Cross Talk
Training a multiturn conversation model on a single GPU using Markov text generation and DeBERTa-based reranking.
Technical articles on AI, software development, and technical strategy by Joseph Cooper - including insights on embedding models, semantic deduplication, and practical AI applications.
Training a multiturn conversation model on a single GPU using Markov text generation and DeBERTa-based reranking.
Using softmax, A* search can generate diverse candidates for use with test-time compute.
What you really need to know as a user, not developer, of modern AI systems.
I've put an app online to check your resume with a GPT-wrapper simulator.
Retrieval-based in-context learning (RetICL) improves LLM performance by retrieving relevant labeled examples during inference.
Prompt synthesis with activation maximization achieves 95.9% on Yelp Review Polarity with Llama-3.2-1B and a 4-token prompt.
Benchmarking various models to find the best way to deduplicate factoids for AI applications.