My latest side project, an AI chatbot that I vibe coded, is now live.
-
JMS on AI storytelling
J. Michael Straczynski, a man who knows a thing or two about storytelling,1 has a two-part essay on his substack about why AI has not yet produced a great manuscript, and might never.
Silence where a story might have been (part 1)
Silence where a story would have been (part 2)
AI is already being used to write manuscripts in collaboration with human writers. We know this because a handful of writers have been caught at it. But almost certainly there are writers who weren’t caught, and whose AI collaborations have been published.
He’s right that AI won’t write a story on its own. “Write me a story” is a laughably vague prompt. You’re leaving the details up to the model, which will produce an average of all the literature it knows about, and that’s statistically very likely to be mediocre.
If you prompt better, you’ll get better results. If you iterate, providing yet more specific instructions, you’ll get better results still. More on that is coming soon (I’ve been experimenting).
But you’re still the one steering the story machine. Straczynski’s point is that AI doesn’t do anything without a human telling it to. By its very architecture, it will never observe a weird little moment of human interaction and think, “I should write a story about that.”
I think it’s way too early to say conclusively that a machine will never be able to have that experience. But such an AI will be a lot more advanced than anything we have now… and it’ll probably have a body.
- Straczynski still holds a record for writing an entire 22-episode season of a TV show… twice. In fact, of the 110 episodes of Babylon 5, he wrote 92. That’s not the reason he titled his 2019 autobiography Becoming Superman, but it’d be understandable if it were. ↩︎
-
When is a copy not a copy?
In 1993, a company called MAI Systems sued Peak Computer, a computer repair firm, for copyright infringement. Peak’s technicians had turned on MAI clients’ computers to diagnose them, which loaded MAI’s proprietary operating system into RAM. MAI argued that loading its software into memory—even briefly, even just to make sure the computer was working, even though there was no way to start the computer without loading the software—constituted an unauthorized copy. Because the Peak technician was not licensed to use that software, MAI said, Peak had committed copyright infringement.
They won.
(more…) -
Don’t be ’fraid of that ghost
Michael Andrews has an interesting post about some of the credibility issues surrounding generative AI: phantom authorship, potential boobytraps, and countermeasures against them. A key insight is that most LLM knowledge isn’t from primary sources of facts, but rather from secondary sources’ simplified explanations of the primary sources. The latter are simply more numerous. So sometimes, a LLM’s knowledge lacks the depth you’d want.
If you’ve ever watched a television news report about something you’re an expert in, you already know how wary you should be of secondary sources.
-
Quantity has a quality all its own
The aphorism “quantity has a quality all its own” is usually attributed to Josef Stalin, though the earliest traceable source appears to be an American defense newsletter from 1979.
Whoever said it, they were talking about armies. More soldiers don’t just let you fight the same battles better. Past a certain size, your army can fight a different kind of battle entirely, with new strategies and tactics. The observation applies at other scales, too: firing a machine gun is a very different experience from firing a musket—especially if you’re on the receiving end.
The aphorism might as well be the thesis statement for one of the most surprising discoveries in modern AI research. I touched on it in my last post when I compared Mark V. Shaney’s capabilities to modern LLMs. The discovery is this: bigger language models don’t just do the same things, only better. When they grow large enough, they start to be able to do entirely new things.
(more…) -
The ghost of Mark V. Shaney
In 1984, an unusual user started posting in net.singles, a Usenet newsgroup where lonely people discussed dating, and he fit right in… sort of. He would respond to threads with sentences like “I have a great time to try to herd cats, and I’m not sure I agree with you.” Plausible. Slightly off, but weirdly confident.
The poster was named Mark V. Shaney, and he wasn’t human. “He” was a computer program, or bot, that was in essence the forerunner of today’s large language models (LLMs).
(more…) -
Welcome to The Inference
I wanted to write for a living as soon as I learned that books don’t spring fully formed like Athena from the brow of Zeus but in fact are written by regular people. Hey, I’m a regular people!
Not too long after that realization, I discovered the Apple II—and developed a second obsession, this one over a technology that was changing the world.
I once intended to pursue a career in programming. But I stumbled into a job that let me scratch both my writing and programming itches. I’ve been a technical writer ever since.
The arrival of large language models (LLMs) felt like a technological New Testament, a new era with new rules, but no less transformative than the personal computer revolution. The two things I loved and understood best, software and language, had formed a new, more intimate relationship. I’d used words to write about code; now code could itself read and write.Cool! … Cool?
I’ve spent years documenting AI and ML features at Snowflake and Azure Cognitive Services, sitting close enough to see how the sausage is made, but far enough back to still find it tasty. Over those years, I’ve learned enough about LLMs to have developed opinions about them.Lately, I’ve been having thoughts about AI that don’t belong in documentation. The Inference is a place for those thoughts to go. I’ll try to be technically correct (the best kind of correct), intellectually curious, and mercifully brief. But no promises on that last one.
Let me answer the obvious question up front: yes, I’m working with a large language model to create this blog. I’ll write more about that experience as it evolves.So pull up a comfy chair, sit down, settle in. Invite a Glen of Imaal Terrier onto your lap. Welcome to The Inference.