I’ve read the paper and the skeptical comments here, to wit: it’s just an actor/critic pipeline by another name.
I’ll bite and say this is actually interesting — and the paper title is misleading.
What they’ve done here is hooked up a text-only LLM to multimodal critics, given it (mostly) an image diffusion generation task, and asked it to improve its prompting of the multimodal generation by getting a set of scores back.
This definitely works, based on their outputs. Which is to say, LLMs can, zero shot, with outside tool feedback, iteratively improve their prompting using only that tooling feedback.
Why is this interesting? Well, this did not work in the GPT-3 era; it seems to do so now. I see this as an interesting line to be added in the ‘model capabilities’ box as our models get larger and more sophisticated — the LLMs can perform some sort of internally guided search against a black box generator and use a black box scorer to improve at inference time.
That’s pretty cool. It’s also generalizable, and I think is worth keeping in mind on the stack of possible approaches for, say agentic coding, that you can use a critic to not just ‘improve’ generated output, but most likely do some guided search through output space.
I really wish we would find a different term for this.
Doing something always takes at least one attempt, i.e. "one shotting". "Zero shotting" is an oxymoron, which makes it a term that only creates more confusion rather than succinctly conveying something.
"One shot" is simply about the action itself, but it says nothing about how much preparation was done beforehand. "Zero shot" additionally implies without training or preparation.
TCGs have a related "zero turn win" concept, where the opponent goes first and you win without getting a turn due to the set of cards you randomly drew and being able to activate them on the opponent's turn.
I think of a shot as an example, not a try: “One shot” is “One example”. Zero shot is “Zero examples”. I don’t love it, but I don’t hate it, got a better word for it?
My favorite AI term to ridicule is the recent "Test Time Compute" nonsense, which has nothing whatsoever to do with testing. It literally just means "inference time".
And if I hear someone say "banger", "cooking", "insane", or "crazy", one more time I'm going to sledge hammer my computer. Can't someone, under 40 please pick up a book and read. Yesterday Sam Altman tried to coin "Skillsmaxxing" in a tweet. I threw my coffee cup at my laptop.
> I think is worth keeping in mind on the stack of possible approaches for, say agentic coding, that you can use a critic to not just ‘improve’ generated output, but most likely do some guided search through output space.
The one issue I keep finding with those approaches is that there’s already good tools for the problem, but we keep searching for wasteful approaches because “natural languages” for something humans are not going to interact without a good deal of training.
I do understand the hope of getting LLMs do the bulk of the work, and then after audit, we fix the errors. But both audit and fixing will require the same mental energy as writing the code in the first place. And possibly more time.
Specialist tools are always more expansive and offer more controls than general public tools. Most approaches with agentic coding is offering general interfaces instead of specialized interfaces, but redirecting you to a bespoke and badly designed specialized interface whenever you want to do anything useful.
I hear that. Counterpoint - if you all you have is a Philips-head screwdriver, all you have is a Philips-head screwdriver. On the other hand if all you have is a six axis CnC mill, well, then you have a lot.
I think of this less as audit misses, and more as developing a permanently useful tool. For open model weights, humanity will not (unless we’re talking real zombie apocalypse scenarios) lose these weights. They are an incredible global asset, so making them more generally useful and figuring out how to use them is super helpful.
Are they using the same diffusion models as the GPT-3 area? Meaning is it the LLM that has improved or is it the diffusion model? I know it's probably a foolish take but I am really skeptical of the "larger models will solve all our problems" line of thinking.
They don’t compare in the paper. I will say I experimented extensively with GPT-3 era LLMs on improving ouput by trying to guide early diffusion models with critical responses. It was a) not successful, and b) pretty clear to me that GPT-3 didn’t “get” what it was supposed to be doing, or didn’t have enough context to keep all this in mind, or couldn’t process it properly, or some such thing.
This paper has ablations, although I didn’t read that section, so you could see where they say the effectiveness comes from. I bet you thought that it’s emergent from a bunch of different places.
FWIW, I don’t think LLMS will solve all our problems, so I too am skeptical of that claim. I’m not skeptical of the slightly weaker “larger models have emergent capabilities and we are probably not done finding them as we scale up”.
My photoresistor nightlight can "see" that it is dark and it "knows" to turn on the light - not only does it not have training, it does not have any code!
And if you think that is amazing, my bi-metallic strip thermostat "feels" the temperature and then modifies the environment because it "knows" if it's hot to turn on the A/C, and if it's cold to turn on the heat - no training or code!
All of this AI stuff is just unbelievably incredible - what a brave new world (of word games)!
The nightlight and thermostat's response to stimulus is nowhere near analyzing a picture of a clock tower and responding with "Image of a city's tallest, historic landmark with a sepia filter." To me, recognizing the umbrella in the spoon is one of the most impressive items they list.
Through the story and experience of a blind man, they end up getting into the question of what does it mean to see
The podcast is pretty straightforward, but it does end up showing that defining “seeing” is a philosophical question, rather than a simple obvious answer
They only did that for image generation. The more interesting part is that an LLM can approach or find the correct caption for an image, video or audio during test time with no training using only the score as a guide. It's essentially working blind almost like the game Marco Polo where the scorer is saying "warmer" or "colder" while the LLM is finding its way towards the goal. This is an example of emergent capabilities since there are no examples of this in the training data.
