Emergent Representations of Program Semantics in Language Models Trained on Programs · HackerPapers discussions

Emergent Representations of Program Semantics in Language Models Trained on Programs — mentioned by nl

Tue, 03 Nov 2026 12:07:03 GMT

Yes you are right about random initilization of course. Long day here. For the second: No, not fine tuning at all. For one thing in-context learning is enough for learning novel tasks[1]. Secondly, it can do new things outside that data. LLMs build models of the world[2]. That means it can model novel behavior based on that internal representation. [1] https://arxiv.org/abs/2005.14165 [2] https://arxiv.org/abs/2305.11169

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — mentioned by altruios

Wed, 19 Aug 2026 22:05:17 GMT

https://www.youtube.com/watch?v=uRDBco-cSK4 https://www.technologyreview.com/2024/11/27/1107377/a-minecr... sadly paid-walled (and decently coded) article. The point is, there appears to be emergent behavior happening: the forming of religion, governance, and social interaction that was not in any system-card. Which makes sense, A brain in a vat with no external stimuli is a boring thing indeed, so too would an LLM be outside of a harness and any input. But put either in a society... More generally: if having an internal model of how the world works improves next token prediction, then the…

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — mentioned by satvikpendem

Sat, 07 Mar 2026 16:31:03 GMT

https://arxiv.org/abs/2305.11169 https://arxiv.org/abs/2506.02996

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — mentioned by famouswaffles

Mon, 19 Aug 2024 16:44:44 GMT

You are making a lot of assumptions that are mostly wrong. Case in point: https://arxiv.org/abs/2305.11169 I'm asking for something testable, not some post-hoc rationalization you believe to be true. I'm not asking you to tell me how you think LLMs work. I'm asking you to define "real reasoning" such that i can test people and LLMs for it and distinguish "real reasoning" from "fake reasoning". This definition should include all humans while excluding all LLMs. If it cannot, then it's just an arbitrary distinction.

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — mentioned by famouswaffles

Sun, 25 Jun 2023 15:38:59 GMT

>But to know that, one has to understand what the data means semantically. And our current AIs ... well, don't. Another wrong statement, you're on a roll today. https://arxiv.org/abs/2305.11169 https://arxiv.org/abs/2306.12672 There's a word we would use to describe your confidently erroneous statements were it one of the outputs an LLM. Wonder what that might be..

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — HN submission

Tue, 13 Jun 2023 15:38:59 GMT

Evidence of Meaning in Large Language Models Trained on Programs

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — mentioned by famouswaffles

Mon, 22 May 2023 23:49:02 GMT

>Actual reasoning, or reconstruction of existing texts containing similar reasoning? The papers were linked in another comment. 3 of them don't even have anything to do with a existing dataset testing. so yeah, actual. for the world model papers https://arxiv.org/abs/2210.13382 https://arxiv.org/abs/2305.11169 >Lack of access to cameras or vehicle controls isn't why it can't drive a car. It would be best to wait till what you say can be evaluated. that is your hunch, not fact. >The existence of numerous ChatGPT jailbreaks is evidence to the contrary. No it's not. People fall for social…

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — HN submission

Sun, 21 May 2023 15:37:41 GMT

Evidence of Meaning in Language Models Trained on Programs

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — mentioned by famouswaffles

Sun, 21 May 2023 02:46:45 GMT

No world model ? A world model is so obvious papers like these are more confirmation than surprise https://arxiv.org/abs/2305.11169 https://arxiv.org/abs/2210.13382 There a certain sentiment that AGI however you wish to define it won't infact be a "We'll know it when we see it" situation but rather a "AGI will arrive long before consensus reaches its AGI". LLMs have made me believe this will 100% be the case, either way. It's one thing to argue over things we can't evaluate even now but man the 100th "They can't reason!" every week is pretty funny when you can basically take your pick of…

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

Emergent Representations of Program Semantics in Language Models Trained on Programs — HN submission

Fri, 19 May 2023 18:02:29 GMT

Evidence of Meaning in Language Models Trained on Programs

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