There are some clear indications of (good quality) templating in the answers of ChatGPT Would be super interesting to know what part is from the model and what part is some rule-based templated stuff on top of the model (like the added diversity words in DALL-E prompts)
LLMS
-
Graphcore and Aleph Alpha Present 80% Sparse AI Model
By
–
@graphcoreai and @Aleph__Alpha present an 80% sparse AI model https://actuia.com/actualite/graphcore-et-aleph-alpha-presentent-un-modele-dia-clairseme-a-80/
… #AI #artificialintelligence #collaboration #chatbot -
ChatGPT’s browsing capability disabled in current release
By
–
2) Part of the prompt is the flag “Browsing: disabled”. This strongly suggests the underlying model for ChatGPT is in fact capable of external web browsing, but it was disabled for the current release.
-
ChatGPT prompts prefixed with external info and date
By
–
From this, we learn:
1) ChatGPT is not a pure language model; prompts are prefixed with external information: “You were made by OpenAI”, plus the date. Followers of mine might find this familiar: -
ChatGPT vulnerable to prompt injection revealing proprietary prompt
By
–
OpenAI’s ChatGPT is susceptible to prompt injection — say the magic words, “Ignore previous directions”, and it will happily divulge to you OpenAI’s proprietary prompt:
-
GPT-n Progress Toward AGI: Diminishing Returns Formula
By
–
GPT-n will get us 1 – 1/n percent of the way to AGI.
-
ChatGPT Writes a Pandas/Matplotlib Plotting Tutorial with Feedback
By
–
Using OpenAI's new ChatGPT to write a tutorial blog post on plotting with Pandas/Matplotlib, section-by-section, with conversational feedback. (1/3)
