Tech

AI in practice: Chatbot tool comparison

Come look over my shoulder while I explore how and whether LLMs are good writing tools: Here’s a wee version of the LLM comparison exercise I did with my team. We’ll make it a two-fer so you can see how the “good writing” skill works in practice, though we’ll see how that actually goes.

One of the more useful things you can do with an LLM is hold up a few ideas side by side and apply lenses to them. I know this history pretty well, so I asked a series of LLMs, why is Wisconsin’s cultural identity and cohesion stronger than Indiana’s, from a historical and business perspective?

Here are the answers in one doc, for comparison.

Each LLM will give us more or less the same story, different flavor. Within the industry, the differences across the models reflect “model personality.” Asking “why” instead of “whether” will probably drive the answer to favor Wisconsin. Using multiple lenses (two states, historical + business, identity + cohesion) forces the LLM to cross-reference across more of its training data, which tends to produce a more comprehensive answer.

For all the chatter about consciousness and whatever, remember that an LLM is an infinite series of if/then/elses applied to human language and semantics, so being able to talk about language and communication, getting meta with the tool and how you think through language, helps a lot when using one. This is maybe the one thing I like about experimenting so hard with the tools. I’m thinking about the technical side of writing and enjoying it quite a lot.

Functionally: all of them acknowledge hard historical truths within the subject matter and don’t shy away from critical perspectives, which is good. Both Gemini and Copilot include in-line links, which lets you judge the output’s authority in the moment as a reader. I liked Copilot’s more than I expected here. Claude’s answers are more lyrical and do provide more context, and yet do not encourage checking against outside sources by providing links within the output. And you can see that even with the good writing skill calling out hard bans on certain structure, Claude plows right through them.

Model personality: Claude favors sociological answers to Copilot’s economic answers. Claude is also highly intellectual and narrative by comparison, and that narrative style can mask nuance by sinking relative context within the storytelling. Gemini simplifies, boosts and cheerleads where the others don’t, and really goes hard on Wisconsin’s reputation as a drinking and Packers state when there are stronger structural arguments in play. Copilot is tricky because it looks authoritative like a briefing, which also makes it easily “extractible” for the user, but every citation requires authentication unless this is one of those “good enough” tasks.

As a writer, something I find annoying across the whole spread is the semantic reveal. LLMs are semantic machines, and it is persistently revealed in ways that are weird to the human ear. All of them go out of their way to describe things as “structural,” “connective” as in “connective tissue,” “load-bearing” and “legible.”

Finally, I included a second tab where I asked Claude for analysis across the four outputs, where it suggests that my framing of the question is altogether kind of problematic. It shows how a strong prompt is sometimes also a bad approach.

There are a lot of possible takeaways here, but I’d rather set aside the question of which tool is “good” or “bad” or “better” and think more about the patterns across the tools and their implications.

One of the tricky things about consumer AI tools like Claude and Gemini is that the experience varies widely depending on the person using it, and it’s not always clear why. I have spent a lot of time learning the tools so I can advise on them in my work, and this variance of experience has become a frustrating part of the deal.

I manage a team of writers and creatives at work, and we are expected to be familiar with the tools, despite complex and sometimes hostile feelings about the political and environmental implications of this sector. That’s quite a pickle, organizationally, managerially. Borrowing from Haraway, I thought, okay, what if we take these tools seriously as a team of writers and creatives and put our professional standards up against them?

Among other exercises, I did a couple of comparisons on my team that help create discussion around the “plausibility” question. People dismiss LLM outputs as being merely plausible answers, rather than accurate or factual ones. And that’s correct; they are, and that’s the design. In many cases, plausibility is fine. Take Wikipedia, for example, which we understand to be a pretty good source, a plausible source, unless you’re writing a formal paper requiring original sources.

I digress. Ultimately, we needed to understand together that LLMs are not a WYSIWYG tool and talk through the implications.

I asked everyone to run the same paper through their LLM of choice, prompting it for a plain language summary. We then copied and pasted it into a shared doc, and compared and contrasted for discussion. Upon discussion, we had several takeaways, including that they were all similar in spirit but sometimes varying wildly in style and approach.

Knowing that algorithms are responsive and not static, we did it again later in the day and copied and pasted our outputs into the shared doc. We compared and contrasted the difference between AM and PM. Again, it was similar in spirit but varied in style and approach. Some changed dramatically. One team member whose morning summary had been jokey and conversational received a much more staid and serious version in the afternoon.

At the time, I asked Claude to explain the variance: “Even with the same prompt and source material, LLMs don’t produce identical outputs each time. This is by design — there’s a degree of randomness (called “temperature”) in how the model selects words, which means each run produces a slightly different path through the text.”

Anyway, this got our gears turning on how (and whether) to approach LLMs as a team and as individuals and led to good group discussion. (It’s important to create space for criticism and critical approaches here.) It also gave us more confidence as a team responding to this new layer of complexity in our work, and helping our professional contacts and peers think about how to approach the tools and when and whether to use them. There will be tasks where AI-based tools are “good enough,” and tasks where they are not.

The swirl of mystery and speculation around this sector has people up in arms, and it’s useful to have approaches that give people firsthand experience and to see how the experience works for others. The god trick of the singular interface turns out to be a bear for navigating it in the workplace, where our work is foundational, prosocial and specific.

