๐ ๐ ๐ช ๐ | ๐ฌ ๐ณ ๐ ๐๐ฝ | ๐ฌ ๐ ๐ | ๐ฌ ๐ผ ๐๐ฝ | ๐ฅ ๐ฌ ๐ณ ๐ ๐๐ฝ | ๐ช ๐ฑ ๐ฆ ๐จ | ๐ ๐ก ๐ฒ | ๐ ๐ผ ๐๐ฝ | ๐ ๐ก ๐ฒ | ๐ฅ ๐ฌ ๐ณ ๐ ๐๐ฝ i-๐-wi-jeสณ | สฐau-ni-ti-noสณ au-no-pa au-ndi-tiสณ ๐ฅ-au-ni-ti-noสณ wa-pi-naแตwa ti-ru-te ti-nd-tri ti-na-ru-he สฐau-ni-ti-noสณ i-301-wa-ja/e | สฐau-... jaแต-di-ki-to i-pi-na-ma si-ru-te ta-na-ra te-ti-u ta-na-te i-da ๐ แดดI ๐ฎ WA ๐ฑ JA ๐ฑ JA ๐ DI ๐ธ KI ๐น TU ๐ แดดI ๐ข PI ๐ NA ๐ MA (๓ฒ)
I believe the phonetic values for Phaistos here were based on similarity.
i.e, evaluation, retention yes. variation or "planning" no.
That is not to say you cannot use LLMs. Alpha evolve does exactly that. It uses an external simple evolutionary planner. The overarching point he's making is that our planner is still "dumb" and we need to work on it.
When you iteratively guide an LLM in claude code, you are the external planner. That also works.
Are you sure? It says:
"It's fine to use LLMs to answer questions, analyze, distill, refine, check, suggest, review. But not to *create*."
That exception is experimental and somewhat limited; Only allows "well tested, high-quality" PRs on parts of the codebase that have a low probability of causing soundness issues, and it has a seperate review process with much higher standards.
And it requires the reviewer to agree to the use of LLMs ahead of time, before the PR is opened.
IMO, it has a high likelihood of degrading to a closed system, where some programmers with a good track record have little issue merging LLM generated PRs, while anyone without a reputation will struggle to even open an ai-assisted PR.
If a green checkmark goes away so be it. AI might or may not understand how to fix it but it's no burden to the user / developer.