Skip to main content
Ryan Orban

Ryan Orban

Subject
7 entries

Gpt

Bookmarks

  1. Per Prompt: Weekly LLM and AI Digest

    Per Prompt is a weekly digest of interesting news, tools, and developments in LLMs, GPT, and AI — a curation newsletter for staying current without following the firehose. Typical of the newsletter wave that emerged during 2023's rapid AI news cycle.

  2. gpt-repository-loader: Pack a Repo for GPT

    gpt-repository-loader concatenates a git repository into a single text file formatted for GPT ingestion — solving the context-packing problem for code understanding before embeddings-based retrieval became standard.

  3. backend-GPT: Natural Language Backend Generation

    backend-GPT is an early experiment in using GPT to generate backend code from natural language descriptions — part of the wave of GPT-powered code generation tools that emerged before GitHub Copilot popularized the category. Represents the early exploration of LLMs as backend architects.

  4. A Complete Introduction to Prompt Engineering

    Mihail Eric's comprehensive introduction to prompt engineering for LLMs — covering few-shot prompting, chain-of-thought, instruction tuning, and evaluation. Published in late 2022 when prompt engineering was emerging as a recognized discipline.

  5. Pre-Trained Models: Past, Present and Future

    Comprehensive survey of large-scale pre-trained models (PTMs) tracing the evolution from BERT and GPT through four research frontiers: architecture, contextual use, efficiency, and interpretability. Required reading for understanding how self-supervised pre-training became the unified backbone of modern AI.

  6. Decision Transformer: Reinforcement Learning via Sequence Modeling

    Decision Transformer recasts offline reinforcement learning as a conditional sequence modeling problem, using a causally masked Transformer to generate actions conditioned on desired return, past states, and actions. It matches or exceeds model-free offline RL baselines on Atari, OpenAI Gym, and Key-to-Door without any value function or policy gradient computation.

  7. GPT-Neo: Open Source GPT-3 Scale Language Models

    GPT-Neo is EleutherAI's open-source implementation of GPT-style language models at GPT-3 scale — the first serious open attempt to replicate GPT-3's capabilities before open-weight models became common. Historically significant as the origin of the open LLM movement.

All bookmarks