| ▲ | zahlman a day ago |
| For a project like this, relying on AI assistance also makes it effectively dead in the water. |
|
| ▲ | minimaxir a day ago | parent | next [-] |
| Why? |
| |
| ▲ | all2 a day ago | parent | next [-] | | Time-cost for machines instead of willing knowledgeable humans. The former requires money, the latter requires passion. Arguably, passion for a project is without price. | | |
| ▲ | zero1009 a day ago | parent | next [-] | | Someone pays for the AI? That's the new human maintainer. | | |
| ▲ | nozzlegear a day ago | parent | next [-] | | Who will pay if someone, somewhere is not passionate about it? | | |
| ▲ | throw1234567891 a day ago | parent [-] | | You can spin up a model locally and pay yourself. Who will maintain the project if the passionate sole maintainer burns out? | | |
| ▲ | nozzlegear 13 hours ago | parent | next [-] | | I strictly use only local models, so I agree, but the project was built with Fable so my argument hinges on the assumption that the maintainer is going to continue using Fable and needs to pay for it. | |
| ▲ | inigyou 20 hours ago | parent | prev [-] | | Which model works well? | | |
| ▲ | all2 15 hours ago | parent [-] | | Qwen 3.6 27b at q6 works decently well on 24GB of VRAM |
|
|
| |
| ▲ | bloppe a day ago | parent | prev [-] | | Hypothetically, maybe. In practice, probably not. | | |
| ▲ | CookieCrisp a day ago | parent [-] | | If it's valuable enough to someone, and it isn't keeping up, someone will pay. If it's not valuable enough for someone to pay, then who cares? | | |
|
| |
| ▲ | jack_pp a day ago | parent | prev [-] | | Humans have time-cost too, much higher than machines. Considering SOTA right now, for a project like this it would make more sense for the community to contribute and verify tests, sponsor updates with $. |
| |
| ▲ | wild_pointer a day ago | parent | prev | next [-] | | Trust | |
| ▲ | bt1a a day ago | parent | prev [-] | | [flagged] | | |
| ▲ | chomp a day ago | parent [-] | | I don’t want to be mean, but try to run a large project and you’ll realize there’s more to it than “can I find some bodies to crank out code” |
|
|
|
| ▲ | frollogaston a day ago | parent | prev | next [-] |
| Not convinced. I was looking for an answer like "it doesn't actually have parity with CPython." If it does, that's a decent indication that it can be sustained. |
|
| ▲ | simonw a day ago | parent | prev [-] |
| Good luck implementing and then maintaining a project of this size and complexity at ~100 lines of verified code per human developer per day. |
