Template:M intro work Large Learning Model: Difference between revisions

{{d|LLM|/ɛl ɛl ɛm/ (''also “[[large language model]]”'')|n|}}

Once upon a time, an [[LLM]] was a “Master of Laws”: the postgraduate mark of the ''sensei'' in the society of legal service providers — either of that, or of the indolence of one not prepared to strike out and put what she has learned into practice — but still: it spoke to perseverance, depth, comprehension and mastery, however pigeon-hearted its motivation.

''[[Cui bono|Who benefits]]'', primarily, from this emergent technology? Experience should tell us that the first  — and often the ''last'' — to benefit from legal productivity tools are the ''lawyers''. Should we expect [[this time is different|this time be different]]?

And bear in mind it will be the lawyers who deploy [[LLM]]s as a tool, not their clients. Why? ''Because of that [[ineffability]]''. An [[LLM]] is a pattern-matching device. It understands nothing. It cannot provide unmediated legal advice. It can only ever be a “back-breaker”: the “last mile” needs a human who knows what she is doing, understands the context and complicated human psychology at play in the cauldron of 1 [[negotiation]]. An [[LLM]] can draw pretty, impressive-at-a-distance doodles, but it cannot do that. Nor can it write [[legal opinion]]s — well, not meaningful ones — and nor, unmediated by a law firm, does it have the insurance policy or deep, suable pockets for which a client is paying when it seeks legal advice in the first place.

“But, [[JC]], come on. Be realistic. It is dog-eat-dog out there. Any lawyer keeps the bounty of the [[LLM]] from her clients will soon have her lunch eaten by others who won’t. You cannot fight the invisible hand. We are in a race to the bottom.”

Nor should we underestimate the overwhelming power of the lawyer’s intuition that ''what has gone before is sacrosanct''.

''Writing'' is perhaps the greatest of human inventions, binding together people who never knew each other, citizens of distant epochs. Books break the shackles of time. A book is proof that humans are capable of working magic.”

Fittingly, the first [[chatbot]] was a designed as a parlour trick. In 1966 Joseph Weizenbaum, a computer scientist at MIT created the programme “[[ELIZA]]” to explore communication between humans and machines. [[ELIZA]] used pattern matching and substitution techniques to generate realistic conversations. You can try it out [https://web.njit.edu/~ronkowit/eliza.html here].

Like all good conjuring tricks, [[generative AI]] relies on misdirection: its singular genius is that it lets us misdirect ''ourselves''. We wilfully suspend disbelief, never noticing who is creatively re-rendering machine-made screed as magic. ''We are''. We are neuro-linguistically programming ''ourselves'' to be wowed by a {{plainlink|https://en.wikipedia.org/wiki/Digesting_Duck|mechanical duck}}, when the clever part is really happening inside our own heads.

Now, in all kinds of literature, ''bar one'', “reading” is where the real magic happens.  

''Construal''. It is the [[Emergent|emergent]] creative act and community consensus that renders ''Hamlet'' a timeless cultural leviathan and {{br|Dracula: The Undead}} forgettable pap.<ref>Maybe not ''that'' forgettable, come to think of it: it has stayed with me 15 years, after all.</ref> A literary work may start with the text, but it stays there barely a moment. The “meaning” of a literary work is ''necessarily personal'' to the reader: it lives between the reader’s ears, and within the cultural milieu that interconnects the reading population over the generations — ''all as construed by the apparatus between the reader’s ears''.

=====On the absence of metaphors in foxholes=====

Now there is one kind of “literature” that ''is'' like a computer programme: where the ''last'' thing the writer wants is for the reader use her imagination, , or bring her cultural baggage in from the hall and use it to “construct” a meaning. In this singular domain, clarity of the writer’s intention is paramount: the only priority is divining the what those who wrote the text meant by it.

Now: the punchline. Given how integral the reader and her cultural baggage are to the creative act in normal literature, we can see how, in that domain, a [[large language model]], freely spitting out text ripe with interpretative possibilities — text that positively ''begs'' for someone to “construct” it, just to make sense of it — is a feasible model.  

We don’t doubt that LLM is coming, nor that the legal industry will find a use for it: just that there is a ''useful'', sustained use for it. It feels more like a parlour trick: surprising at first, diverting after a while, but then the novelty wears off, and the appeal of persevering with what is basically a gabby but unfocussed child wears pales.

Large learning models already can execute this “research assistant” mode. It seems less flashy but — if we can trust it — this is a compelling use case that will remain once our inflated expectations has collapsed into the trough of despair. We could ask Bing AI to track down a long-lost childhood story.{{Quote|1=Bing, do you know a children’s story involving a fox or a wolf or something being chased by a pack of hunting dogs and it hides under a rock. The hiding place is too small, and it has to poke one part of its body out. It has an argument with each of its body parts to see which is the most deserving of being saved and concludes its tail is the least deserving, so it sticks its tail out. The hunting dogs arrive and grab it by the tail and catch it. Moral of the story is something like you are only as good as your weakest link.}}At first, Bing shrugged its shoulders and said, “sorry”. When we persevere with a few more details, success!{{Quote|1=I found the story you were looking for! It’s called “The Wolf and His Tail”. In this story, a wolf is being chased by a pack of hunting dogs and hides under a rock, The hiding place is too small, and it has to poke one part of its body out. It has an argument with each of its body parts to see which is the most deserving of being saved and concludes that its tail is the least deserving so it sticks its tail out. The hunting dogs arrive and grab it by the tail and catch it. The moral of the story is that you are only as good as your weakest link.}}Magnificent! We can ask who wrote the story:{{Quote|“The Wolf and His Tail” is a children’s story that was written by Barbara Juster Esbensen. It was first published in 1972.}}There is only one problem: ''this is not true''. Barbara Juster Esbensen was indeed a children’s author, but she wrote no such book. It is as if Bing has been badgered into false memory syndrome.

In other news, scientists are concerned that [[ChatGPT]] might be getting worse. Studies indicate that its accuracy at tasks requiring computational accuracy, like playing noughts and crosses or calculating prime numbers, is rapidly diminishing.