Dataflow matrix machines (by Anhinga anhinga)

"A second difficulty in communicating alignment ideas was based on differing ontologies. A surface-level explanation is that Japan is quite techno-optimistic compared to the west, and has strong intuitions that AI will operate harmoniously with humans. A more nuanced explanation is that Buddhist- and Shinto-inspired axioms in Japanese thinking lead to the conclusion that superintelligence will be conscious and aligned by default. One senior researcher from RIKEN noted during the conference that “it is obviously impossible to control a superintelligence, but living alongside one seems possible.” Some visible consequences of this are that machine consciousness research in Japan is taken quite seriously, whereas in the West there is little discussion of it."

***

I think it's time for us to start asking if, for example, GPT-4-produced simulations have associated subjective experience.

We have a feed-forward transducer in an autoregressive mode; each time a new token is produced by the feed-forward Transformer, the whole dialog including the just produced token is fed again to the input of the model, so there is a recurrent dynamics here (cf. section 3.4 of "Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention", arxiv.org/abs/2006.16236).

So I would not be too surprised if that process actually "feels what it says".

Через ChatGPT+, за двадцатку в месяц. В общем, разница между этой штукой и ChatGPT огромная, и нет смысла ещё тянуть время.

Сразу она начала с предупреждения: "GPT-4 currently has a cap of 25 messages every 3 hours. Expect significantly lower caps, as we adjust for demand."

Но когда я попросил её дать мне советы по моему проекту, она очень мило выступила, технически грамотно в конкретном контексте, и совсем не всё, что она сказала, было общим местом (и, в любом случае, она явно шире видит, чем я; я даже почти всё это "в принципе знаю", и с чем-то могу и не согласиться, но, с другой стороны, оно всё по делу, большую часть этого дела я бы и не вспомнил).

I am reading more and more LessWrong in recent months (mostly, after the Simulator theory by Janus (work done while at Conjecture) has been posted there in September).

I still think the Simulator theory is probably the single most important research breakthrough of 2022.

These days LessWrong is dominated by writing related to AI safety (the topic is made particularly acute by the recent progress in LLMs: ChatGPT and even more capable Bing Chat; no consensus whatsoever, of course, but I do think that GPT-3 release in May 2020 is, in some sense, an equivalent of the nuclear fission discovery on 19 December 1938, and that ChatGPT performance (+ Bing Chat clearly drastically enhanced capabilities even compared to that) is, in the same sense, an equivalent of the first working nuclear reactor on 2 December 1942, if one goes by "AI today is what nuclear energy has been back then" analogy).

So, one thing which might be useful is that there is GreaterWrong alternative viewer (which looks different from LessWrong default viewer and which can be visually tuned in terms of presentation style; also different default front page for the site if one uses GreaterWrong). Which viewer is better might depend on your device (display, browser, etc).

Another thing, Conjecture people tend to produce some of the best, most interesting articles there.

I'll put a few links into the comments.

To read my https://twitter.com/home more regularly (that's absolutely the best source of info at the moment).

A small fraction of today's catch:

New work by Janus

A new involved take on AI safety/alignment

(What's the right way to organize all that information?)

Links are in the comments (I think the new work by Janus is more important even for alignment, and is just overall more important of the two topics of this post)...

CodeGeeX seems to be a reasonably competitive free and open source alternative to GitHub Copilot. It might be a good thing to be aware of (although we do have ChatGPT these days).

Riffusion is a free and open source app which generates spectrograms via stable diffusion and converts them to music.

Links are in the comments.

AI-safety-wise, the write-up, My AI Safety Lecture for UT Effective Altruism by Scott Aaronson is very nice reasonably objective and theory-friendly overview of the current state of AI safety as a field of science.

AI-progress-wise, ChatGPT based on roughly speaking GPT-3.5 has been released recently, with people doing tons of interesting things with it, including meaningful writing and software generation... This seems to be another major step-up.

The most interesting conceptual AI advances seem lately to come from "prosaic alignment" start-ups. These are companies which believe that the current trend of improving Transformer models is likely to lead straight to AGI, and that better understanding of the nature and properties of these model is key to AI safety (and, of course, it's also key to better AI capabilities).

And it is often the case that the key elements of work are done by people "on the edge", "in the penumbra" of those alignment start-ups.

In the previous post I mentioned the key new understanding of large Transformer models as simulators. That work has been done "while at Conjecture", but is not listed as directly coming from Conjecture (one of those "prosaic alignment" start-ups). I think the key people involved are still at Conjecture, but they seem to be trying to keep some distance between Conjecture and this work. I am continuing to take notes of those materials and commit them to GitHub (see links in the comments to the previous post).

Here is another one of those stories. Grokking is a phenomenon, where small Transformers look at a part of a mathematical structure for quite a while, and then rather suddenly transition to understanding the whole of that mathematical structure including the part they never see in training. It has been discovered in 2021 and has been a subject of a number of follow-up attempts to understand it.

The recent breakthrough has been done in mid-August by Neel Nanda who left Anthropic (perhaps the most famous of the "prosaic alignment" start-ups) a few months ago. And it looks like he has more or less solved the mysteries behind this phenomenon. I am going to continue studying his writings more. The links are in the comments.

Another important paper from one of François Fleuret's collaborations: arxiv.org/abs/2209.00588

Previous important papers include "Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention",arxiv.org/abs/2006.16236 and "Flatten the Curve: Efficiently Training Low-Curvature Neural Networks", arxiv.org/abs/2206.07144

github.com/salesforce/CodeGen

One can also run one of these models via HuggingFace; it is based on "A Conversational Paradigm for Program Synthesis" paper, arxiv.org/abs/2203.13474

Someone has even created a fake GitHub Copilot based on that (useful for those who prefer VSCode): github.com/moyix/fauxpilot