|
| ▲ | 8cvor6j844qw_d6 3 hours ago | parent | next [-] |
| It tends to bail occasionally for me once auth-related code comes into play. Nowadays Codex handles the bulk of the implementation and Fable/Opus on the planning. Not sure if Anthropic patched it, but early on its release the web UI Fable guardrails will trip if you mention you're a biologist. |
|
| ▲ | gensym an hour ago | parent | prev | next [-] |
| I hit it whenever doing anything related to security. Auditing code, probing systems, investigating suspicious user activity, etc. |
|
| ▲ | brookst 4 hours ago | parent | prev | next [-] |
| Yeah same. Multiple 20x max accounts, I typically hit > 50% of the fable usage limit on eace, literally never seen a guardrail. Maybe I’m boring? Maybe they have some kind of account reputation system? |
|
| ▲ | WatchDog 2 hours ago | parent | prev | next [-] |
| Doesn't it silently downgrade to Opus for ML work? |
|
| ▲ | SatvikBeri 3 hours ago | parent | prev | next [-] |
| I hit it once when I asked a question about whether butterflies remember anything from their time as caterpillars. I've never hit it for coding, but I also don't really do much related to security. |
| |
| ▲ | hparadiz 2 hours ago | parent [-] | | It's less likely to give you pushback if you inject your own AI personality into the prompt. |
|
|
| ▲ | jmvoodoo 3 hours ago | parent | prev [-] |
| I’ve only hit it twice. First time was a code review. Fair. 2nd time was literally me being lazy and telling it to commit and open a PR. Very strange. |
