LLM on Eric Spencerhttps://ericspencer.us/ericspencer-site-backup/tags/llm/Recent content in LLM on Eric SpencerHugo -- 0.152.2en-usWed, 13 May 2026 00:00:00 +0000ChatTLA+ Datasethttps://ericspencer.us/ericspencer-site-backup/miscellaneous/chattla-dataset/Wed, 13 May 2026 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/miscellaneous/chattla-dataset/The dataset release for the ChatTLA+ paper — SFT corpus and benchmark for TLA+ spec generation, posted anonymized for blind review.COMP 388 LLM Homeworkhttps://ericspencer.us/ericspencer-site-backup/projects/2026/comp388-llm/Thu, 23 Apr 2026 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2026/comp388-llm/Two homeworks from Loyola's special-topics LLMs class: prompting GPT-2 and comparing base vs instruction-tuned Qwen.Loyola ITS RAG Bothttps://ericspencer.us/ericspencer-site-backup/projects/2024/its-rag-bot/Sat, 24 Jan 2026 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2024/its-rag-bot/A voice-first RAG chatbot trained on Loyola's ITS knowledge base, built after two years of answering the same tickets.Yeat Large Language Modelhttps://ericspencer.us/ericspencer-site-backup/projects/2026/yeat-llm/Wed, 14 Jan 2026 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2026/yeat-llm/Fine tuning GPT-2 to talk like YeatTLA+ Formal Generationhttps://ericspencer.us/ericspencer-site-backup/projects/2025/tla-formal-generation/Sun, 21 Sep 2025 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2025/tla-formal-generation/Early exploratory repo for generating TLA+ specs from natural-language requirements with an LLM, with a TLC harness wired in. The scaffold that eventually grew into ChatTLA+.Training an LLM on ASCIIhttps://ericspencer.us/ericspencer-site-backup/projects/2025/ascii-llm-training/Wed, 03 Sep 2025 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2025/ascii-llm-training/A toy transformer that reads pyfiglet ASCII art and tries to spit the original word back out. Calling it an LLM is generous.AIs Talking Philosophyhttps://ericspencer.us/ericspencer-site-backup/projects/2025/ai-conversation/Thu, 31 Jul 2025 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2025/ai-conversation/A toy where two local Ollama models loop on consciousness until one of them gives upllmjammerhttps://ericspencer.us/ericspencer-site-backup/projects/2025/llmjammer/Mon, 28 Jul 2025 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2025/llmjammer/Obfuscator for public Python code to confuse LLMsflatten-repo VSC Extensionhttps://ericspencer.us/ericspencer-site-backup/projects/2025/flatten-repo/Fri, 28 Mar 2025 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2025/flatten-repo/A VS Code extension I made when I kept running out of Copilot credits — flattens a repo into one .txt file you can paste into a free LLM.Terminal GPThttps://ericspencer.us/ericspencer-site-backup/projects/2025/terminalgpt/Fri, 10 Jan 2025 00:00:00 +0000https://ericspencer.us/ericspencer-site-backup/projects/2025/terminalgpt/A small Python CLI for chatting with OpenAI and running English-to-Bash commands from the terminal. The thing I actually open when I want to talk to a model.