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。

The Curious Similarity Between LLMs and Quantum Mechanics

16 点作者 rdlecler13 个月前

7 条评论

herculity2753 个月前
This is godawful slop written by someone who seems to have a cursory enthusiast's understanding of either of these topics.
评论 #43015316 未加载
评论 #43015400 未加载
评论 #43017084 未加载
mike_ivanov3 个月前
This one makes more sense <a href="https:&#x2F;&#x2F;link.springer.com&#x2F;article&#x2F;10.1007&#x2F;s10701-021-00503-3" rel="nofollow">https:&#x2F;&#x2F;link.springer.com&#x2F;article&#x2F;10.1007&#x2F;s10701-021-00503-3</a><p>Emergent Quantumness in Neural Networks<p>Abstract: ...Madelung equations, that is, a hydrodynamic form of the Schrödinger equation, can be derived from a canonical ensemble of neural networks where the quantum phase was identified with the free energy of hidden variables.
throwaway2903 个月前
&gt; Tokens take on definite semantic meaning defined by their context.<p>&gt; Quantum particles resolve to particles upon measurement<p>Tokens don&#x27;t have meaning though, it is in our heads. Particles are measurable on the other hand
Sharlin3 个月前
Both LLMs and QM are based on linear algebra. That’s pretty much where the similarities end.
评论 #43015987 未加载
gyrovagueGeist3 个月前
ah, yes, the spooky similarities of hilbert spaces and probability theory
ajkjk3 个月前
I think there&#x27;s more to this than the skeptical commenters here think.<p>The closer you look at quantum mechanics the more it seems to be entirely (in some sense) information-theoretic, although this nature is largely concealed from our vantage point on the inside. Measurement and quantization are due to the fact that we&#x27;re part of any quantum system we measure and we have to experience a single value for our measurement, which comes out as a probability distribution over possible values (although why it takes the exact distribution that it does is a still mysterious, I believe?). Entropy and decoherence under time evolution result from the fact that if you let a bunch of states mix together for a while they statistically tend into more decohered configurations. Conservation laws seem to be slightly emergent rather than completely fundamental: internal to systems some limited &#x27;off-shell&#x27; interactions that don&#x27;t conserve e.g. energy are allowed, but these are suppressed by the time we measure anything, so we only experience the laws holding exactly.<p>When all of this is peeled away, the resulting system looks like &quot;a bunch of initial (discrete) data, plus rules for looking at the implications of that data as it is allowed to interact with other data, in such a way that certain high-amplitude states amplify and low-amplitude states get destructively interfered away, allowing complex patterns to crystallize and replicate&#x2F;evolve at increasingly macroscopic scales&quot;. Which, if you squint, looks a lot like a cellular automata such as Conway&#x27;s Game of Life. But it can also (under some squinting) look like how thinking works, or how neural networks work, -ish: start with some low level bits, look for patterns in those, look for patterns in those patterns, etc, and then observe that certain resulting states have their amplitudes driven to 1 while others are driven to 0. Which reminds me, at least, of convolutional NNs. I don&#x27;t know much about how LLMs work but I suspect they are perhaps slightly less good of an analogy, although perhaps they do but it&#x27;s just slightly more masked by the architecture.<p>I wouldn&#x27;t, like, bet anything on the details, but I suspect that in the long run there will be some widely-held hypothesis (similar in status to the Church-Turing thesis) that the universe, the brain, neural networks, and cellular automata all have some essential symmetry in their structure. Something to do with the requirements for how a system has to work if it is going to have emergent complexity.<p>(Incidentally I think this is what Stephen Wolfram sees also and is the basis for his quirky &quot;Wolfram Physics Project&quot;, although I suspect that in his overconfidence&#x2F;immunity to critique he&#x27;s pretending to see a lot more of it than he actually does.)
Terr_3 个月前
Punchline of <a href="https:&#x2F;&#x2F;www.smbc-comics.com&#x2F;comic&#x2F;the-talk-3" rel="nofollow">https:&#x2F;&#x2F;www.smbc-comics.com&#x2F;comic&#x2F;the-talk-3</a>
评论 #43017135 未加载
评论 #43017893 未加载