Prompt Engineering Guide (3.5K) Our prompt engineering guide is trending on Hacker News! Thanks for all the support. Do check it out if you want to learn more about how to make the best use of LLMs. https://
github.com/dair-ai/Prompt
-Engineering-Guide
…
@dair_ai
-
Prompt Engineering Guide Trends on Hacker News
By
–
-
Energy Transformer: Replacing Feedforward Blocks with Associate Memory
By
–
10). Energy Transformer – a transformer architecture that replaces the sequence of feedforward transformer blocks with a single large Associate Memory model; this follows the popularity that Hopfield Networks have gained in the field of ML.
-
Augmented Language Models: Reasoning Skills and Tool Integration Survey
By
–
7). Augmented Language Models – a survey of language models that are augmented with reasoning skills and the capability to use tools.
-
Auditing Large Language Models: Policy Framework Proposal
By
–
9) Auditing large language models – proposes a policy framework for auditing LLMs.
-
Geometric Clifford Algebra Networks Transform Neural Network Architecture
By
–
8). Geometric Clifford Algebra Networks (GCANs) – an approach to incorporate geometry-guided transformations into neural networks using geometric algebra. https://t.co/XHnKevDMLk
— DAIR.AI (@dair_ai) 20 février 20238). Geometric Clifford Algebra Networks (GCANs) – an approach to incorporate geometry-guided transformations into neural networks using geometric algebra.
-
Reinforcement Learning Optimizes Computer Vision Model Performance
By
–
5). Vision meets RL – uses reinforcement learning to tune computer vision models with task rewards; observes large performance boosts across multiple CV tasks such as object detection and colorization.
-
Language Quantized AutoEncoders Enable Few-Shot Image Classification
By
–
6). Language Quantized AutoEncoders (LQAE) – an unsupervised method for text-image alignment that leverages pretrained language models; it enables few-shot image classification with LLMs.
-
pix2pix3D: 3D-Aware Conditional Generative Model for Image Synthesis
By
–
3). pix2pix3D – a 3D-aware conditional generative model extended with neural radiance fields for controllable photorealistic image synthesis. https://t.co/Xkmw0NJieC
— DAIR.AI (@dair_ai) 20 février 20233). pix2pix3D – a 3D-aware conditional generative model extended with neural radiance fields for controllable photorealistic image synthesis.
-
Moral Self-Correction Emerges in Large Language Models at 22B
By
–
4). Moral Self-Correction in Large Language Models – finds strong evidence that language models trained with RLHF have the capacity for moral self-correction. The capability emerges at 22B model parameters and typically improves with scale.
-
LLMs Fail Arithmetic With Irrelevant Context
By
–
LLMs and irrelevant context – finds that many prompting techniques fail when presented with irrelevant context for arithmetic reasoning. 11 of 11