RT by @swyx: 🆕 In Code They Act, In Proof We Trust — Erik Meijer last year, @solomonstre defined agents as "an LLM that's wrecking its environment in a loop", and @simonw coined the Lethal Trifecta for agents, that remains unsolved. our closing keynote @headinthebox introduces the main motivations behind Automind and the Universalis interpreter - agents that carry their own verifiable proof of safety! link to talk below· 代码中的行动，证明中的信任

<p>🆕 In Code They Act, In Proof We Trust — Erik Meijer<br> <br> last year, <a href="https://rss.xcancel.com/solomonstre" title="Solomon Hykes">@solomonstre</a> defined agents as "an LLM that's wrecking its environment in a loop", and <a href="https://rss.xcancel.com/simonw" title="Simon Willison">@simonw</a> coined the Lethal Trifecta for agents, that remains unsolved.<br> <br> our closing keynot