar episodes found.
Similar Podcasts
No similar podcasts found.