AI stuff
Everything I want to remember about LLMs and other machine learning stuff
AI stuff
Avoiding generative models is the rational and responsible thing to do – follow-up to “Trusting your own judgement on ‘AI...’”
Baldur Bjarnasonbaldurbjarnason.com
the author makes some interesting points about too much anecdotal evidence in developer productivity research and self experimentation but goes too far in my opinion.
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.
How to think about agent frameworks
blog.langchain.dev
Does AI Actually Boost Developer Productivity? (100k Devs Study) - Yegor Denisov-Blanch, Stanford
youtube.comA working prototype often says more than a 10-page PRD. You can build faster than you can explain. And if something runs, it’s easier to rally people around it.But this isn’t really about writing. It’s about bad writing and shallow product artefacts.Bloated PRDs no one reads. Strategy decks that signal alignment but avoid decision. Words that sound... See more
Prototypes Don’t Make Decisions - On writing, judgment, and why clarity still matters in product even when you can prototype fast. | Stuart Winter-Tear posted on the topic | LinkedIn
But I don’t think he really answers the question he shows in the beginning: Why can’t I just unplug it? Why is Distribution not the bottleneck? Feels a but fluffy
Building and evaluating AI Agents — Sayash Kapoor, AI Snake Oil
youtube.comWhat to keep in mind as an AI Engineer working with agents
How We Build Effective Agents: Barry Zhang, Anthropic
youtube.comMCP: An (Accidentally) Universal Plugin System
worksonmymachine.ai