TLDR Tech / AI
The Oracle and the Firm
OpenAI and Anthropic have decided on different approaches to context management. OpenAI uses compaction, compressing everything and retaining only the relevant information. This results in one long thread that maintains a lot of coherence. Anthropic splits context windows across various agents, where each agent executes on the sub-problem within its own context window. Sub-agents do a large amount of work, then pass back only the relevant information to the parent agent. Anthropic's approach can result in sub-agents doing duplicate work, forgetting information, and generally wasting more tokens.
Read the full story