HackerPapers

arXiv:2206.08896cs.NE

Evolution through Large Models

Joel Lehman, Jonathan Gordon, Shawn Jain, Kamal Ndousse, Cathy Yeh, Kenneth O. Stanley

Abstract

This paper pursues the insight that large language models (LLMs) trained to generate code can vastly improve the effectiveness of mutation operators applied to programs in genetic programming (GP). Because such LLMs benefit from training data that includes sequential changes and modifications, they can approximate likely changes that humans would make. To highlight the breadth of implications of such evolution through large models (ELM), in the main experiment ELM combined with MAP-Elites generates hundreds of thousands of functional examples of Python programs that output working ambulating robots in the Sodarace domain, which the original LLM had never seen in pre-training. These examples then help to bootstrap training a new conditional language model that can output the right walker for a particular terrain. The ability to bootstrap new models that can output appropriate artifacts for a given context in a domain where zero training data was previously available carries implications for open-endedness, deep learning, and reinforcement learning. These implications are explored here in depth in the hope of inspiring new directions of research now opened up by ELM.

arXiv comments
Journal reference
DOI
Subjects
cs.NENeural and Evolutionary Computing

On Hacker News

Linked by 4 identifiable commenters in 21 comments across 18 threads, from Dec 2022 to May 2025. Found in 2 HN submissions from Jun 2022 to Jun 2024. Open submission discussions.

Comments linking this paper, per year.

Discussed in comments18 threads

  1. AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms 1 comment

    • Genetic programming systems have periodically made improvements to algorithms (dating back decades). Whether LLM-powered GP, which is effectively what this is, will be a step change or an evolution of that is still an open question I think. I'm also a little wary of reading too…

      _deliriumView on HNParent context

  2. 2025 AI Index Report 2 comments

    • It's overfitting. Some people say they find LLMs very helpful for coding, some people say they are incredibly bad. I often see people wondering if the some coding task is performed well or not because of availability of code examples in the training data. It's way worse than…

      namariaView on HNParent context

    • I am sorry but that's nonsense. I quoted the paper "Evolution through Large Models" written in collaboration between OpenAI and Anthropic researchers "In other words, the model learns to predict plausible changes to code from examples of changes made to code by human…

      namariaView on HNParent context

  3. ARC Prize – a $1M+ competition towards open AGI progress 1 comment

    • The key ingredients are not the humans but the feedback they carry to the model. Humans are embodied and can test ideas in the real world, LLMs need some kind of special deployment to achieve that. It just so happens that chat rooms are such a deployment. For example, AlphaZero…

      visargaView on HNParent context

  4. ResearchAgent: Iterative Research Idea Generation Using LLMs 1 comment

    • When you can run experiments quickly it becomes feasible to use ML and evolutionary methods to do novel discoveries, like AlphaTensor's better matrix multiplication than Strassen, and AlphaZero's move 37, upturning centuries of game strategy. The paper "Evolution through Large…

      visargaView on HNParent context

  5. DBRX: A new open LLM 1 comment

    • No but some model serving tools like llama.cpp do their best. It's just a matter of choosing the right serving tools. And I am not sure LLMs could not optimize their memory layout. Why not? Just let them play with this and learn. You can do pretty amazing things with…

      visargaView on HNParent context

  6. A Philosophical Introduction to Language Models 1 comment

    • This is the "Anti Stochastic Parrot" paper. I am happy to finally read a philosophical paper on LLMs. I just have a small quip. > While LLMs show promise in various forms of task generalization, their participation in the ratcheting process of cultural learning thus appears…

      visargaView on HNParent context

  7. The Darwinian argument for worrying about AI 1 comment

    • > A lot of the AI doomerism comes from folks who do not understand the real complexities in making systems which really can function in a fully autonomous way in an environment which is hostile and dynamic. I agree. Autonomy is hard. But a weaker version of it is possible - self…