You might call this a taste test: Obsessed with the story about the McDonald’s CEO and how his LinkedIn-style videos selling the McD’s franchise have escaped containment, leading to one of the funnier CEO/product marketing dynamics in recent history. Burger King’s CEO swooped in, holding widely-marketed listening sessions with customers and to demonstrate his love for the Whopper in contrast with the deeply weird McD’s videos. Must read: Internet long-hauler Katie Notopoulos on how direct-to-public marketing works when the public is more familiar with the product than the org’s leaders.

My teenager thinks fast food is cool and subversive (cue the sound of one hundred moms groaning) and she and her friends regularly talk shop. They are Taco Bell fans and think burger stops are kind of gauche. Not gauche: Baja Blast.

In the meantime, the fast food sector is becoming a playground for AI approaches, causing a lot of nervous discussion on social media and in tech spaces.

Apparently one thing LLMs excel at is deanonymization at scale. The original promise of pseudonymity online was social and normative, over and above any question of technical depth: decent people don’t try to unmask you, because why. What strikes me today is how what used to be unacceptably antisocial behavior online is now both automated and unremarkable.

Over the last couple of weeks, I asked a couple of chatbots what could be known about me from this pseudonymous site, where I am more intentional about what I choose to reveal and conceal. It pulled the obvious but also drew conclusions based on a few geographic points I’d made in context that were both revealing and correct. I also noticed that it only drew from the top two pages of information - anything beyond page two of posts wasn’t part of the compute. Archives are for humans?

People assume that there is some computer magic on the backend where the LLMs connect all your account logins behind the scenes, but no, in fact it does all this through inference, by linking your digital trail, your friends, your breadcrumbs of likes and hearts and follows, and obvs your posts, into a picture of who you are, practically and demographically.

Like Rickrolling on steroids: I didn’t even know P2P music file downloads were still a thing, but of course, and the scene had a big week recently when somebody trolled SoulSeek by generating a bunch of popular songs sung in Homer Simpson’s voice, then quietly polluted the platform by offering the AI generated Homer files up to other users. Someone then set up a digital radio station of all the Homer Simpson songs called D’oh Radio. Here’s more reporting from Gizmodo.

There is a long tradition of Simpsonifying things that go online, so this is the latest iteration. We observed Homer covers going viral on social in 2024 and 2025.

Second wavers in tech and engineering talked a lot about the “god trick” of presenting knowledge and information, particularly around math and science, in a way that suggests its objectivity is eternal, immortal, unknowable. Work by Safiya Umoja Noble and others extended this lens to Internet search and architecture, finding that the search algorithm was a series of business decisions wearing neutrality to create a customer service experience. Websites do this (so does this blog). LLMs take that same trick and compress it further.

It’s an old idea, and one I’ve been drawing from while I tinker with Claude. The “god trick” is baked right into the AI interface: one input, one output, an authoritative-seeming answer, offered without named perspectives behind it, trained on text produced overwhelmingly by a narrow demographic who has historically had access to both literacy and publishing, by programmers and new media drawing from the same well. Smushed together, it gives the impression that consensus and authority exists where there are many loose ends and competing ideas in play. Sometimes that’s fine.

I’ve begun to recognize how LLMs can work like autocorrect for ideas, drawing from ranked search sources first before fanning out to more obscure sources, trying to determine and assert what’s important to me, a user known by demographics and data. It feels like a big linguistics machine, which is pretty cool in some regards, but also aggressive in others. The math doesn’t always work to connect me to what I want to find because I am situated in my individual context in ways LLMs are not able to understand, with my memory, in my body, with my unique experiences, which shape and translate meaning for me as I interact with the world (and the web).

McKenzie Wark for Verso Books on Donna Haraway, in 2015: “Creating any kind of knowledge and power in and against something as pervasive and effective as the world built by postwar techno-science is a difficult task. It may seem easier simply to vacate the field, to try to turn back the clock, or appeal to something outside of it. But this would be to remain stuck in the stage of romantic refusal. Just as Marx fused the romantic fiction that another world was possible with a resolve to understand from the inside the powers of capital itself, so too Haraway begins what can only be a collaborative project for a new international. One not just of laboring men, but of all the stuttering cyborgs stuck in reified relations not of their making.”

I’ve been spending more time in tech spaces online and getting good information from folks like @manton, creator of Micro.blog. Like this reflection on how to think about AI now that vibe coding works. Something I’m thinking about: there’s an emerging tension between those who see value in being able to immediately prototype an idea and the people downstream who have to manage the outputs/code over time. The ability to proof every idea sounds like a superpower until you’re the one driving and maintaining the results.

Some additional discussion of LLM models, including open weight and “staggered openness,” where orgs “release previous versions of proprietary models once a successor is launched, providing limited insight into the architecture while restricting access to the most current innovations.”

“Open source,” “open weight,” and “proprietary” describe different relationships between LLM model producers and users, governing what you see, modify and control. Comparing them isn’t necessarily about “best,” but whether you’re optimizing for transparency, compliance or performance. Massive investment in proprietary models means the best-resourced research teams, the largest training runs, and the most sophisticated safety work tend to happen behind closed doors.