fullstackchris

Verimu - we're trying to help medium and small businesses across the EU get up to speed with the new Cyber Resiliance Act requirements (which start in September!) trying to make it as frictionless as possible - drop in a github action and you are good to go. Web based dashboard coming soon!

https://verimu.com

and the "hype-wits" don't realize openclaw is just claude with good mcp. there is nothing new under the sun. its just the first time someone was benevolent enough to open source the codebase to the public or it went viral enough to matter... and yet what people focus on is its "emergence" or "agi" - neither of which are remotely true. but good luck "crushing" those "mid-wits"

exactly. so much text with so little actionable or notable content... actually 0

another slop post - show costs, show what you have built, or at least a tiny snippet of code? (or even just direct links to git repo or projects IN post please?)

getting sick of this fluff stuff

> Using LLM agents is expensive: if they give you already 50% more productivity, and your salary is an average salary, they are not. And LLMs will only get cheaper. They are only expensive in absolute, not in relative terms.

critical distinction: unless your getting paid comparable to your ouput (literally 0 traditional 9-5 software jobs I know unfortunately) this is infact the opposite - a subscription to any of these services reduces your overall salary, it doesnt make it higher...

then there is the case i know the dishonest are doing is firing of claude or whatever and going for a walk

I mean his rage is somewhat warranted, there is a comment a few threads up of a guy asking what model comparable to Opus 4.6 can be run on 16 gb VRAM...

Supporters and haters alike, its getting pretty stupid out there.

For the millionth time, it seems learning basics and fundamentals of software engineering is more important than anything else.

$1000 a day is such an odd choice of rule... why not just $50? Why not $10000?

so much garbage ego in statements like this. if you really knew about software, you'd recognize there are about a million ways to be successful in this field

> better to not have bugs in the first place

you must have never worked on any software project ever

this is such a strawman argument. what are they going to take from you? your triple forloop? they literally own the weights for a neural net that scores 77% on SWE. they dont need, nor care, about your code

exactly - and this is what good agile attempts to address - implement (importantly) user-facing function in exactly the smallest size possible (also important) with those two things you can build, identify issues / questions / problems in the fastest feedback loop as possible

indeed, i would argue 'big iterations' are the ones where all the problems which the author mentions crop up in the first place!

> Since the foundations like tech stacks, frameworks, and libraries are always changing rapidly these days, there are few accepted best practices, and most issues are incorrectly believed to be subjective.

Huh? at least in web, the "big ones" (angular/react/vue/svelte) have been around for YEARS at this point and IMO mostly stablized (though i still don't understand why angular needs to releast a breaking change version every 6-12 months)

the major 'issue' is often near 0 understanding in the fundamentals i'm talking like, super basic, what is an onclick function, how do we get our website to talk to our backend. if you can have clean domain and abstraction cuts, the rest really is a 'technical detail' - i.e. language / framework / technologies truly are all subjective. there are probably combined over 1000 valid tech stacks for a standard "show me table entries in a web dashboard" - not one is 'more correct' or 'more wrong' than the other, but rather in a given _organization_ or with a _given set of devs_ etc. that makes it 'more wrong'. the tech doesn't care, its the team of humans and HOW that team of humans interacts with the stack that is where things can go off the rails

there are so many ways to skin a cat and there ARE tradeoffs (positive AND negative) to each of these tech decisions... i'm not sure what the author is getting at - he seems to hint there are a select few sets of known best practices and tech choices, but fails to list them explicitly... this is dubious at best, and in some way counteracts his claim that it is "incorrect" that tech choices are subjective.

if you want to be non-subjective, be objective. name exactly the tech decisions and best practices you are talking about!

I mean, they could be - if it's self-hosted, has proper failure modes, etc. etc., but all these things have gone out the window in the current cringe gold rush

This is not a weekly limit though, it is a 4 hour one. You still have not clearly defined what you are talking about.

you do realize behind each of these 'autonomous agents' is a REAL model (regardless of which one it is, OpenAI, anthropic, whatever) that has been built by ML scientists, and is still victim to the context window problem, and they literally DO NOT get smarter every day??? does ANYONE realize this? reading through this thread its like everyone forgot that these 'autonomous agents' are literally just the result of well-crafted MCP tools (moltbot) for LLMs... this brings absolutely nothing new to the pot, it's just that finally a badass software engineer open sourced proper use of MCP tools and everyone is freaking out.

kind of sad when you realize the basics (the MCP protocol) has been published since last year... there will be no 'agent revolution' because its all just derived from the same source model(s) - likely those that are 'posting' are just the most powerful models like gpt5 and opus 4.5 - if you hook up moltbot to an open source one it for sure won't get far enough to post on this clown site.

i really need to take a break from all this, everything would be so clear if people just understood the basics...

but alas, buzzwords, false claims, and clownishness rule 2026

tl;dr; this isn't 'true emergence'; it rather shows the powerful effect of proper and well-written MCP tool usage

This is incorrect. I have the $200 per year plan and use Opus 4.5 every day.

