Native function calling in LLMs and the use of agents serve distinct yet complementary roles in the deployment of AI systems. Function calling is best for direct, single-step actions linked...
Read more → I am a big fan of local models for quick and efficient prototyping. I am also at home with the out-of-the-box CLIs they offer. However, sometimes the convenience of a...
Read more → Another fantastic research memo from Anthropic that dives into whether language models can match human persuasiveness. They focused on complex and emerging topics where people are less likely to have...
Read more → While Fine-Tuning, RAG, and Prompt Engineering are covered exhaustively, not a lot of attention is paid to continuous pre-training of LLMs. As new data becomes available, continuous pre-training is a...
Read more → Humans are capable of strategically deceptive behavior — acting normally harmless and helpful in most situations but then behaving very differently to pursue alternative objectives when the opportunity arises. Can...
Read more →