Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis · HackerPapers discussions

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — mentioned by jsrozner

Mon, 14 Sep 2026 21:55:52 GMT

One funny thing is that in order to tune the models to make what they're doing explainable to humans, you need to have humans involved in the RL pipeline to indicate which explanations are good. You can understand this as learning a mapping between the model's internal "world" (i.e., 'meaning,' which is hopefully coherent and consistent -- but definitely not always! see, e.g., https://arxiv.org/html/2505.11581v1) and language (i.e. 'form') that reflects that world. For this to work, you need both coherent / consistent internal model worlds, and also good mappings onto human language.…

Paper and discussion history. A mention is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — mentioned by ianjbutler

Fri, 28 Aug 2026 06:52:05 GMT

Is being wrong/ignorant about whether/how something can be automated the same as having a preference for doing it manually? Maybe so if it's your patent, your thesis I guess.. But as it relates to more/less magic, maybe the more modern lens on this is e.g. https://arxiv.org/html/2505.11581v1 . Is manual feature-engineering more like what you'd evolve, or more like what you'd get from SGD ? Feasibility and performance is always a question, there are others like what is robust, stable, adaptable, predictable, explainable. Maybe the manual-features people were interested in something besides the…

Paper and discussion history. A mention is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — mentioned by publicdaniel

Thu, 26 Feb 2026 12:23:43 GMT

This reminds me of the latest Ken Stanley paper on representations. “Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis“ https://arxiv.org/abs/2505.11581

Paper and discussion history. A mention is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — mentioned by vatsachak

Sun, 30 Nov 2025 16:18:19 GMT

"Animals experience pressure for a lot more "general" intelligence because of the highly multi-task and even actively adversarial multi-agent self-play environments they are min-max optimized within, where failing at any task means death. In a deep optimization pressure sense, LLM can't handle lots of different spiky tasks out of the box (e.g. count the number of 'r' in strawberry) because failing to do a task does not mean death." Point to me a task that a human should be able to perform and I will point to you a human who cannot perform that task, yet has kids. Survival is not a goal, it is…

Paper and discussion history. A mention is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — HN submission

Sat, 15 Nov 2025 01:07:24 GMT

Questioning Representational Optimism in Deep Learning

1 point; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — HN submission

Thu, 05 Jun 2025 14:17:23 GMT

Questioning Representational Optimism in Deep Learning

1 point; 3 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — mentioned by kmeisthax

Tue, 03 Jun 2025 18:06:09 GMT

If there aren't any five-legged dogs in your trainset, it's safer[0] to just remember that all dogs are four-legged than to actually recognize and count legs. After all, you might have a few images of dogs in your trainset that are misleading enough to look five-legged (e.g. because a dog is in front of another dog). Overrepresentation is a different source of bias. That's what gives you, say, image generators that always draw "golden 1970s sci-fi robot" as C3-PO even when given additional instructions to draw something else. Both of these problems are manifestations of the difference between…

Paper and discussion history. A mention is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — mentioned by akarshkumar0101

Tue, 20 May 2025 16:09:28 GMT

Tweet: https://x.com/kenneth0stanley/status/1924650124829196370 Arxiv: https://arxiv.org/abs/2505.11581

Paper and discussion history. A mention is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — HN submission

Tue, 20 May 2025 11:24:07 GMT

Questioning Representational Optimism in Deep Learning

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis — mentioned by mattdesl

Tue, 20 May 2025 08:41:04 GMT

The full title of the paper is “Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis.” https://arxiv.org/abs/2505.11581

Paper and discussion history. A mention is not an endorsement.