Astra fails in similar ways, and at similar frequency, as GPT 5.6 Sol does. It often goes way out of scope, or just stops prematurely, or tries to find odd and even dangerous workarounds when it gets stuck.
It's phenomenal at computer use and 3D stuff. I've been using it less and less for coding.
LLM's introduces problems, and it finds them in its own internal thinking. But instead of actually modifying the previous generated answer to fix the real issue, it adds another layer to deterministically guard around it, greatly expanding the scope of the fix. This scales with effort, and the result is spaghetti and with a side of bugs.
Best to stick with a high end model + low effort, do a manual pass on high effort and fix the bugs you know are reachable.
saejox · · focus · HN ↗
xAI missed its chance, Ball is on Anthropic's court.
enraged_camel · · focus · HN ↗
It's phenomenal at computer use and 3D stuff. I've been using it less and less for coding.
sneezychl · · focus · HN ↗
Best to stick with a high end model + low effort, do a manual pass on high effort and fix the bugs you know are reachable.