Dev burns $700 in Opus 5.5 credits on one weekend build: 'never seen a model do that'
ivan_bezdomny · x · 2026-10-06
Developer ivanbezdomny says he had Opus 5.5 grind on a brand-new system over the weekend — $700 in credits later, the model kept going and produced a solid system.
He notes he's never seen a model sustain long tasks that well; Astra ran even longer but was far less organized and dumped bad code. The context: a broader argument that AI × consultants is "the main show" reshaping software and IT services.
Related event: AI Disruption Narrative Challenged by Consulting Strength and Model Power(2 posts)→
More from coding & agent
- Gradio says training your own models via a single ml-intern prompt is huge alpha — Gradio · 2026-10-06
- Most performance wins are under 5 lines of code — a 20% zstd fix case — DanielLockyer · 2026-10-06
- Developer laments that Claude Code and Codex do everything, leaving him out of the loop — zsakib_ · 2026-10-06
- Building agent skills from a structured wiki distilled from past experience — rseroter · 2026-10-06
- Using EvoX to draft bug reports: AI quietly turns "not shown" into "user skipped" — yawning42 · 2026-10-06
- Chunkr: open-source Rust chunking lib claims ~20x speedup over LangChain with full benchmarks — Ok_Cartographer5609 · 2026-10-06