Opus Beats Astra on Design Quality, But Costs 3x Time and Tokens
chaseleantj · x · 2026-09-13
In an ongoing 3D-generation experiment, the author prefers Opus's design output over Astra's and will use Opus high for subsequent tests — with the caveat that Opus takes about 3x the time and tokens compared to Astra.
More from coding & agent
- Models already understand harnesses: a minimal agent harness takes hours, but customization still needs you — omarsar0 · 2026-10-31
- krishnan on autonomous lab agents: criticism changed the next search, not just verdicts — krishnan · 2026-10-31
- krishnan proposes logging ruled-out troubleshooting hypotheses for future reopening — krishnan · 2026-10-31
- PI agent rejected 75 proposals in 30 hours; manager banned recurring bad ideas — krishnan · 2026-10-31
- Multi-agent AI lab autonomously researches quantum spins in diamond, revises drifting experiments — krishnan · 2026-10-31
- Build your own agent harness: omarsar argues vendor harnesses will quietly constrain users — dair_ai · 2026-10-31