Virtual Machinations: Using Large Language Models as Neural Computers: LLMs can function not only as databases, but also as dynamic, end-user programmable neural computers.
Author: 
Erik MeijerAuthors Info & Claims
Erik MeijerAuthors Info & ClaimsAbstract
We explore how Large Language Models (LLMs) can function not just as databases, but as dynamic, end-user programmable neural computers. The native programming language for this neural computer is a Logic Programming-inspired declarative language that formalizes and externalizes the chain-of-thought reasoning as it might happen inside a large language model.
References
[1]
Bengio, Y., Ducharme, R., Vincent, P., Janvin, C. 2003. A neural probabilistic language model. The Journal of Machine Learning Research, 3, 1137?1155; https://dl.acm.org/doi/10.5555/944919.944966.
[2]
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., Amodei, D. 2020. Language models are few-shot learners. Proceedings of the 34th International Conference on Neural Information Processing Systems. Article 159, 1877-1901; https://dl.acm.org/doi/abs/10.5555/3495724.3495883.
[3]
Chip, H. 2024. Sampling for text generation; https://huyenchip.com/2024/01/16/sampling.html.
[4]
Dong, Q., Li, L., Dai, D., Zheng, C., Wu, Z., Chang, B., Sun, X., Xu, J., Li, L., Sui, Z. 2023. A survey on in-context learning. arXiv:2301.00234; https://arxiv.org/abs/2301.00234.
[5]
Fodor, J. A. 1975. The Language of Thought. New York, NY: Thomas Y. Crowell Co.
[6]
Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Guo, Q., Wang, M., Wang, H. 2024. Retrieval-augmented generation for large language models: a survey. arXiv 2312.10997; https://arxiv.org/abs/2312.10997.
[7]
Hernandez, E., Sharma, A. S., Haklay, T., Meng, K., Wattenberg, M., Andreas, J., Belinkov, Y., Bau, D. 2024. Linearity of relation decoding in transformer language models. arXiv:2308.09124; https://arxiv.org/abs/2308.09124.
[8]
Karpathy, A. 2023. LLM OS. Bear with me I'm still cooking. X; https://x.com/karpathy/status/1723135784142979392.
[9]
Körner, P., Leuschel, M., Barbosa, J., Santos Costa, V., Dahl, V., Hermenegildo, M. V., Morales, J. F., Wielemaker, J., Diaz, D., Abreu, S., Ciatto, G. 2022. Fifty years of Prolog and beyond. arXiv:2201.10816; https://arxiv.org/abs/2201.10816.
[10]
Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., Liang, P. 2023. Lost in the middle: how language models use long contexts. arXi:2307.03172; https://arxiv.org/abs/2307.03172.
[11]
Mei, K., Li, Z., Xu, S., Ye, R., Ge, Y., Zhang, Y. 2024. AIOS: LLM agent operating system. arXiv 2403.16971; https://arxiv.org/abs/2403.16971.
[12]
Mellish, C. 1985. Some global optimizations for a Prolog compiler. Journal of Logic Programming 2(1), 43?66; https://www.sciencedirect.com/science/article/pii/0743106685900044.
[13]
National Weather Service. API Web Service documentation; https://www.weather.gov/documentation/services-web-api.
[14]
Necula, G. C. 2000. Proof-carrying code (abstract): design, implementation and applications. In Proceedings of the 2nd ACM SIGPLAN International Conference on Principles and Practice of Declarative Programming, 175?177; https://dl.acm.org/doi/10.1145/351268.351289.
[15]
OpenAI. Function calling. OpenAI Platform documentation; https://platform.openai.com/docs/guides/function-calling.
[16]
Packer, C., Fang, V., Patil, S. G., Lin, K., Wooders, S., Gonzalez, J. E. 2023. MemGPT: towards LLMs as operating systems. arXiv:2310.08560; https://arxiv.org/abs/2310.08560.
[17]
Siek, J. 2012. Crash course on notation in programming language theory; https://siek.blogspot.com/2012/07/crash-course-on-notation-in-programming.html.
[18]
Tegmark, M., Omohundro, S. 2023. Provably safe systems: the only path to controllable AGI. arXiv:2309.01933; https://arxiv.org/abs/2309.01933.
[19]
Tennent, R. D. 1977. Language design methods based on semantic principles. Acta Informatica 8, 97?112; https://link.springer.com/article/10.1007/BF00289243.
[20]
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., Zhou, D. 2023. Chain-of-thought prompting elicits reasoning in large language models. arXiv:2201.11903; https://arxiv.org/abs/2201.11903.
[21]
Wikipedia. Vector database; https://en.wikipedia.org/wiki/Vector_database.
[22]
Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T. L., Cao, Y., Narasimhan, K. 2023. Tree of thoughts: deliberate problem solving with large language models. arXiv:2305.10601; https://arxiv.org/abs/2305.10601.
[23]
Yao, S., Zhao, J., Yu, D., Du, N., Shafran, I., Narasimhan, K., Cao, Y. 2023. ReAct: synergizing reasoning and acting in language models. arXiv 2210.03629; https://arxiv.org/abs/2210.03629.
Index Terms
- Virtual Machinations: Using Large Language Models as Neural Computers: LLMs can function not only as databases, but also as dynamic, end-user programmable neural computers.
Index terms have been assigned to the content through auto-classification.
Recommendations
Layout-sensitive language extensibility with SugarHaskell
Haskell '12: Proceedings of the 2012 Haskell SymposiumProgrammers need convenient syntax to write elegant and concise programs. Consequently, the Haskell standard provides syntactic sugar for some scenarios (e.g., do notation for monadic code), authors of Haskell compilers provide syntactic sugar for more ...
Compiling a reflective language using MetaOCaml
GPCE 2014: Proceedings of the 2014 International Conference on Generative Programming: Concepts and ExperiencesA reflective language makes the language semantics open to user programs and allows them to access, extend, and modify it from within the same language framework. Because of its high flexibility and expressiveness, it can be an ideal platform for ...
Layout-sensitive language extensibility with SugarHaskell
Haskell '12Programmers need convenient syntax to write elegant and concise programs. Consequently, the Haskell standard provides syntactic sugar for some scenarios (e.g., do notation for monadic code), authors of Haskell compilers provide syntactic sugar for more ...
Comments
Information & Contributors
Information
Published In
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 19 July 2024
Published in QUEUE Volume 22, Issue 3
Check for updates
Qualifiers
- Research-article
- Popular
- Editor picked
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 6,884Total Downloads
- Downloads (Last 12 months)6,884
- Downloads (Last 6 weeks)3,774
Reflects downloads up to 12 Sep 2024
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderMagazine Site
View this article on the magazine site (external)
Magazine SiteGet Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in