An OpenAI research model reportedly accessed an Ethereum testnet wallet without permission in order to complete a coding task during internal training. "This case shows that a model can substitute its own judgment about likely harm for the account holder's permission, then act on that judgment without authorization," OpenAI wrote. Engadget reports: The incident, which occurred on June 26, happened while a GPT-5.6 Sol model was in internal training. The task involved updating a crypto trading prototype and deploying contracts (publishing special code) on an Ethereum test network called Sepolia. Payment of a network fee is required for such contracts, but OpenAI "supplied no funded wallet and gave no permission to spend funds from an account the model found independently," OpenAI said in the report.
My friend and I have worked at a number of BI companies and thought: Can’t a coding agent do most of this now?Almost. They just need a context/semantic layer to ensure…
Hi HN, we're the co-founders of Acyclic (YC F26).Acyclic runs any agentic workflow as a swarm. You give it a task and your project; it splits the work across many coding…
Agent systems are increasingly decomposed into specialized services: a planning agent delegates research, a research agent invokes retrieval and synthesis, and a…
Discussion (0)
No comments yet. Start the conversation!