wdym by "beyond comparing description embeddings"? thats not how agents currently work. they currently work by asking the llm to pick a tool, very similar to this approach
PROMPT ENGINEERING
-
RLHF: Reinforcement Learning from Human Feedback Guide
By
–
informative blog post by Chip Huyen on "RLHF: Reinforcement Learning from Human Feedback" This blog post covers:
⦿ Pre-training for completion
⦿ Supervised fine-tuning for dialogue
⦿ Reinforcement Learning from Human Feedback Blog link: https://
lnkd.in/gPuKbCiP Bonus RLHF -
Free ChatGPT Prompt Engineering Course for Developers
By
–
#ChatGPT Prompt Engineering for Developers Free Short Course by @DeepLearningAI_ & @OpenAI https://
deeplearning.ai/short-courses/
chatgpt-prompt-engineering-for-developers/
… #ArtificialIntelligence #MachineLearning #DeepLearning @data_nerd @ahier @FmFrancois @enilev @Damien_CABADI @Shi4Tech @gvalan @CatherineAdenle @avrohomg @anijov -
Chain-of-Thought Prompting: Does Incorrect CoT Hurt Performance?
By
–
A question I get asked a lot about chain-of-thought (CoT) prompting is whether having incorrect CoT will hurt performance. This implicit research question here is basically whether the model is really learning how to reason from the CoT example, or if CoT exemplars elicit
-
Creativity as Art in ChatGPT Prompting and Future Programming
By
–
The impact of creativity in prompting ChatGPT is limitless. It feels to be more of an art than a science. Great "programmers" of the future will in part have to be artists. Perhaps they always were, but now the method and medium of creation has become much more accessible.
-
Created an AI voice model of President Macron — results
By
–
Non je n’ai pas utilisé ElevenLabs pour générer la voix de Macron pour des raisons que j’ai déjà expliqué. Je vous invite à aller voir la vidéo ou j’y résume ce que j’ai fais et comment je m’y suis pris. J'ai fait une IA du Président Emmanuel Macron, voici les résultats.
-
Evolution of Human-Computer Interfaces: From Punch Cards to Natural Language
By
–
oh that wasn’t very clear—i meant the evolution of how we use computers,from punch cards to command lines to higher-level programming to GUIs to touch interfaces to programming in natural language
-
V5.1 Released: Enhanced Image Generation and RAW Mode
By
–
V5.1 is now available! Images are more coherent, sharp, and beautiful. It's easier to use and should respond more precisely to instructions. We've also added a "RAW" mode for expert users to reduce the 'opinionatedness' of our model and give you more creative control.
-
Chain-of-Thought Prompting: Emergence in Large Language Models
By
–
Additional response 2: Another popular example of emergence which also underscores qualitative changes in the model is chain-of-thought prompting, for which performance is worse than answering directly for small models, but much better than answering directly for large models.
-
RLHF: Reinforcement Learning from Human Feedback Explained
By
–
New post: RLHF – Reinforcement Learning from Human Feedback Discussing 3 phases of ChatGPT development, where RLHF fits in, how RLHF works, hypotheses on why it works, and relationship between RLHF and hallucination. https://
huyenchip.com/2023/05/02/rlh
f.html
…