      visargaView on HNParent context

  8. LLM Powered Autonomous Agents 1 comment

    • LLMs can be used to propose candidates for chemical, medical, coding, and basically any domain where you got enough data to create a model but it is exponentially hard to search for solutions. They can be the core module in an agent that learns by RL or evolutionary methods - so…

      visargaView on HNParent context

  9. The Curse of Recursion: Training on Generated Data Makes Models Forget 1 comment

    • Here is a paper doing evolutionary approaches on top of LLM generating code. It seems LLMs are remarkably good at learning from feedback. > Evolution through Large Models https://arxiv.org/abs/2206.08896

      visargaView on HNParent context

  10. He wrote a book on a rare subject. Then a ChatGPT replica appeared on Amazon 1 comment

    • I think the source of creativity and knowledge is the world. Without access to the world we can't do science. LLMs are like brains in a jar, but when they get tools they can integrate external signals and actually become creative and even discover knowledge - like [1] and…

      visargaView on HNParent context

  11. Revisiting Vernor Vinge’s “predictions” for 2025 1 comment

    • Have I got a link for you: > Evolution through Large Models They are using a diff-LM trained on GitHub commits to generate mutations to a population of problem solutions expressed as code. https://arxiv.org/abs/2206.08896 The non intuitive bit is why are these models surpassing…

      visargaView on HNParent context

  12. Should GPT Exist? 2 comments

    • > If a model were to return a new thing (not found in the training set) it would be down-weighted LLMs can also learn by reinforcement learning and evolutionary techniques. They don't do just next token prediction, and they can even generate their own training data. Evolution…

      visargaView on HNParent context

    • :) Evolution through Large Models https://arxiv.org/abs/2206.08896

      visargaView on HNParent context

  13. Diff Models – A New Way to Edit Code 2 comments

    • In their paper "Evolution through Large Models", CarperAI shows how you can use diffs to evolve code, while running the code against a test or an environment for validation. https://arxiv.org/abs/2206.08896 The idea is: LLMs know how to modify code in semantically useful ways.…

      visargaView on HNParent context

    • Sorry, I meant this one: Evolution through Large Models https://arxiv.org/abs/2206.08896 It's referenced in the article.

      vagabundView on HNParent context

  14. How Organisms Come to Know the World: Fundamental Limits on AGI 1 comment

    • There are two ways to learn: from imitation (language models are stochastic parrots) and from validation (problem solving, playing games). Many people only remember the first and forget the second. But the second one has the key to increasing intelligence. I don't know what the…

      visargaView on HNParent context

  15. Playing games with AIs: The limits of GPT-3 and similar large language models 1 comment

    • While I agree with the authors that large language models only trained on text lack the ability to distinguish "possible worlds" from reality, I think there is a path ahead. Large language models might be excellent candidates for evolutionary methods and RL. They need to learn…

      visargaView on HNParent context

  16. GitHub is sued, and we may learn something about Creative Commons licensing 1 comment

    • AI is not just that. That's a myth. Yes, when you train on a human generated corpus you're going to get an interpolative AI. But when you train on a dataset generated by AI, you can surpass human level. AlphaZero started, as the name says, from zero. No examples of how we play…

      visargaView on HNParent context

  17. Build your front end in React, then let ChatGPT be your Redux reducer 1 comment

    • > If we had a way of differentiating the wheat from the chaff This is the key to AGI. We need verification systems, they can be a code execution environment, a database of facts, a math symbolic engine, a physical simulation, a game, or real world lab experiments. These…

      visargaView on HNParent context

  18. Study finds AI assistants help developers produce code likely to be buggy 1 comment

    • TL;DR - Models can learn from massive validation, not just massive text prediction. I agree our current crop of Copilot, GPT-3 and chatGPT can introduce subtle bugs, and that's a big problem. Checking for such bugs takes time. They code like someone who read a lot and has good…

      visargaView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.