metaseq VS gpt-2-output-dataset

This is a super important issue that affects the pace and breadth of iteration of AI almost as much as the raw hardware improvements do. The blog is fun but somewhat shallow and not technical or very surprising if you’ve worked with clusters of GPUs in any capacity over the years. (I liked the perspective of a former googler, but I’m not sure why past colleagues would recommend Jax over pytorch for LLMs outside of Google.) I hope this newco eventually releases a more technical report about their training adventures, like the PDF file here: https://github.com/facebookresearch/metaseq/tree/main/projec...

The number of people who can actually pre-train a true LLM is very small.

It remains a major feat with many tweaks and tricks. Case in point: the 114 pages of OPT175B logbook [1]

[1] https://github.com/facebookresearch/metaseq/blob/main/projec...

Reliability at scale: take a look at the OPT training log book for their 175B model run. It needed a lot of babysitting. In my experience, that scale of TPU training run requires a restart about once every 1-2 weeks—and they provide the middleware to monitor the health of the cluster and pick up on hardware failures.

I really appreciated this log of Facebook training a large language model of how troublesome AI development can be: https://github.com/facebookresearch/metaseq/tree/main/projects/OPT/chronicles

Stable Diffusion will run on any decent gaming GPU or a modern MacBook, meanwhile LLMs comparable to GPT-3/ChatGPT have had pretty insane memory requirements - e.g., <https://github.com/facebookresearch/metaseq/issues/146>

It seems so, check this log book from Meta: https://github.com/facebookresearch/metaseq/blob/main/projec...

especially: "Our classifier is not fully reliable. In our evaluations on a “challenge set” of English texts, our classifier correctly identifies 26% of AI-written text (true positives) as “likely AI-written,” while incorrectly labeling human-written text as AI-written 9% of the time (false positives). Our classifier’s reliability typically improves as the length of the input text increases. Compared to our previously released classifier, this new classifier is significantly more reliable on text from more recent AI systems." Many other classifiers are similar, e.g.:

Links search found: https://github.com/openai/gpt-2-output-dataset (dataset? I want GPT, Pre-trained model).

Source: the literal source code and paper by the original creators of a detector that most of these knockoff detectors are based on.

OpenAI published a detector themselves that seems to be quite good. https://github.com/openai/gpt-2-output-dataset/tree/master/detector

Here is OpenAI's own detector, but it's not impossible to beat by just doing some fairly basic stuff with things like automatic paraphrasing.

To a certain extent, GPT-2 worked because of the smaller dataset of just 40GB. Even in that model, researchers running detection found accurate results only in the: