I'd approach this distinction differently. Prediction from compression is valid within the distribution of the compressed data. Which brings it much closer to LLMs in this case (can an LLM talk about a topic it has never seen in training? unlikely if it cannot be derived from other training data)
> Which brings it much closer to LLMs in this case (can an LLM talk about a topic it has never seen in training? unlikely if it cannot be derived from other training data)
This is a great experiment. Do some world building offline about Smergle the Keen finding the Hoopla of Kynashiusous. Then ask ChatGPT what reagents would have been more effective in breaking through the borantiastic door than squeeble stomach juices.
Of course we know the answer - it will either drop into a 'I have only been trained on data before blah blah blah' or 'I cannot talk about current world leaders' or 'I have not been trained on your hackneyed and unpublished romantasy saga, why don't you tell me about it?'
On the other hand, if it is aware of the general concepts of your concept, and has bridging concepts for related topics it has been trained upon, it might try to apply the general concepts to a specific but different scenario.
I’d argue the opposite. The geometry involved in reconciling photos from two separate lenses with different focal lengths is quite challenging. If you pay close attention you will see some differences in the before/after samples in the site (for example the ear in that kitchen selfie).
The math is surely more complex than aligning same-lens photography even when you consider the change in angle and perspective between two shots from the same lens.
Not really. Whether you have two different lenses or the same lenses with some offset from hand movement you need to accurately model the lens(es). Once you can do that for one lens you can just as easily do it for two - it's just more variables to optimize, not a fundamentally harder problem. Panorama software has supported images from different lenses since forever.
I thought the actual 30 papers have never been disclosed. Do you have a source tying the recommendations back to Ilya, or did you come up with this list?
The list I got was from ex-OpenAI employee Andrew Carr on X. I believe he said in his post however that the list he uploaded is not the full list they were provided at OpenAI however.
The Web MIDI API[0] used by the author has a built-in precise scheduler, that has higher precision and works better than the unreliable setTimeout approach used by OP when coupled with the Performance API[1].
Pass a timestamp as the second argument to midiOutput.send(data, timestamp), calculated with performance.now. Something like midiOutput.send(data, performance.now() + offset)
It’s not as simple. I trained an LLM before on exactly this, to scratch the itch of this question.
The task was simple, using the MS-MARCO[0] dataset which contains queries, search results, answers, I made a training set that has:
1. Questions paired with real results supporting them (mixed with some irrelevant results), and a correct answer
2. Questions paired only with irrelevant results, with the answer “No answer present”
The dataset was huge (close to 1M samples), and I trained using different techniques, from SFT (just mimicking the dataset) to DPO (good answer contrasted with a bad answer for the same user query) to GRPO (verifier that checks my annotations whether an answer was present or not)
Lo and behold, this didn’t reduce hallucination, rather made it much worse. Now the model started claiming “No answer present” even when it is, or even when the question didn’t need search results in the first place (simple stuff like what is X+Y).
Now you could argue that my training was basic compared to what frontier labs could do. Yet I think it hints at a more profound limitation. LLMs are finicky and don’t have a neat understand of things from first principles (list of search results, check relevance of result to user query, if answers are below a certain threshold of relevance then don’t consider them to answer …).
tl;dr: not as simple as one might think, perhaps not attainable at all.
Thank you for sharing! Based on your experience, do you think a two-model system might fare better? For example, two models in serial where the second model is trained to "sniff out" potential hallucinations and fact check them (and possibly iterate with the first model)?
You are however likely to observe better results in smaller models since they're usually more strapped for "cognitive capacity", so two separate calls reduce the load in each request, and hallucination in my experience is a common side effect of overloading an LLM cognitively.
You can increase the context window beyond its max trained context using RoPE scaling[0] which will require more VRAM.
But you can increase your context window for the same VRAM by quantizing the KV cache with FP8 (double the context) or TurboQuant (more than double)[1].
Glad I'm not the only one to immediately think of it. It's a great story, but did feel unlikely when I first read it; should it prove largely true it would be terrifying.
