Custom harness lets devs mix older models: 'previous models are good enough for daily work'
omarsar0 · x · 2026-09-14
omarsar0 explains he's been 'pacing' model usage for months: daily work mixes Opus 5, GPT-5.6 Sol and open models like DS4, rarely needing Fable 5.1 or GPT-6 Astra except for long-running tasks or demos.
His two points: a custom harness gives more than control — it enables custom dynamic workflows across models; and previous models are already good enough for most real-world tasks, so you don't need the latest and greatest for everything.
Related event: DAIR.ai Founder Mixes Opus 5 and GPT-5.6 for Daily Work(2 posts)→
More from coding & agent
- The key coding skill now: directing agents well — and knowing when not to trust them — YvesMulkers · 2026-09-14
- chrome-mcp fills a 30-field form in real Chrome: 148 logged, auditable actions — SYEDNIICK · 2026-09-14
- Building a Local Router With Smart Fallbacks to Stop Rate Limits Killing Your AI Agents — phanue1 · 2026-09-14
- A SQLite/S3 filesystem with per-directory OpenPolicyAgent scripts for AI agents — tobowers · 2026-09-14
- Processing SIEM tickets with AI: workflow tool or pure agent? — Melodic_Tooth6885 · 2026-09-14
- Same 3D simulation prompt: Agnes 2.5 Pro Beta costs ~$0.20 vs ~$1.70 on GPT-5.6 Sol — iamaliveix · 2026-09-14