⚠️ AI agents are wildly premature technology that is being rolled out way too fast. The deepest lesson about the vibe coded AI agent disaste…

⚠️ AI agents are wildly premature technology that is being rolled out way too fast. The deepest lesson about the vibe coded AI agent disaster story that is running around is NOT about losing your data. ⚠️ 𝗜𝘁’𝘀 𝗮𝗯𝗼𝘂𝘁 𝗔𝗜 𝘀𝗮𝗳𝗲𝘁𝘆. The user wasn’t (totally) naive. He thought system prompts and guardrails would save him. They didn’t. In this case he lost data. Eventually people will lose lives.

Data Driven Agent Design with Evals & Hill Climbing Algorithms this is a mental model dump i’ve been thinking through + iterating on as we’r…
memory ownership is why we need open harnesses blog about this coming this weekend
The memory ownership point is the real story here. Running a persistent agent 24/7, memory isn't a feature — it's the entire value layer. Lo…
tldr > evals are the new training data. instead of updating weights, you're updating the agent harness > problem is agents are famous cheate…
Relying on model providers' stateful APIs or harnesses creates lock-in: switching models means losing your agent's memory -- a cost that onl…

Source: Gary Marcus (X) | 2026-04-27

Related