AI stuff
Everything I want to remember about LLMs and other machine learning stuff
AI stuff
Everything I want to remember about LLMs and other machine learning stuff
Should the user write the system prompt? Maybe. But we could also write better, individual system prompts for users based on their context and allow them to edit it.
What to keep in mind as an AI Engineer working with agents
Very interesting insights in how reasoning models work. He argues that the intermediate "reasoning traces" (e.g., chains of thought) produced by LLMs are not necessarily meaningful or reliable, and that these traces can be misleading or simply stylistic rather than substantive.
Full text in my email
On the other side: There is often resistance to new tech, no matter how good or bad. But are top-down mandates the right tool? The overall post is a bit toxic but the core idea has merit.