The Lighthill Debate (1973) - part 1 of 6

Well, there was this place called "The Turing Institute" which was in Glasgow. It was run by a very nice man called Don Michie. I met Don a handful of times, and he was extremely kind and generous to me. He worked at Bletchley Park and died aged 91 having hit a bridge at 120mph going the wrong way up the M11 at 2am sitting next to his wife who had defected to Russia thirty years before. Don was driving, at the time he had been blind for six months. Anyway, The Turing Institute existed because of Don's drive to commercialise Expert Systems. Don was a driver in the Alvey project which was a grand project to solve issues around Expert Systems in response to the Japanese Fifth Generation project. A man called Lighthill then rumbled the Expert System movement. If you want to watch a demolition of it see the following video : ▶ this video and the other 5 of them (you will find them in the sidebar!) Fun fact. In video 6 you can watch Christopher Strachey have a pop at AI. Christopher didn't work at Bletchley, he was too young, but he did work at Manchester with Alan Turing and they created computer music and love poetry in collaboration before Turing killed himself. Strachey went on to be the first Professor of Computer Science at Oxford, he was a scion of a great family of artists and poets. But enough of this. The Turing Institute was an attempt to say "we are right, look", but in fact it failed. Don was clear why, when you hit 40k rules knowledge bases became completely intractable. I

in “A rising sentiment that IBM’s Watson can’t deliver on its promises” · View on HN

Haha, this is arguably the article in AI. Other landmark events in the field include the Dartmouth Conference, when John McCarthy named the field "Artificial Intelligence", defined the goals, and set out to achieve them, unfortunately it's not easy to point to a single paper on the subject, though do read the conference proposal, posted on HN recently [ [link] ]; then you have the Lighthill report where the UK Government essentially lost interest in the project, the conclusions are debatable, but clearly and entertainingly argued, a video of the presentation of the report, with McCarthy present and responding, is available online also [ ▶ this video ]. Finally I'd cite the 1970s era book What Computers Can't Do, and its 90s reprint, What Computers Still Can't Do as all you need to know about the current state of AI, its ultimate aims and the fatal flaws in its fundamental assumptions. The fact that it was written in the 70s and applies to today's discussions on AI should be enough to indicate its prescience. Modern AI ignores or is unaware of many of the critiques that have gone before, only time will tell if they will soon hit the same historical obstacles. The points I've mentioned here don't really cover the history and development of Neural Networks, but they went through a similar process of discovery, critique, near-dormant research, and finally a return to popularity, but with neglect of the critiques rather than addressing them. Welcome to the field!

in “Computing machinery and intelligence (1950)” · View on HN

Why do you have to start your comment by accusing me of moving the goal posts? I don't even like ball games. Why is it so hard to have a decent conversation on the internet? It's a serious concern and I stand by it. It's perfectly possible -it's even easy- to make algorithms, systems, programs, what have you, that can solve one problem, perform one task, and do nothing else. Hell, you can train a dog to perform one task. Sit boy! Boy sits. And that's all it knows to do. 80% of AI research output, ever since Dartmouth, has been like that. 99% of AI research output in the last ten years is like that. My entire phylum of AI research (I'm a PhD student studying Inductive Logic Programming and even knowing nothing about that, the name should give you an idea) is roundly dismissed today as a "failure" because it couldn't get from "we can solve an instance of this problem" to "we can solve any instance of this problem" quickly enough. Researchers promised it was just a matter of "generalising" like you say, tuning and tuning until everything worked in the real world as well as it worked in blocks worlds, but the sources of funding didn't listen and then we had a winter [1]. Why is what you're doing any different when you look at it from the present? We haven't seen the future yet. In the present, you have a robot that can open one door. In the future, you have a lot of doors that wait for robots to open them. Actually, looking at your paper, you don't even have a robot that can open

in “Deep reinforcement learning is a waste of time (2019)” · View on HN