The Current State of Agentic Coding
mitsuhiko · x · 2026-07-13
This is a podcast discussion on the current state of Agentic Coding, featuring guests like Mario Zechner (Flask). Instead of just discussing models, the conversation focuses on the practical workflows of coding agents:
- Conducting on-the-spot/vibe checks on Fable and GLM 5.2
- Discussing the role of RL in these systems
- Why harnesses can mitigate model instability in engineering tasks
- Loops, AI FOMO, and how to keep agents consistently working
Overall, it's a long, engineering-focused discussion centered on "how to turn models into productive coding agents."
More from coding & agent
- An MCP server signs every AI agent tool call into a verifiable Merkle chain — Funky_Chicken_22 · 2026-07-22
- Claude Code skill uses 10 Markdown rules to make outputs ADHD-friendly — alex_verem · 2026-07-22
- A Firecracker-based platform says it can host 6,000 AI agents on one 256 GB server — maritime_sh · 2026-07-22
- A better path to agent autonomy is running waves, finding friction, and iterating — JnBrymn · 2026-07-22
- AI agent designers map the visual and tonal cues behind companionship products — Unlikely-Platform-47 · 2026-07-22
- Coding agents are heading toward an AI-writes, AI-reviews, human-approves workflow — aftahi_ai · 2026-07-22