Lunar Retro
@lunarretro.bsky.social did:plc:u3dd2n6xd4amclcdifhhlk27
Author of The Choir Mythos. http://www.choir-files.com | Co-writer for @shotRoHi Half of the Crown: http://tinyurl.com/2p9acw6s
Bluesky’a katılma tarihi:
- Takipçi
- 77
- Takip edilen
- 159
- Post
- 112
- Sıralamaya girdiği gün
- 0
Özet
Lunar Retro (@lunarretro.bsky.social), 18 Ekim 2023 tarihinde katılan bir Bluesky kullanıcısı. 77 takipçisi var, 159 hesabı takip ediyor ve 112 post paylaştı.
Sıralama geçmişi
Bu hesabın postlarının Debya günlük listesine girdiği en iyi günler.
Bu hesap henüz günlük sıralamaya girmedi.
Son beğendiği postlar
Bluesky ağındaki herkese açık beğeniler.
Every time an LLM-generated PR gets merged to any repo, my trust for it goes down a bit. Glad Godot is safe for now. Hope it stays that way.
Postu gösterThat's not even considering the emotional hit of getting a perfectly reasonable pull request automatically rejected by an AI because the dice landed the wrong way. Delegating a technical decision upon a probabilistic model is a stupid move, and no reasonable project should opt into doing this.
Postu gösterLLMs can't even "agree" with themselves upon repeated querying. You could try this and get a different judgment each time, regardless of what the worth of a contribution might be. It's not going to save anyone any stress if maintainers need to double check the decision the machine made.
Postu gösterIt's going to be a burden maintainers either way. What makes you think an LLM can make a good, automated judgement call on the worth of a contribution regardless of whether it's made by a human or another LLM? LLMs are not a tool for decision making and it's naive to think that it is.
Postu gösterand AI judging human contributions is especially not a good thing AI shouldn't be making any judgement at all
Postu göster
Blokladığı hesaplar
Bluesky’da bloklar herkese açık kayıtlardır.