Memory Augmented Large Language Models are Computationally Universal · HackerPapers discussions

Memory Augmented Large Language Models are Computationally Universal — mentioned by Gomotono

Fri, 29 May 2026 08:19:32 GMT

I do. This is the newest thng i'm aware of: https://www.percepta.ai/blog/can-llms-be-computers But there were papers in 2023 with a different approach requiring external memory https://arxiv.org/abs/2301.04589 too

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by naasking

Wed, 24 Sep 2025 14:18:25 GMT

Memory Augmented Large Language Models are Computationally Universal, https://arxiv.org/abs/2301.04589

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by famouswaffles

Sat, 03 Feb 2024 05:08:29 GMT

No, Transformers with memory are turing complete. Like i said, the modifications are trivial. https://arxiv.org/abs/2301.04589

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by famouswaffles

Tue, 17 Oct 2023 19:35:14 GMT

Transformers with memory can abstract recursively in theory. https://arxiv.org/abs/2301.04589. If it's just extra computation that's the kick then simply more tokens will suffice. You can even even implement a computation token if you wish. https://arxiv.org/abs/2310.02226 Frankly, the ability to truly abstract recursively is by no means necessary either. Humans can't actually do this. Either in every day practice (you will get bored, you will lose interest) or in theory (flawed memory, finite memory, you will die). Limited recursive abilities =/ trivial recursive abilities. The current state…

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by famouswaffles

Fri, 21 Jul 2023 02:32:34 GMT

With memory they are. https://arxiv.org/abs/2301.04589

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

Memory Augmented Large Language Models are Computationally Universal — HN submission

Sun, 09 Jul 2023 22:43:12 GMT

Memory Augmented Large Language Models Are Computationally Universal

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by spacebanana7

Fri, 12 May 2023 14:21:31 GMT

LLMs (at least the ones with read/write memory) can exactly simulate the execution of a universal Turing machine [1]. AFAIK running such models will therefore entails the same fundamental security risks as ordinary software. [1] https://arxiv.org/pdf/2301.04589.pdf

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by famouswaffles

Fri, 21 Apr 2023 01:04:04 GMT

Not even going to bother with the weird leap of logic you've made here but Memory augmented LLMs are computationally universal - https://arxiv.org/abs/2301.04589

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by famouswaffles

Mon, 10 Apr 2023 20:20:37 GMT

The significance of the paper is moreso the implications of how far ICL can take you rather than the ease/viability of the solution proposed. Sure there are better methods for arithmetic but arithmetic is extremely quantifiable with rigid steps. What happens when you step out of that kind of domain ? Like the above blog. or Code documentation. For example, you can paste new documentation in a gpt-4 instance and it will use it for your queries as if it trained on it. Basically Memory Augmented Large Language Models are Computationally Universal https://arxiv.org/abs/2301.04589. and you kind of…

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by famouswaffles

Wed, 29 Mar 2023 05:42:34 GMT

The idea that updating weights is particularly necessary is questionable. Memory augmented llms are computationally universal. https://arxiv.org/abs/2301.04589 and make no mistake, in context learning can be used in a meaningful way to resolve deficiencies. gpt-3 getting 98.5% accuracy (on even very large numbers) on addition arithmetic by describing the algorithm of addition to be performed on 2 numbers. https://arxiv.org/abs/2211.09066 In context learning is just overpowered. It's essentially implicit fine-tuning https://arxiv.org/abs/2212.10559v2 as for asking questions, llms can do that…

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by blurbleblurble

Fri, 17 Mar 2023 21:38:58 GMT

Well I don't understand the nitroglycerin reference and of course "computationally universal" doesn't mean "sentient" but the point is when you add the external memory they (Flan-U-PaLM 540B to be specific) have been demonstrated to be capable of simulating a specific, well defined Turing machine without special training. There are some other papers out there arguing this from a theoretical angle too, but this is the one whose title I quoted: https://arxiv.org/abs/2301.04589

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

Memory Augmented Large Language Models are Computationally Universal — HN submission

Fri, 17 Mar 2023 11:12:49 GMT

Memory Augmented LLMs Are Computationally Universal

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by famouswaffles

Thu, 16 Mar 2023 19:28:45 GMT

In context learning is already implicit finetuning. https://arxiv.org/abs/2212.10559. It's very questionable to what extent continuous training is necessary past a threshold of intelligence. Memory Augmented Large Language Models are Computationally Universal https://arxiv.org/abs/2301.04589

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

Memory Augmented Large Language Models are Computationally Universal — HN submission

Thu, 16 Mar 2023 14:12:03 GMT

Memory Augmented Large Language Models Are Computationally Universal

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by mad0

Wed, 15 Mar 2023 09:23:30 GMT

It does to some degree. Some people have shown that you can prompt GPT to behave like shell or python interpreter. Then you can "execute" some statements, of course to some degree of saneness. However I'm not sure if it does in this particular case where we ask it for explanation. Also see this paper: https://arxiv.org/pdf/2301.04589.pdf tldr if we equip LLM models with infinite memory it becomes Turing complete.

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

Memory Augmented Large Language Models are Computationally Universal — HN submission

Tue, 21 Feb 2023 09:09:55 GMT

Memory Augmented Large Language Models Are Computationally Universal

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

Memory Augmented Large Language Models are Computationally Universal — mentioned by blurbleblurble

Tue, 21 Feb 2023 09:03:08 GMT

The "predicting words" part of the language models is a building block, but the actual applications being built around the LLMs are using that predictive ability in very dynamic ways along with external memory, feedback and sophisticated control methods to attenuate and channel their behavior. And anyhow: > Memory Augmented Large Language Models are Computationally Universal https://arxiv.org/abs/2301.04589

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