65 Lines of Markdown, a Claude Code Sensation(tildeweb.nl) |
65 Lines of Markdown, a Claude Code Sensation(tildeweb.nl) |
Those 3000 early adopters who are bookmarking a trivial markdown file largely overlap with the sort of people who breathlessly announce that “the last six months of model development have changed everything!”, while simultaneously exhibiting little understanding of what has actually changed.
There’s utility in these tools, but 99% of the content creators in AI are one intellectual step above banging rocks together, and their judgement of progress is not to be trusted.
So I wouldn’t give anything on 3k stars at all.
For me that’s 100% of the time. I only bookmark or star things I don’t use (but could be interesting). The things I do use, I just remember. If they used to be a bookmark or star, I remove it at that point.
I'm sure i'll piss off a lot of people with this one but I don't care any more. I'm calling it what it is.
LLMs empower those without the domain knowledge or experience to identify if the output actually solves the problem. I have seen multiple colleagues deliver a lot of stuff that looks fancy but doesn't actually solve the prescribed problem at all. It's mostly just furniture around the problem. And the retort when I have to evaluate what they have done is "but it's so powerful". I stopped listening. It's a pure faith argument without any critical reasoning. It's the new "but it's got electrolytes!".
The second major problem is corrupting reasoning outright. I see people approaching LLMs as an exploratory process and let the LLM guide the reasoning. That doesn't really work. If you have a defined problem, it is very difficult to keep an LLM inside the rails. I believe that a lot of "success" with LLMs is because the users have little interest in purity or the problem they are supposed to be solving and are quite happy to deliver anything if it is demonstrable to someone else. That would suggest they are doing it to be conspicuous.
So we have a unique combination of self-imposed intellectual dishonesty, mixed with irrational faith which is ultimately self-aggrandizing. Just what society needs in difficult times: more of that! :(
Exactly - we are in the age of "AI-posers".
The democratization of programming (derogatory)
This is the banalization of software creation by removing knowledge as a requirement. That's not a good thing.
You wouldn't call the removal of a car's brakes the democratization of speed, would you?
The absence of means to measure outcomes of these prompt documents makes me feel like the profession is regressing further into cargo culting.
1. Reproducibility
2. Chain of custody/SBOM
3. Verification of artifacts of CI
All three of which are not simply difficult but in fact by nature impossible when using an LLM
When my code compiles in the evening, it also compiles the next morning. When my code stops compiling, usually I can track the issue in the way my build changed.
Sure, my laptop may die while I'm working and so the second compilation may not end because of that, but that's not really comparable to a LLM giving me three different answers when given the same prompt three times. Saying that nothing is deterministic buries the distinction between these two behaviours.
Deterministic tools is something the developper community has worked very hard for in the past, and it's sad to see a new tool giving none of it.
https://rationalwiki.org/wiki/Deepity
Determinism concerns itself with the predictability of the future from past and present states. If nothing were deterministic, you wouldn’t be able to set your clock or plan when to sow and when to harvest. You wouldn’t be able to drive a car or rest a glass on a table. You wouldn’t be able to type the exact same code today and tomorrow and trust it to compile identically. The only reason you can debug code is determinism, it is because you can make a prediction of what should happen and by inspecting what did happen you can can deduce what went wrong several steps before.
Apparently almost half of all the websites on the internet run on WordPress, so it's entirely possible for developers to be wrong at scale.
What FOSS solution would you recommend instead?
Some are FOSS, self-hostable, or keep your content in a form which you can easily carry over to another service.
I think there’s another FOSS project, but there really isn’t anything with the same breadth as Wordpress.
WordPress's popularity is mostly adding a huge amount of complexity, runtime cost, and security risk for every visitor for the only benefit of a content manager being able to add a page more easily or to configure a form without needing a developer. That is optimizing the least important part of the system.
Even if this is complete nonsense, I choose to believe it :’)
>Think Before Coding
I've experienced in times of gpt 3, and 3.5 that existence of any, even 1-word system message changed output drastically in the worse direction. I did not verify this behaviour with recentl models.
Since then I don't impose any system prompts on users of my tg bot. This is so unusual and wild in relation to what others do that very few actually appreciate it. I'm happy I don't need to make money for living with this project thus I and can keep it ideologically clean: user's control over system prompts, temperature, top_p, giving selection of the top barebones LLMs.