Actually, it's the name of the paper. And while the team also developed and released a system to elicit the behavior by doing what you described, it's entirely possible that the researchers thought the title to be the most important finding in their work.
You don't have to train the LLM soecifically for the tasks and even the auxiliary tools aren't trained on the tasks they are used as scorers for (because they aren't doing the task,just evaluating how well the LlM is), so there is no task-specific training.
In actor/critic the actor and critic are normally learned, i.e., their weights are adjusted during the process. The paper is correct that their method is zero-shot, but it doesn't mention that their method is essentially equivalent to a few rounds of training but then discarding the training update.
Anyone who works with deep architectures and momentum-based optimizers knows that the first few updates alone provide large improvements in loss. In this paper the breakthrough is that computing these first few updates at test time enables one to describe the algorithm as "without training" and therefore attract hype.
But they aren't updating the model weights. They're iteratively updating the prompt. It's automating the process that humans use with generative models.
Exactly how little training is "without any"? I'm assuming that companies haven't been spending billions trying to train LLMs to better understand things when they can do it without any training.
Emergent capabilities have been one of the wildest developments in software. For most traditional programmers you learn quickly and with great pain that the computer only does what you explicitly program it to do, no more, no less, and unintended behavior is a bug (and if you’re lucky, an accidental feature).
But the idea that entire abilities just emerge from scale… I still have a hard time accepting it.
Readit News
I’ll bite and say this is actually interesting — and the paper title is misleading.
What they’ve done here is hooked up a text-only LLM to multimodal critics, given it (mostly) an image diffusion generation task, and asked it to improve its prompting of the multimodal generation by getting a set of scores back.
This definitely works, based on their outputs. Which is to say, LLMs can, zero shot, with outside tool feedback, iteratively improve their prompting using only that tooling feedback.
Why is this interesting? Well, this did not work in the GPT-3 era; it seems to do so now. I see this as an interesting line to be added in the ‘model capabilities’ box as our models get larger and more sophisticated — the LLMs can perform some sort of internally guided search against a black box generator and use a black box scorer to improve at inference time.
That’s pretty cool. It’s also generalizable, and I think is worth keeping in mind on the stack of possible approaches for, say agentic coding, that you can use a critic to not just ‘improve’ generated output, but most likely do some guided search through output space.
I really wish we would find a different term for this.
Doing something always takes at least one attempt, i.e. "one shotting". "Zero shotting" is an oxymoron, which makes it a term that only creates more confusion rather than succinctly conveying something.
TCGs have a related "zero turn win" concept, where the opponent goes first and you win without getting a turn due to the set of cards you randomly drew and being able to activate them on the opponent's turn.
And if I hear someone say "banger", "cooking", "insane", or "crazy", one more time I'm going to sledge hammer my computer. Can't someone, under 40 please pick up a book and read. Yesterday Sam Altman tried to coin "Skillsmaxxing" in a tweet. I threw my coffee cup at my laptop.
The one issue I keep finding with those approaches is that there’s already good tools for the problem, but we keep searching for wasteful approaches because “natural languages” for something humans are not going to interact without a good deal of training.
I do understand the hope of getting LLMs do the bulk of the work, and then after audit, we fix the errors. But both audit and fixing will require the same mental energy as writing the code in the first place. And possibly more time.
Specialist tools are always more expansive and offer more controls than general public tools. Most approaches with agentic coding is offering general interfaces instead of specialized interfaces, but redirecting you to a bespoke and badly designed specialized interface whenever you want to do anything useful.
I think of this less as audit misses, and more as developing a permanently useful tool. For open model weights, humanity will not (unless we’re talking real zombie apocalypse scenarios) lose these weights. They are an incredible global asset, so making them more generally useful and figuring out how to use them is super helpful.
This paper has ablations, although I didn’t read that section, so you could see where they say the effectiveness comes from. I bet you thought that it’s emergent from a bunch of different places.
FWIW, I don’t think LLMS will solve all our problems, so I too am skeptical of that claim. I’m not skeptical of the slightly weaker “larger models have emergent capabilities and we are probably not done finding them as we scale up”.
And if you think that is amazing, my bi-metallic strip thermostat "feels" the temperature and then modifies the environment because it "knows" if it's hot to turn on the A/C, and if it's cold to turn on the heat - no training or code!
All of this AI stuff is just unbelievably incredible - what a brave new world (of word games)!
Through the story and experience of a blind man, they end up getting into the question of what does it mean to see
The podcast is pretty straightforward, but it does end up showing that defining “seeing” is a philosophical question, rather than a simple obvious answer
Interesting, but title is definitely clickbait.
Deleted Comment
Anyone who works with deep architectures and momentum-based optimizers knows that the first few updates alone provide large improvements in loss. In this paper the breakthrough is that computing these first few updates at test time enables one to describe the algorithm as "without training" and therefore attract hype.
But they aren't updating the model weights. They're iteratively updating the prompt. It's automating the process that humans use with generative models.
Agreed that it's conceptually equivalent though.
But the idea that entire abilities just emerge from scale… I still have a hard time accepting it.