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
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
- “Memory is important, and it creates lock in” Exactly why I don’t want OpenAI, Anthropic or any of the other AI companies owning it.
- OPEN MEMORY, OPEN HARNESS the industry shifts to closed agent harnesses locking memory behind proprietary apis. https://x.com/hwchase17/stat…
- Not your memory not your life
- memory lock-in doesn't kick in when you adopt the harness. it kicks in 6 months later when leaving means starting over from zero. by then th…
- its a directionally correct form factor but way too much lock in
Source: Harrison Chase (X) | 2026-04-12