Earlier this evening I was working away on a translation of one of the medieval St Nicholas miracle stories, BHL 6177, the “Miracles at Angers”. I was using Google translate on the Latin text, which was producing some very decent quality outputs. Then I was checking and correcting it. It did indeed need correcting, but it’s mostly right and far faster than sitting there doing it manually.
A little while later I had a play with Bard, Google’s AI product. (It would have been ChatGPT but this demanded an alarming amount of personal information.) I asked the prompt if it could translate ancient Greek, and it said that it could, including whole documents; but it might not be perfect just yet, but was improving.
So I tried it out with a chunk from the Greek Anthology, which it rendered into English; but I realised afterwards that this probably just retrieved a pre-existing translation. Then I went to Ulrich Harsch’s useful site – which Google downvotes because he hasn’t implemented the latest https – and found a page on George of Pisidia here. This began:
Γεώργιος Πισίδης, διάκονος καὶ ποιητὴς ἐν Κωνσταντινουπόλει, ἐγένετο περὶ τὸ ἔτος 580, ἐτελεύτησε περὶ τὸ ἔτος 634, εὑρετὴς τῶν στίχων δωδεκασυλλάβων.
So I put in “translate the following ancient greek into English:” and then the Greek. The result was:
George of Pisidia, deacon and poet in Constantinople, was born around the year 580, died around the year 634, inventor of the twelve-syllable lines.
That’s very reasonable. I then asked it a second time whether it could translate ancient Greek. This time I got a rather different reply, and much more bullish:
Yes, I can translate ancient Greek. I have been trained on a massive dataset of text and code, including ancient Greek texts. I can translate ancient Greek into English, French, German, Spanish, Russian, Chinese, and many other languages. I can also translate ancient Greek into modern Greek.
I am still under development, but I am able to translate ancient Greek with a high degree of accuracy. I can translate simple sentences, as well as more complex passages. I can also translate ancient Greek poetry and literature.
If you have an ancient Greek text that you would like me to translate, please feel free to share it with me. I will do my best to provide you with an accurate and informative translation.
But …. I just pasted in a chunk from Arethas of Caesarea on Romans here – I’m pretty sure that there’s no English translation of that! – and it just echoed the text. So… in fact it’s not there yet. But it’s food for thought.
But how many of us even understand what these things are doing? A web search was clear enough – just collect URL’s and make a list of words and topics.
But AI? Well, as I understand it, these “generative AI” products are basically a chat-bot on the front of a “large language model” (LLM). An LLM is a “next word predictive engine”, apparently. So basically some code for pattern recognition on the front of a search engine; indeed pre-loaded with a lot of text to search from the web. The AI generative image makers do much the same, apparently.
The amount of hype and exaggeration around “AI” is staggering, as it is with every new fad, but it is not magic. In IT “it” is never magic. If you think “it” is magic, then you don’t understand “it”. Everything is ones and zeros and lumps of metal and silicon. The rest is attempts to sell stuff.
Now I don’t fully understand it. But it did set me to wondering about whether I am wasting my time. For it wouldn’t be the first time that technology has rendered my work useless.
When I came online originally, I was scanning existing English translations of ancient texts and putting these online. Bandwidth was low, and text-only pages were the only way to get stuff online. I did so for some years, until the technology rendered it pointless. Bandwidth became enormous, so file size didn’t matter. The PDF arrived, with exact images of the book pages. OCR improved, so the PDF was searchable. Google Books came along, with every book under the sun prior to 1923, all freely downloadable. I haven’t done any more since then. There’s no point. I don’t regret doing it, but … in a way it was wasted effort.
Since then I’ve concentrated on texts for which no translation exists. At one time I commissioned these. Now that I am retired, I sit here and make my own.
But again the technology is taking this away. Is there any point in an amateur like myself labouring over a Latin text, with my limited Latin, to produce an awkward translation if Google Translate can do it in an instant, and be pretty nearly “good enough”?
Prior to January 2022, the question was academic. Google Translate was rubbish for Latin. And then, suddenly, it wasn’t. In fact it could make sense of sentences better than I could. I can polish the result, and correct minor errors, and do something worthwhile; but basically it is doing the job. Furthermore, it is quite likely to improve further.
So I’m getting this feeling of dejà vu. Is there any point? I’m not sure, and I’m not going to stop right now, if only because I’m still enjoying it. But it is food for thought.
The world-wide web is a very different place from what it was. One horrible aspect of the new craze for “AI” is that, for the first time, the products are commercial. You have to pay to use them.
This is a novelty, and an unwelcome one. It marks a big shift from the free, open internet that we have had until now. Bye-bye the internet to which I contributed, where it was expected to be free. No longer. Worse yet, those who contributed freely find their work turned against them.
I saw this evening a report that StackOverflow, the computer programmers’ forum site, has lost 50% of its traffic. The bots hoovered up all the replies to technical questions, shared freely by ordinary people, out of the kindness of their hearts, and embedded them in new tools like GitHub Copilot. This, needless to say, is a commercial product. And it’s killing the original site.
Will the internet change, until we have to pay for everything, via a million subscriptions? It is beginning to look like it.
The new AI is also biased in various directions, probably for commercial reasons, certainly in line with horrible American politics, but also simply in selecting what some corporation wants us to see. That corporation wants us to see “important stuff”. They decide what is important.
For instance, if you type into Google search “Who is Roger Pearse”, you get some rubbish at the top about some “Roger Pearce”, selected by Google; but then you get stuff from my blog, and material by me. My name is not common, and I write on a specialised subject, and have done so for 24 years. In a fair and level internet, I would naturally appear.
The same query in Bard AI produces “I’m designed solely to process and generate text, so I’m unable to assist you with that.” Which is not too bad, except that, if I repeat this for public figures, like “Joe Biden”, I get an article back. A source is given, which is – of course – Wikipedia.
Indeed if I ask “Who was Petrus Crabbe”, a very obscure figure, it begins with the text mainly from the Wikipedia article. I myself wrote this article, in a moment of madness, so I know just what is on the web about him. Bard AI is using Wikipedia plus one other source linked from it. No doubt ChatGPT is doing the same. But I don’t think that ChatGPT intends to send any money to me in return for my generous efforts.
So AI is only returning “important people”. In this case it is defined as people for whom there is a Wikipedia article. I do not have an article about me in that toxic hell-site, nor do I wish to. Of course if you asked someone in the national television industry who Roger Pearse is, they would have no idea. But… the practical effect of the coding around AI is to reduce the information, to only “approved sources”, to only “important people”.
Yet originally the web was a levelling phenomenon. That was part of the charm. Anybody could start a website. Anyone could start a search engine. You rose or fell on merit.
And now? Well, what we see in AI is what someone in a major corporation chooses that we should see. Little people don’t matter.
I don’t see any reason immediately to change what I am doing. But it is, as I said, food for thought.