PulseAugur
实时 20:46:55
English(EN) People praise the newest and shiny models like # Codex 5.5, yet I repeatedly encounter significant logic holes in what they produce. And it's tedious to explain

用户发现高级AI模型的逻辑缺陷和记忆问题

一位用户对当前高级AI模型的状况表示沮丧,指出存在重大的逻辑缺陷和缺乏持久记忆。尽管公众称赞 Codex 5.5 等模型,但由于模型无法在提示之间保留上下文,用户发现纠正其错误非常困难。这种经历让他们质疑AI是否真正解决了当今许多问题,特别是与时间限制相关的问题。 AI

影响 强调了当前AI模型面向用户的局限性,表明炒作与实际应用之间存在差距。

排序理由 用户对AI模型能力的观点文章。

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

报道来源 [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    People praise the newest and shiny models like # Codex 5.5, yet I repeatedly encounter significant logic holes in what they produce. And it's tedious to explain

    People praise the newest and shiny models like # Codex 5.5, yet I repeatedly encounter significant logic holes in what they produce. And it's tedious to explain all the context to a bot that forgets it three prompts later. # AI is not the answer to most of the problems we have to…