TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

"But LLMs are not deterministic "

3 点作者 gandalfgeek大约 2 个月前

3 条评论

labrador大约 2 个月前
I really like this framing. It reminds me of how early steam engines needed governors—a simple mechanical feedback loop—to prevent them from spinning out of control. The engine itself wasn’t &quot;safe&quot; or &quot;stable&quot; by design; stability was something imposed externally through a control mechanism.<p>In a way, LLMs feel similar. Their internal workings may be probabilistic and unpredictable, but that doesn&#x27;t mean we can&#x27;t build external feedback loops—tests, validation layers, human oversight—to steer them toward reliable, useful outcomes. The unpredictability isn’t a flaw; it’s just a raw, unmanaged state that invites control systems around it.<p>Maybe what unsettles people is that the &quot;chaos&quot; is now at the language layer, where it feels more personal and less abstract than when it&#x27;s buried in hardware or OS internals. But we&#x27;ve always tamed unpredictable systems with good design—LLMs are just the next place to apply that thinking.
评论 #43519687 未加载
techpineapple大约 2 个月前
I find this both interesting and very wrong. On the one had there seem to be some potential edge cases where this framing could be useful. On the other hand I think “But LLMs are not deterministic” is really code for “I find limited utility in a tool that regularly acts aggressively contrary to my goals”
casenmgreen大约 2 个月前
I could be completely wrong, but I think determinism isn&#x27;t the issue.<p>The issue is that LLMs cannot explain their reasoning.<p>LLMs are not expert systems; expert systems provide an answer <i>and explaining their reasoning</i>.