Miguel Dev

Apr 18, 2024 | lesswrong.com | Miguel Dev

Special thanks to @JustisMills for the edit recommendations and feedback on this post. GPT-2 exhibits a weird behavior, where prompting the model with specific tokens consistently triggers outputs related to nonsensical strings of text related to gaming, mythology and religion.

Mar 28, 2024 | lesswrong.com | Miguel Dev

(This post is intended for my personal blog. Thank you.)One of the dominant thoughts in my head when I build datasets for my training runs: what our ancestors 'did' over their lifespan likely played a key role in the creation of language and human values. I imagine a tribe whose members had an approximate of twenty to thirty-five years to accumulate knowledge—such as food preparation, hunting strategies, tool-making, social skills, and avoiding predators.

Mar 18, 2024 | lesswrong.com | Miguel Dev

What did I do differently in this experiment? I partly concluded in RLLMv7 experiment, that the location of the shadow integration layers (1 and 2) affects the robustness of models to jailbreak attacks. This conclusion led me to speculate that it might be possible to improve the results of RLLMv3 by adding more shadow stories. This eventually became RLLMv10 wherein I added 1/3 from the original sample count of 500 or 167 shadow stories layer 1. This then brought the total 667 samples.

Mar 8, 2024 | lesswrong.com | Miguel Dev |Nathan Helm-Burger |Shankar Sivarajan |Radford Neal

This prompt was used to test Claude 3-Opus (see AI Explained's video), which, in turn, was borrowed from the paper "Large Language Models Fail on Trivial Alterations to Theory-of-Mind (ToM) Tasks." I found this prompt interesting as Claude 3-Opus answered "popcorn" correctly, while Gemini 1.5 and GPT-4 answered "chocolate". Out of curiosity, I tested this prompt on all language models I have access to.

Mar 7, 2024 | lesswrong.com | Miguel Dev

This is just a brief and light read. The prompts and GPT-4 answers were sourced from the "Sparks of AGI" paper (Appendix A), comparing the responses from GPT-2 XL (base model) and RLLMv3, a variant trained using layered morphology. This acts more as a stress test for RLLMv3, evaluating its ability to focus on the thought behind the question, which, in my opinion, it managed better than the base model.