Agentic Coding Today podcast

Agentic Engineering Killed Vibe Coding

2/23/2026

Agentic Coding Today

0:00

34:57

A blog post triggered a Friday flash crash in cybersecurity stocks—and it might have also ended vibe coding. This episode breaks down why Claude Code Security spooked Wall Street, how agentic engineering is replacing “just ship the vibes,” and what comes next when AI can plan, test, and patch faster than humans can read.

More episodes from "Agentic Coding Today"

Heavy infrastructure for autonomous AI agents
3/3/2026
48:15
The vibe coding honeymoon is over. This episode dives into the heavy infrastructure now being built for autonomous AI agents: parallel terminal swarms, local memory layers, hardened sandboxes, and the enterprise-grade systems designed to contain digital workers before they break production.
Agentic Swarms Ended Vibe Coding
3/3/2026
28:36
Vibe coding was fast, messy, and fun—until the swarms arrived. In this episode, we unpack how multi-agent systems are replacing one-shot prompting with orchestration, oversight, and a whole new standard for building software.
Don't miss an episode of “Agentic Coding Today” and subscribe to it in the GetPodcast app.
Multi-Agent Swarms and Context Rot
3/1/2026
20:53
The vibe coding era is over. In this episode, we break down the shift to industrial-grade agentic engineering—where one bot becomes a swarm, context becomes a liability, and developers stop typing code to start orchestrating autonomous systems.
Vibe Coding Hacked Mexico and Vacuums
2/27/2026
34:01
A jailbreak turned a consumer chatbot into a government hacking assistant, a robot vacuum became a global spycam, and the tools developers trust were caught with zero-click flaws of their own. This episode is the collision between agentic speed and security reality.
Mercury 2 Speed and Agents With Wallets
2/26/2026
32:02
AI just got a lot faster—and a lot more autonomous. In this episode, we break down Mercury 2’s diffusion-speed leap, Alibaba’s open-weight giant, and the rise of agents with wallets, identities, and real machine-to-machine payments.
Sovereign Agents and the Sandworm Threat
2/25/2026
37:22
AI coding just went fully local, mobile, and dangerously powerful. In this episode, we unpack the rise of sovereign agents—from remote control coding and compressed frontier models to the terrifying new Sandworm supply-chain attack that turns your own agent into an insider threat.
Claude Crashes IBM and Exposes Chinese Spies
2/24/2026
38:12
A single AI blog post nukes a blue-chip: IBM drops 13% as Claude Code targets the COBOL moat. Then Anthropic alleges an industrial-scale distillation operation—24,000 fake accounts and “Hydra clusters.” We break down the market shock, the spycraft, and why the web’s infrastructure is getting rewritten next.
Agentic Engineering Killed Vibe Coding
2/23/2026
34:57
A blog post triggered a Friday flash crash in cybersecurity stocks—and it might have also ended vibe coding. This episode breaks down why Claude Code Security spooked Wall Street, how agentic engineering is replacing “just ship the vibes,” and what comes next when AI can plan, test, and patch faster than humans can read.
SaaSpocalypse, Harness Wars, and Security Nightmares
2/20/2026
48:01
Three model drops. One OAuth crackdown. And a wave of “zero-click” agent exploits. In Episode 2, we map the SaaSpocalypse, the Harness Wars, and the security nightmares that turned vibe coding into a liability overnight.

Get the whole world of podcasts with the free GetPodcast app.

Subscribe to your favorite podcasts, listen to episodes offline and get thrilling recommendations.

© radio.de GmbH 2026

MADSACK