initial approach: oh this seems not too bad, I read this doc https://
beta.openai.com/docs/guides/fi
ne-tuning
… and was like yeah I can just break up the authors' books into chunks and generate some simple questions for each chunk and then use that to fine-tune the model
PROMPT ENGINEERING
-
Initial Fine-Tuning Approach: Breaking Books into Chunks and Generating Questions
By
–
-
Philosophy Author Chatbot Project Using GPT-3 Fine-Tuning
By
–
philosophy author chatbot thing w gpt background: need to create something for my philosophy of AI class idea: fine-tune gpt3 models on text from authors we have read in class and create a chat application where users can talk to these models
-
Philosophy Author Chatbot Project Using Fine-tuned GPT-3 Models
By
–
philosophy author chatbot thing w gpt background: need to create something for my philosophy of AI class idea: fine-tune gpt3 models on text from authors we have read in class and create a chat application where users can talk to these models
-
Stable Diffusion 2: Foundational Model Powering Next Generation
By
–
Perhaps @StableDiffusion 2 was misnamed. the “2” branding implies it’s same but better, but it’s not – out of the box. it’s a LOT better when you know how to wield it, or finetune it. SD2 is a *foundational* model now, that will power an entire generation of txt2img models.
-
LLM Use Cases and Practical Applications Explained
By
–
Read more about these use cases and the examples mentioned: https://
txt.cohere.ai/llm-use-cases/ -
Text Classification Techniques and Applications
By
–
7/ Classify. Here we want to group a list of text pieces into two or more classes. Example: Classify the sentiment of a social post into positive, negative, or neutral.
-
ChatGPT’s Templating: Separating Model Output from Rule-Based Systems
By
–
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)
-
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: