ThursdAI preview: labs race to personal agents, but who guards a poisoned email?
altryne · x · 2026-10-22
This week's ThursdAI preview centers on the race to personal agents — Claude Duet, dots, Muse, Grok Bot — and the key question: who checks the agent when it reads a poisoned email? Guests include Karan Vaidya (Composio) on agent security, Prince Canuma running a 40B coding model on a Mac via Flint, and theJoshMeister on a wild security week: AI finding PHP holes, PHP2Shell, and the LiteLLM backdoor. Also covers Anthropic giving away 5% of itself and Dario answering critics.
Related event: ThursdAI Weekly: Anthropic's 5% Giveaway and Claude Duet Take Center Stage(5 posts)→
More from coding & agent
- swyx hails Opus 5.5 as best work-estimator model; dev counters that review time is the real bottleneck — petrusenko_max · 2026-10-23
- Agent Field Kit launches free agentic defense toolkit against LLM-enhanced attackers — alvelda · 2026-10-23
- LiteLLM PyPI compromise and Railway breach: Oct 21 attack timeline and free response kit — alvelda · 2026-10-23
- Daily Experiment Planner agent: one prompt to save scientists hours of lab prep — nlarusstone · 2026-10-23
- Two £300 Snapdragon mini PCs, no GPU: 46 tok/s local Qwen3.8 Flash Next with custom ToRc engine — WorldlyAd7946 · 2026-10-22
- Chrome engineer asks: do agents improve incident response or just ship unpatched deps 10x faster? — fhinkel · 2026-10-22