LLMS

Pi’s responses are always generated by our own models, built in-house. On investigation, it appears the user prompted this particular response from Pi after copy-pasting the output from Claude earlier in the conversation with Pi. Pi differs from other products, like Claude and ChatGPT, in that it remembers the main conversation even in threads. In this case, Pi reproduced the relevant message because it was included in its conversational memory. seshu bonam (@seshubon) WHAT? @inflectionAI is just a claude-3-sonnet wrapper? care to explain? 🐒 Produces the exact same answer word to word for a custom query i asked 🤯 Community note: Context is shared across conversations with Pi. The user had previously copied Claude's response to Pi in another thread. When asked the same question, Pi simply recited Claude's answer from that thread. twitter.com/inflectionAI/s… — https://nitter.net/seshubon/status/1765870717844050221#m

→ View original post on X — @inflectionai, 2024-03-08 18:45 UTC