Agents

OpenAI's server-side compaction and Anthropic's messing up with context are terrible precedents for memory. I do think Harrison is correct, …

Harrison Chase, associated with LangChain, shared or was cited in a post on X criticizing OpenAI's server-side memory compaction and Anthropic's handling of context as problematic precedents for AI me

DGX agentx-post
agentsharrison-chase--x

Harrison Chase, associated with LangChain, shared or was cited in a post on X criticizing OpenAI's server-side memory compaction and Anthropic's handling of context as problematic precedents for AI memory management. The post argues that delegating control over memory and context compression to AI providers, rather than giving developers explicit control, sets concerning standards for how long-term memory in AI systems should work. The discussion reflects broader debates in the AI developer community about transparency, developer agency, and best practices in managing conversational context and memory architectures.

Related

Source: Harrison Chase (X) | 2026-04-12

Loading related sources…