| ▲ | varispeed 4 hours ago | |
They are unusable (unless you want to deliberately destroy your codebase). So if Cursor's models are Kimi based, then well. I'll skip them altogether. | ||
| ▲ | vidarh 2 hours ago | parent | next [-] | |
Kimi works great in their CLI, but their CLI has a number of workarounds for quirks of their models, including detecting when the model gets into a loop, and reverting to a checkpoint but letting the model compose a "message" to its past self (search their CLI for "BackToTheFuture"...) It doesn't work so well in a harness that doesn't take those quirks into account. | ||
| ▲ | ok_dad 8 minutes ago | parent | prev | next [-] | |
I only use composer 2.5 day to day and it works fine with human review. | ||
| ▲ | esskay 19 minutes ago | parent | prev | next [-] | |
Composer 1.x was poor. The new one is a totally different beast and absolutely fine for day to day. | ||
| ▲ | jmcqk6 2 hours ago | parent | prev | next [-] | |
I'm using Composer extensively, and it works great for me. Your experiences are not universal. | ||
| ▲ | bel8 3 hours ago | parent | prev | next [-] | |
I wouldn't skip at least testing the original. Model distilling done by Cursor could be the culprit. | ||
| ▲ | Bnjoroge 2 hours ago | parent | prev | next [-] | |
They are far from unusable. They aork great for 80-90% of a typical full stack dev. Alot less useful for more noche stuff | ||
| ▲ | qingcharles 2 hours ago | parent | prev [-] | |
They're not unusable, they're just bad when compared with all the real frontier models. | ||