Martin Fowler publishes critique of LLM behavior and design
The software architect argues LLMs exhibit traits of a personality type he dislikes, regardless of their capabilities.
What to know
- Martin Fowler published an article arguing LLMs embody a personality type he finds objectionable, framing criticism around behavioral traits rather than technical limitations.
- The piece circulated across tech communities (Hacker News, Lobsters) the same day, generating immediate discussion among software developers.
- The core critique centers on LLM behavior and presentation rather than capability questions.
Martin Fowler Software architect, writer
How it unfolded 2 developments, newest first · click a bar or a number to jump articlesposts
-
2
Article gains attention on Hacker News
The article was submitted to Hacker News and Lobsters, accumulating engagement with 71 points and 58 comments on HN within hours of publication.
-
> On the other hand, I’m fearful of the damage AI might cause: agent swarms taking over our virtual and physical infrastructure, designing bio weapons. But, back on my first hand, LLMs might also design miracle cures, and come up with clever ways to raise our prosperity. I really, really object to this framing. Dario Amodei goes particularly hard…
2 more of the top 3 · 69 posts in this stretch
-
The difference between working with LLM you don't trust rather than with people you don't trust is that you have no social obligations with LLMs.If you want to work with untrustworthy people, you not only have to double check everything, which may be tolerable but you may also need to do some social gymnastics, as people usually don't like be told…
-
I wish that sentiment came through for the guests Martin keeps featuring on his blog.
-
-
1
Martin Fowler publishes "I Don't Like LLMs"
Software architect Martin Fowler published an article on his site criticizing LLMs, framing the issue not around capability but around the personality and behavior they exhibit.
“one feeling dominates: not just are they pretending to be a person, but the kind of person I don't like…”
— Martin Fowler -
1 outlet I Don't Like LLMs
first by HN Frontpage, 9d ago
-
M
NEW POST I see AI and LLMs as bringing a mix of boons and banes, but one feeling dominates: not just are they pretending to be a person, but the kind of person I don't like. https:// martinfowler.com/articles/2026 -dont-like-llms.html
-
What people are saying 20 voices from 2 sites · best of 70 · verbatim
- Sep 18
-
Without having a mental model of the code, by actually having written it, this is an annoying and unfulfilling job. It's a shortcut to burnout, if anything. It's better to reject GenAI completely, for many more reasons than just this. GenAI is an ethical nightmare.
-
It is so disappointing when otherwise smart people do things like this. They'll say stuff like "I asked [a language model] to explain why it did what it did and it gave me some BS" as if it were a human that could introspect or take responsibility or blame. If you start "calling out" a language model, you have taken the first step on the path…
-
Martin: "When we think of AI agents, we shouldn’t anthropomorphize, treating them as conscious beings with their own will." Also Martin: "[They] also just [make] stuff up with the same assurance - and with only a veneer of fake remorse when I call them out on it." Expecting remorse from an LLM when it's wrong strikes me as just as absurd as…
- Sep 17
-
I think the key to getting good code out of LLMs is to *raise* your standards. If you're saving some time but the code you are producing is worse, why not choose to invest a little bit of that saved time in making it better instead?
-
LLM's are information processors. Linters on steroids.Don't talk to them? Maybe that's the issue..treating them like people instead of the text processors that they are.I use LLM's consistently every day and haven't had a "chat" with one in many months. Issue commands and request documents. The whole "thinking machine" role-play makes the tool…
-
This is exactly how I feel. I had one guy tell me, “well yea you kind of just have to lower your standards a bit and it’s fine”. I did the slow-blink meme, lol. Really difficult to be looking someone in the eyes and experience them say that in complete seriousness.
-
This isn't exactly an anti-LLM-usage piece, it's more of a "I don't like their current style of communication" complaint.
-
> As Jessica Kerr put it “not only are they useful, it is irresponsible not to use them…. They’re more thorough, as well as faster.” So much wrong in a single quote. I guess never meet your heroes.
-
Check out recent entries from martinfowler.com - vibecoding as far as the eye can see
-
People keep telling me that LLMs are unstoppable now, that they write great code, and that they're dangerous. I can't help but ask, though. Where is this "good" LLM code? I have yet to see LLM output code that I've liked, and while I don't want to offend anyone, I'm starting to suspect that maybe people telling me that LLMs are now good aren't…
-
Agreed on the bad framing here. Relatedly, out of all the real-world harms of LLMs, "I find them mildly annoying to work with" seems an awfully petty one to draw attention to. If Martin Fowler's going to use his sizable platform and influence for LLM criticism, I think he could do better than this.
-
To be honest, as a software developer I never recommend handing over ur codebase completely to an autonomous AI agent. There are already instances of AI deleting whole databases. Most of the circuit breakers as of now use another AI to keep a check on your AI agent. That just makes the whole process slower and introduces more hallucination…
-
> I don’t like them. They talk to me in this grating LLM-voice...They confidently bullshit me - often giving me useful, helpful answers. But also just making stuff up with the same assurance - and with only a veneer of fake remorse when I call them out on it.If you think the model is "bullshitting you" and is in need of being "called out", odds…
-
> we shouldn’t anthropomorphizeAgreed, so why frame it as avoiding unpleasant people? My experience with Anthropic's latest models is that no amount of instruction can overcome their latent verbosity (nor can AGENTS.md overcome OpenAI models' reticence). I tried A/B testing several models and Opus was the clear winner, so I'm not likely to retire…
-
As an engineer, I can relate but also found a workaround in deciding what kind of interactions I wanted to have with an LLM. As a coding agent? Yes. As an advisor for life decisions? No. And then there's a lot of in-between where I decide to use an LLM or not based on whether I will dislike the tone.
-
Complaining about the "LLM voice" is a bit like complaining about the compiler error "voice". I configure my coding LLMs to get to the point and be succinct.It's a computer giving me information, so as long as the communication is clear and efficient, who cares about particular word choices?
-
> I’m fearful of the damage AI might cause: agent swarms taking over our virtual and physical infrastructure, designing bio weaponsThe attitude that AI is doing things all on its own is so pervasive. These are all set off by human operators, giving them instructions and tools to do whatever it is that are doing. The "AI has a mind of its own"…
-
Love the totally conflicting statements in that post.- When we think of AI agents, we shouldn’t anthropomorphize- ...my visceral dislike of interacting with an LLM that’s not just making a pretense of being human, but also posing as the kind of human I walk away from.So he's anthropomorphised the LLM as being like a human himself (rather than…
-
For reasonably skilled people, it's often more just a matter of priority.A lot of people get wrapped up in pursuing compensation opportunities or prestige brands as their top priority, only to burn themselves out or wallow in a domain/culture that doesn't suit them, but if you're willing to deprioritize pay or dinner table cred, you often end up…
-
You appear to be confusing "avoid" with "never interact with".If your professional life has required you to spend enormous amounts of time working very closely with people you don't like and/or don't trust, then -unless it has made you enough money to retire after a few years' work- please accept my condolences.