they don't maximize rewards, they are given a prompt (a kind of inception) and continue the sequence
PROMPT ENGINEERING
-
LLMs as Cognitive Engines Orchestrating Compute Infrastructure via Text
By
–
Good post. A lot of interest atm in wiring up LLMs to a wider compute infrastructure via text I/O (e.g. calculator, python interpreter, google search, scratchpads, databases, …). The LLM becomes the "cognitive engine" orchestrating resources, its thought stack trace in raw text
-
Galactica LLM Performance with XGBoost Model Implementation
By
–
Amazed by the performance of Galactica by @paperswithcode
— SRK (@sudalairajkumar) 16 novembre 2022
Tried with prompt "jupyter notebook on how to use xgboost model" @tunguz might like it 🙂 #LLM #NLP #AI pic.twitter.com/7ohrREfiltAmazed by the performance of Galactica by @paperswithcode Tried with prompt "jupyter notebook on how to use xgboost model" @tunguz might like it 🙂 #LLM #NLP #AI
-
Large Language Models Are Not Zero-Shot Communicators
By
–
Large language models are not zero-shot communicators Ruis et al.: https://
arxiv.org/abs/2210.14986 #Artificialintelligence #DeepLearning #MachineLearning -
GPT Training Framework with Dataset and Sampling Tools
By
–
Prompt: "You are a GPT and you're in charge of training an even better GPT, congrats! You have a dataset here . You can train it on document chunks like this: and sample its current understanding like this: . And here's a calculator and a scratchpad . Begin:"
-
Understanding Code Generated by AI Assistants Matters
By
–
“Be careful with copilot code generation assistance. We need people to understand their codes.” – Don Knuth, Turing Award winner (1974), luminary of @stanford CS dept, and a dear friend, at @StanfordHAI Fall Conf
-
Create Midjourney-Style Images with Open Source Stable Diffusion
By
–
Midjourney without Midjourney… @prompthero has fine-tuned Stable Diffusion so you can create images in the style of Midjourney, but with an open source model. You can run it on the web or via an API on Replicate:
-
Training data presence affects image generation result interest
By
–
It is possible that images like this were in the training set, in which case the result is indeed less interesting. Would be good to know.
-
Astronaut Riding Horse: DALL-E’s Remarkable Pose Accuracy
By
–
What's remarkable about this image is that the astronaut is in the correct riding pose, even though DALL-E has presumably never seen "an astronaut riding a horse" as prompted.