We Should Take Text Optimization More Seriously

kept by eddie jun 10

Text optimization—modifying prompts, context, memory, and harnesses—is a legitimate, sample-efficient learning mechanism that deserves the same rigorous study as weight optimization.

The Problem is Prompt Debt
Hand-tuning natural language prompts for AI systems accumulates debt that slows iteration, locks teams to one model, and should be replaced with metrics, tests, and automated prompt optimization.
also on DSPy, #machine-learning, #software-engineering, #developer-tools
9 Observations from Building with AI Agents
Building AI agents reveals nine lessons including using best models for prototyping, fine-tuning for stable tasks, static typing to reduce hallucinated code, and closed-loop prompt optimization.
also on DSPy, #software-engineering, #developer-tools
Where’s My Flying Car? - by Bryan Bischof
AI voice agents, coding tools, writing apps, personal assistants, and memory systems still lack polished, daily-driver UX by end of 2025.
also on Notion, Cursor, OpenAI, #developer-tools
Understanding is the new bottleneck
As AI agents write code faster than humans can review, understanding remains critical for creative participation, not just verification.
also on Notion, Cursor, #ai-coding, #software-engineering, #developer-tools