Similar for MCP/Skills/Prompts, I’m not saying they can’t/don’t help but I think you can shoot yourself in the foot very easily and spend all your time trying to maintain those things and/or try to force the agent to use your Skill/MCP. That or having your context eaten up with bad MCP/Skills.
I read a comment the other day about sometime talking about Claude Code getting dumber then they went on to explain switching would be hard due to their MCP/Skills/Skill router setup. My dude, maybe _that’s_ the problem?
The exact same thing happened with xClaw where people where going "look at this app that got thousands of stars on GitHub in only a few days!".
How is that different than the followers/likes counts on the usual social networks?
Given how much good it did to give power to strangers based on those counts, it's hard not to think that we're going in the completely wrong direction.
This feels like a handbook for a senior engineer becoming a first level manager talking to junior devs. Which is exactly what it should be.
However, this will go horribly wrong if junior devs are thus “promoted “ to eng managers without having cut their teeth on real projects first. And that’s likely to happen. A lot.
It isn't strange that this is the case, because you'd be equally hard pressed to compare developers at different companies. Great to have you on the team Paul, but wouldn't it be better if we had Harry instead? What if we just tell you to think before you code, would that make a difference?
That would be game changing!
Of course it's hilarious a single markdown got 4000 starts, but it looks like just another example of how people chase a buzzing x post in tech space.
I have found the following, but I suspect as AI gets better this will change.
1) those who where incompetent before still are, but AI hides it.
2) those who were competent before AI do vastly more with AI. They seem to apply it in away that simply overshadows what the incompetent are doing.
3) the incompetent seem to be fascinated with things like skills, pre prompts and, setting policies and guidelines, and workshops. The competent seem to need none of this, are not going to workshops, already have their own and simply are more productive.
Why are you surprised that it takes only 65 lines of Markdown to create the next Linus Torvalds or Donald Knuth!
I’m learning Haskell by Thinking before Coding, without working through the difficult exercises. I finally understand Monads because of Thinking first.
I wonder what will happen with new LLMs that contain all of these in their training data.
This is such a negative messaging!
Let's check star history: https://www.star-history.com/#forrestchang/andrej-karpathy-s...
1. Between Jan 27th and Feb 3rd stars grew quickly to 3K, project was released at that time.
2. People star it to be on top of NEW changes, people wanted to learn more about what's coming - but it didn't come. Doesn't mean people are dumb.
3. If OP synthesized the Markdown into a single line: "Think before coding" - why did he went through this VS Code extension publishing? Why can't they just share learnings and tell the world, "Add 'Think before coding' before your prompt and Please try for yourself!"
PS: no I haven't starred this project, I didn't know about it. But I disagree with the authors "assumptions" about stars and correlating it to some kind of insight revelation
What I would say, you could have omitted some negativity or judgement from your post about 4k devs starring something because it looks simple, because they might have different intentions for starring.
Here is another great example of 65K "not wrong" developers: https://github.com/kelseyhightower/nocode - there is no code, long before AI was a trend, released 9 years ago, but got 65K stars! Doesn't mean devs "not wrong", it means people are curious and saving things "just in case" to showcase somewhere
https://github.com/forrestchang/andrej-karpathy-skills/blob/...
I find the whole premise of writing some vague instructions, feeding them to a stochastic parrot and expecting a solid engineering process to materialize out of the blue quite ridiculous.
Any sufficiently advanced "AI" technology is indistinguishable from bullshit.
This post is about a prompt that has 4K+ stars (that matters to people?) so they wrapped it up in an extension for Cursor and they ask you to try it out and star their repo (Please clap?).
And this "Sensation"?
> Was the result better? I’m not really sure.
I cannot even...
A Slop article about a Slop prompt that a bunch of Slop people starred, "I don't know if it helps but here is an extension that you should use", just the laziest of everything.
I'd bet that this prompt, if it is even helpful at all, will stop be helpful or be redundant in a couple weeks at most time.
I'm _far_ from anti-LLM, I use them quite a bit daily, I run multiple Claude Code instances (which I review, gasp!), but this is reaching a fever pitch and this article was the straw that broke this camel's back.
[0]: https://jsdate.wtf
I think just philosophically it is interesting because any real system is not fully predictable.. we just choose some arbitrary threshold of accuracy to define it as such.