YC Partner Argues Most AI Apps Are Currently 'Horseless Carriages'

Pete Koomen, a Y Combinator partner, argues that current AI applications often fail by unnecessarily constraining their underlying models, much like early automobiles that mimicked horse-drawn carriages rather than reimagining transportation. In his detailed critique, Koomen uses Gmail's AI email draft feature as a prime example. The tool generates formal, generic emails that don't match users' actual writing styles, often producing drafts longer than what users would naturally write.

The critical flaw, according to Koomen, is that users cannot customize the system prompt -- the instructions that tell the AI how to behave. 'When an LLM agent is acting on my behalf I should be allowed to teach it how to do that by editing the System Prompt,' Koomen writes. Koomen suggests AI is actually better at reading and transforming text than generating it. His vision for truly useful AI email tools involves automating mundane work -- categorizing, prioritizing, and drafting contextual replies based on personalized rules -- rather than simply generating content from scratch. The essay argues that developers should build 'agent builders' instead of agents, allowing users to teach AI systems their preferences and patterns.

Read more of this story at Slashdot.