Why AI Alternatives Matter
AI is prone to problems affecting its output: hallucinations, incompleteness, inconsistency, and bias. AI usage is costly, and the popular free services might require expensive paid plans or downgrade to sponsored light versions at any time.
Don't Hit Submit!
Source: image created by OpenAI using Mistral's Le Chat mascot
Ethical issues aside, lazily using AI too often and too early won't make you a better coder or more creative. And AI companies don't only take your money, they're also after your data – and your time!
Techniques like Rubber Duck Debugging (internal dialog development, preparing questions and anticipating answers without actually asking anyone) are alternatives to AI for coding and creativity.
Don't Ask Suggestive Questions
If your question implies a certain answer, asking only makes sense for falsification. AI (and other people) will hopefully tell you when you're completely wrong. Only that AI often doesn't. Current models are trained for flattery and verbosity.
What a waste of time!
Don't Ask Why
Ask open questions, and always prefer to ask "how", not "why".
Stay Skeptical
Don't believe anything without factful proof or a recent, reputable, relevant source.
GEO, the AI-agent-targeting variant of search engine optimization, has already succeeded in gaslighting AI and poisoning its answers with fake sources biased towards commercial results. AI seems much more gullible than real people.
Principle of Least Power
Remember the rule of least power: don't rent a truck when you need a minivan. Don't use AI when you need autocomplete, web search, or a tutorial!
I sketched a pyramid of thinking, creativity, and information retrieval again. As you can guess, AI assistants are "on top" as the most costly exception, while the broad basis should be traditional groundwork. Here's a cute AI-slop adaptation:
Source: Hand-Crafted Creative Counter-Culture against Toxic Digitization
In practice, it's more complicated. What's "AI" and what isn't?
I'm happy with AI ...
I'm happy about "autocomplete on steroids", but I still don't trust agents to refactor a legacy codebase in 2026.
I'm happy with AI-assisted image editing, but I'm tired of all the sloppy stuff taking the place of crafted screenshot collages or authentic photography.
List of Popular AI Providers (2026)
Focusing on privacy and local-first pragmatism, Ecosia and Mistral's Le Chat lead my top ten, although and because I'm aware that they might not be the smartest top-notch vanguards. But they don't have to. No need to let Americans or Chinese know what I'm working on, or what I'm going to tell my doctor, when modest models are smart enough.
- 127.0.0.1 (as local as it gets)
- Ecosia (AI and search engine) 🇩🇪
- Le Chat (IA) 🇫🇷 🐱
- Claude 🇺🇸
- ...
That's my subjective top three, not counting number zero, as I haven't set that up yet.
This list is subject to change, and yours will surely differ.
So, who am I?
I'm developing, designing and optimizing websites and (web) apps.
I have been doing this since 1997.
You can call me old.
What I'm not: I'm neither naive nor nostalgic, ...
... no luddite, no AI-denier, but ...
Do I sound like a grumpy patriot yelling at the sky?
Image generated by OpenAI, probably inspired by Albert Uderzo
What is it that I'm really angry about?
Enshittification
Pragmatism and capitalist logic make most companies eventually deteriorate their products on purpose until they are only slightly better than the second-best alternative, or just good enough not to lose all of their loyal customers and brand reputation.
Taking the cliché further, while Europe often stands in its own way and stalls its administration in bureaucracy, China floods the world market with cheap plastic fashion, networking electronics, and surprisingly successful AI models (not in my top ten).
America, or more specifically, the United States, somehow still manage to defend their position as leading exporters of "premium" hardware, software, and culture. However, the premium becomes hollow because of the aforementioned enshittification.
You might say I'm just jealous of the Californian tech broligarchs. I mean, didn't Elon help popularize electric mobility? Isn't he the one who provides Starlink to Ukraine? Yes, he is. And a dictator built our motorways. Just saying.
Long ago, Google dropped their former "don't be evil" motto.
Honestly, I often get the impression that "be evil" is what drives current tech stakeholders. And that's very bad. Are we human or are we lemmings actively creating a dystopian future?
You might say, I'm just too old to understand, that I'm just pessimistic because I'm too stupid to prompt. You might say my perfectionism is just another nerdy hobby.
Subjective List of Unpopular AI and Search Providers
- ChatGPT by OpenAI (see #quitgpt why)
- Gemini / Google AI mode (see #degoogle)
- Copilot / Microsoft Bing AI
- Perplexity (just another hallucinating American)
- Meta AI (just so that they will get mentioned, too)
- Grok (capable, but most unethical)
In practice, I still use them. It's hard not to, when there is no major relevant search engine index yet besides Google and Microsoft's Bing, which are used by Ecosia and other alternative meta-search engines.
Hypocrites we are?
As Giorgi Kobaidze pointed out in AI Psychosis Is No Longer Fiction, "people worry about AI taking their place, while at the same time actively using it in ways that make it easier for it to do so."
I'm using AI nearly every day. I even use it to generate cartoons and illustrations eventually, after having claimed so many times why that's wrong for so many reasons.
I'm using AI nearly every day as it has already become ubiquitous and seemingly without a practical alternative. Google search results are often so bad and irrelevant, and prepended with sponsored results, while the AI answer, currently on top of everything just seems too promising to ignore.
