Evolution through Large Models · HackerPapers discussions

Evolution through Large Models — mentioned by _delirium

Thu, 15 May 2025 00:19:51 GMT

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 much into the recursive self-improvement idea, because "the GP system can use GP to improve the GP system itself!" is a very old idea that just has never worked, although I realize that isn't proof that it won't eventually work. Some related work from a different company: https://sakana.ai/ai-cuda-engineer/ And some…

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

Evolution through Large Models — mentioned by namaria

Thu, 10 Apr 2025 19:54:35 GMT

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 programmers." https://arxiv.org/pdf/2206.08896 > The idea that models can only write code if they've seen code that does the exact same thing in the past How do you get "code that does the exact same thing" from "predicting plausible changes?"

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

Evolution through Large Models — mentioned by namaria

Thu, 10 Apr 2025 18:01:28 GMT

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 that. It's overfitting to diffs it was trained on. "In other words, the model learns to predict plausible changes to code from examples of changes made to code by human programmers." https://arxiv.org/abs/2206.08896

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

Evolution through Large Models — HN submission

Thu, 13 Jun 2024 06:21:38 GMT

Evolution Through Large Models

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

Evolution through Large Models — mentioned by visarga

Wed, 12 Jun 2024 15:21:46 GMT

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 started from scratch and only had feedback from the self-play game outcomes, but that was enough to reach superhuman level. It was the feedback that carried insights and taught the model. You can make a parallel to the scientific method: you have two stages, ideation and validation. Ideation alone is not scientific.…

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

Evolution through Large Models — mentioned by visarga

Tue, 16 Apr 2024 07:26:55 GMT

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 Models" shows the way. Just use LLMs as genetic mutation operators. Evolutionary methods are great at search, LLMs are great at intuition but get stuck on their own, they combine well. https://arxiv.org/abs/2206.08896 The interplay between LLMs and Evolutionary Algorithms, despite differing in objectives and…

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

Evolution through Large Models — mentioned by visarga

Wed, 27 Mar 2024 19:26:18 GMT

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 evolutionary methods where the LLMs are the mutation operator. You evolve a population of solutions. (https://arxiv.org/abs/2206.08896)

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

Evolution through Large Models — mentioned by visarga

Thu, 11 Jan 2024 21:03:43 GMT

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 contingent on further advancements in these areas, which might lie beyond the reach of current architectures. I don't think cultural transmission with LLMs is that incipient. Evolution through Large Models - https://arxiv.org/abs/2206.08896 We have seen papers where LLMs are used as "search heads" or "mutation operators"…

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

Evolution through Large Models — mentioned by visarga

Fri, 30 Jun 2023 19:44:17 GMT

> 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 replication in software. An AI model can generate text that can train new models from scratch[1]. They can also generate the model code, explain it, make meaningful changes[2], monitor the training run and evaluate the "child" models[3]. So AI can "pull everything from inside" to make a child, no external materials…

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

Evolution through Large Models — mentioned by visarga

Tue, 27 Jun 2023 11:42:49 GMT

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 the quality only depends on how much data the agent can generate. We know that when an agent can do proper exploration like AlphaGo Zero it can reach superhuman levels, it builds its own specialised dataset as it runs. For example: Evolution through Large Models - https://arxiv.org/abs/2206.08896

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

Evolution through Large Models — mentioned by visarga

Thu, 15 Jun 2023 10:30:52 GMT

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

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

Evolution through Large Models — mentioned by visarga

Fri, 12 May 2023 20:54:59 GMT

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 AlphaGo's move 37 (it has access to the go table, which is the "world" of Go) But this "access to the world" needs massive scale, we are billions of humans all experiencing the world, AI needs probably a similar number of agents doing massive trials and search. AlphaGo sure did need lots of self-play games, not just a…

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

Evolution through Large Models — mentioned by visarga

Wed, 15 Mar 2023 10:50:58 GMT

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 the original programming? It's because they got a secondary source for learning - the feedback they get from generating solutions and testing them. Learning through feedback, be it reinforcement, evolutionary or gradient based, is what can push AI forward. AlphaZero started with no human knowledge by pure self-play and…

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

Evolution through Large Models — mentioned by visarga

Wed, 22 Feb 2023 15:03:55 GMT

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

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

Evolution through Large Models — mentioned by visarga

Wed, 22 Feb 2023 12:15:03 GMT

> 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 through Large Models https://arxiv.org/abs/2206.08896

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

Evolution through Large Models — mentioned by vagabund

Sat, 28 Jan 2023 19:50:36 GMT

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

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

Evolution through Large Models — mentioned by visarga

Sat, 28 Jan 2023 19:34:38 GMT

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. Evolutionary algorithms are great at search, but don't learn new mutations by themselves. So combine them together to generate new data and retrain the models. So the old system is: scrape human code and train on it. the new system is: generate code, keep the good parts and retrain. It only costs electricity and is…

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

Evolution through Large Models — mentioned by visarga

Sun, 08 Jan 2023 12:13:43 GMT

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 authors mean by "current algorithmic frame of AI research" because it is very diverse. But evolutionary methods work well with neural networks, they are not just next token predictors. > Evolution through Large Models https://arxiv.org/abs/2206.08896 It is true that simply using a dataset or a bunch of environments is…

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

Evolution through Large Models — mentioned by visarga

Sat, 07 Jan 2023 20:17:49 GMT

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 from solving language problems on a massive scale. But problem solving could be the medicine that cures GPT-3's fuzziness, a bit of symbolic exactness injected into the connectionist system. For example: "Evolution through Large Models" https://arxiv.org/abs/2206.08896 They need learning from validation to complement…

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

Evolution through Large Models — mentioned by visarga

Fri, 06 Jan 2023 14:42:19 GMT

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 the game. In just three days of self-play it surpassed the best human. How was that possible? We got a 2000 year head start, larger brains, and many players, not just one model. AlphaZero did it by creating its own training data. Here is an example of using code language models for this kind of dataset-creation by play.…

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

Evolution through Large Models — mentioned by visarga

Thu, 29 Dec 2022 10:58:25 GMT

> 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 verifiers will produce signal that can be used by the language models to improve. The cheaper and faster verification is, the faster we can iterate. Generating ideas is cheap, proof matters. Just remember AlphaZero a bit - it started from scratch, playing against itself, in a few hours it surpassed human level. Go simulation…

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

Evolution through Large Models — mentioned by visarga

Mon, 26 Dec 2022 19:40:21 GMT

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 memory, but never implemented anything complex. But there is no reason to be the same in the next iteration. Language models can be fine-tuned on code execution, that means giving sufficient exposure to trial and error to learn how to avoid such bugs. Having a way to test its outputs is the key to self improvement. It…

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

Evolution through Large Models — HN submission

Mon, 20 Jun 2022 03:11:08 GMT

Evolution Through Large Models

32 points; 14 discussion replies on HN. Paper and source history. A submission is not an endorsement.