Are Harnesses Worth the Cost?

kept by eddie oct 14

A behavioral harness offers no reliability gain for frontier models like GPT-6 Sol but significantly improves consistency and cost-effectiveness for the cheaper GPT-6 Luna model.

Fragments: April 29
The post collects expert perspectives on AI-assisted development, emphasizing verification over generation, harness engineering, function structure, and the cultural divide between software thinking and human experience.
also on Birgitta Böckeler, #ai-coding, #software-engineering, #developer-tools
Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war
Anthropic’s Claude Opus 5.5 and OpenAI’s GPT‑6 Sol/Luna launch with steep price cuts, undercutting prior models and triggering a new AI model price war.
also on GPT-6 Sol, GPT-6 Luna, #ai-coding, #ai, #developer-tools
Hi, Tomorrow we are re-opening the Pro $200 subscriptions to new subscribers, but together with it we are also changing how we calculate th
OpenAI will reopen its $200 Pro subscription tomorrow but cut its effective API usage by half, promising added non-usage benefits and future model efficiency gains.
also on GPT-6 Sol, GPT-6 Luna, #ai-coding, #developer-tools
On cognitive debt
Nate Meyvis argues that cognitive debt in AI-generated codebases is not inherently worse than in traditional codebases, and AI can help mitigate it.
also on Martin Fowler, #ai-coding, #software-engineering, #ai, #developer-tools
AddyOsmani.com - Bias Toward Action
Bias toward action means taking the smallest responsible step with guardrails, using reversible decisions, error budgets, and safety nets to learn faster without catastrophic failure.
also on Martin Fowler, #software-engineering