I'd prefer providers prioritized more classical products, fixed bugs and improved editors and search results. I mean, sometimes they still do. VS Code, GIMP, and Linux on Desktop prove past progress every day. Maybe AI is an important step towards more progress.
I only hope that we, as humans, and we, as developers, can prevent stakeholders from shaping the future towards their own unethical goals thanks to the new tools they already control too much.
Constructive Criticism
After all, my series is called "constructive criticism" and maybe I shouldn't be so negative. Then again, someone must have their say and point out flaws and fallacies.
Further reading: see links in the text above.
Top comments (17)
"Think first, prompt later" might be the most underrated engineering skill of 2026.
This.
The simple truth is that AI is a senior developer's tool... Because it does Junior level's work. If you use AI, stop treating it like it's smarter than you, treat it for what it is, a brilliant junior, that still leaves AllowAnonymous in endpoints. You need to meticulously validate everything it writes, because it'll run beautifully, but at what cost?
You can gate it, you can add validation steps, system instructs, unit tests, integration tests, all wonderful, but it doesnt help if a button is off the screen now does it? Validate everything, so you dont end up ruining production.
I recently viewed job postings, found a company, you know, just a Series A backed by YC... Went to their career portal, job wasnt listed there, so I clicked on Company Website at the top... It takes me to a site they dont own, infact it's pointing at an unowned domain in general. No human would type in the wrong url, so it was clearly someone who trusted AI, didnt validate, their code wasnt reviewed, they had no production gating, they didnt test the site and the result is a big red flag...
(For cybersecurity context, that means I can buy the site it points at, replicate their website and offer an 'exclusive discount' flyer. If anyone buys anything and gets scammed, that company is held liable, because they point at it, as their company website, on their official site... So for a company that is built on digitizing money and is entrusted with safeguarding it, that right there is a funding killer, infact a company killer.)
The "Principle of Least Power" framing is the bit I want to amplify, because it tends to get lost in AI-vs-no-AI debates. Most of the "AI sucks" arguments I read are actually "I used a sledgehammer where autocomplete would have done." The pyramid structure you sketched captures it well: foundation is rubber-ducking and reading docs, and AI should sit on top as the expensive exception.
The flattery / verbosity problem you mentioned deserves more attention. I have been on both sides of this — building agent systems where the model agreed with obviously wrong assumptions, and being the user who caught it five messages later. What helped our team was explicitly budgeting for "model disagreement" time: treating the first response as a proposal to refute, not a statement to accept.
The GEO Poisoning point is also under-discussed. Are we approaching a point where defaulting to AI for factual questions is itself a risky default?
I love the title, inspired from "The principle of least action" :D !
AI is most useful when it supports our thinking, not when it replaces it.
P.S. as always, I have prematurely published, and then edited and added some more paragraphs shortly after. So, if you have just read this post, please reload and re-check my self-critical section about hope and hypocrisy.
I'd push back on this. the problem isn't using AI too early - it's never checking if you understood the answer. passive acceptance is the failure mode, not early use.
There's nothing to "understand" when an answer is defunct hallucination without any factful proof, then it was just a waste of time, tokens, and energy. Think first, then ask – if you still need to. That's what I wanted to point out. I agree that there are many problems and setup where AI is actually helpful, and you are right, then it is still essential to understand beyond a simple "does it work" (in the happy path) test.
fair - that's the edge case i skipped. hallucinations aside, my point was about the pattern of running with any AI output without checking it at all. but you're right that checking understanding of made-up facts doesn't help - that just locks in the wrong mental model faster
The danger isn't overusing AI.
It's forgetting the alternative approaches that worked perfectly well before AI existed.
Principle of Least AI maps neatly onto least privilege, and the payoff is the same: smaller blast radius by default. The cost of reaching for AI isn't just tokens, it's that every generated piece you didn't write is a piece you don't have a mental model of, so over-using it quietly converts authorship into archaeology. Applying it least means using the model where the work is genuinely mechanical and keeping your hands on the decisions where understanding has to live in your own head. The teams that get burned aren't the ones using AI, they're the ones using it everywhere by default and finding out later that nobody understands the system. Least AI is really least unexamined output.
Thank you for that definition. Until I saw the original poster's question, I'd never seen the phrase, "The Principle of Least AI". So, I was lost. Your definition will work for me, and I like it, too.
"Principle of Least AI" is exactly the right framing. The tool should match the task, not become the default for every task.
The corollary for content creation: AI earns its place when it compresses the genuinely mechanical parts of the workflow. Writing the first draft isn't always mechanical — but publishing it to 8 platforms after you've finished? That's 100% mechanical. Every second you spend copy-pasting and reformatting is cognitive overhead that has zero creative value.
That's the use case we built twRty Blogboat (twrty.org/blogboat) for — not to replace the writer, but to remove the post-writing pipeline entirely. One click, 15+ platforms, credentials stored on-device only. The AI helps generate and edit when you want it. The automation handles distribution because that's a task that should never require human attention.
Least AI where least AI is right. Maximum automation where the task is purely mechanical.
Some comments may only be visible to logged-in visitors. Sign in to view all comments.