Ask HN: Why don't Claude or ChatGPT get message timestamps?
A user points out that Claude and ChatGPT cannot see timestamps for messages in their chat history, meaning they don't know when previous messages were sent and may hallucinate answers when asked. The user finds this a bizarre product flaw and questions why neither company has implemented message timestamps despite the seemingly simple fix.
Background
- The HN post reports that AI chatbots like Claude (by Anthropic) and ChatGPT (by OpenAI) cannot see the timestamps of messages in their conversation history. They only know the current time, so they have no idea if a gap between messages was seconds or days — making them unable to track elapsed time or context shifts naturally.
- This matters because it degrades multi-day or asynchronous conversations: the model can't adjust its behavior for a reply that comes days later (e.g., it won't know to recap or account for changed circumstances).
- The design choice is likely intentional: excluding timestamps from the model's input reduces token use, prevents the model from over-indexing on time gaps, and avoids hallucinations about specific dates. It may also be a safety measure to prevent the model from using timing metadata in unintended ways.
- Some commenters note that a few third-party chat UIs do surface timestamps, but the official apps from both companies deliberately omit them from the model's context window.