Though granted it comes in ~4 hour blocks and it is quite easy to hit the limit if executing large tasks.

This points out a general theory / concept I've been working on for the past few weeks - once software development and decent enough copy writing can be done by the LLM - you are indeed only bottlenecked by your own knowledge / creativity. The LLM, as much other hype is out around there about it is - is still just a latent tool and will do absolutely nothing if you don't interact with it of course!

I see LLMs more and more like a mirror - if YOU can orchestrate high-level knowledge and have a brutally clear vision of what you want and prompt correspondingly, things will go well for you (I suppose this all comes back to 'context engineering' just with higher specificity on what you are actually prompting) turns out domain knowledge, time/experience-built wisdom, and experience in niches, whatever they may be - will and always will be valuable!

SAP the lowest on both axis... had to crack up at that

agree with this article 100%... its those who have no long term programming experience who are likely complaining - the models are just a mirror, a coworker... if you can't accurately describe what you want (with the proper details and patterns you've learned across the years) your going to get generic stuff back

love how a completely valid point gets downvoted becuase the average person refuses to believe they are part of the problem "no! its those big corporations and airline industry! my daily commute has no input at all!"

and this is why we'll never solve the problem

Then go ahead and write vanilla JS and raw HTML! No one is asking you to use any of these bad "state of affairs". If you do build a 100+ page SaaS app without any framework, let me know, I'd love to see how it works.

The frameworks have NOT gotten slower! God I hate Hackernews sometimes... whats really going on is actually that not a single dev reads the release notes / improvements / learns how to actually use the framework. If anything, the latest React release was almost purely a performance improvement release (and has been for a while) ...most people need to fully understand a tool they use before complaining about it.

Everyone always wants a frontend framework that "just works" - sounds a lot like a free lunch to me! You have to manage the state and updates of your application at some point - the underlying software cant just "guess" what you want. But I'm always like a broken record when these react hate / <insert frontend framework here> hate threads show up - most of the confusion is derived from lack of basic concepts of what problems these frameworks solve in the first place.

> a Redux action, which would update the global Redux store, which would cause all Redux-connected components on the page to update, which would cause all their children to update as well. In other words, collapsing one comment triggered an update for nearly every React component on the page. No amount of caching, DOM-diffing, or shouldComponentUpdate can save you from this amount of waste.

yeah this is pretty much 1. an incorrect implementation and/or 2. an incorrect take

and easily solvable with a bit of 'render auditing' / debugging

hot take (that shouldn't be?): if your code is super easy to follow as a human, it will be super easy to follow for an LLM. (hint: guess where the training data is coming from!)

> I don’t know if I feel exhilarated by what I can now build in a matter of hours, or depressed because the thing I’ve spent my life learning to do is now trivial for a computer. Both are true.

I'm not so sure... I mean it's true that regardless of if you are a beginner, junior, or 'senior', if you say "build me an instagram clone" Opus 4.5 will probably do a decent job. I think the skills go still in understanding architecture, and just knowing where pitfalls and problems can arise, or even making some important 'abstraction cut' prompts. I think applications can still grow to a point where you still need to prompt at specific domains only, or the model will fail to do everything you want it to - especially if you give it massive 'fix this this this anad that too' prompts

I'll also argue that level of skill depends on what one can make in those two days... it's like a mirror. If you don't know what to ask for, it doesn't know what to produce

what "AI" are you speaking of? all the current leading LLMs i know of will _not_ do this (i.e web search for latest libraries) unless you explicitely ask

This is probably the best post i've seen about the whole LLM / vibe coding space at least in relation to web dev. Indeed, as the author states, the code / agent often needs some coralling, but if you know all the gotchyas / things to look for, you can focus 100% on the creativity part! Been loving it as well.

This overly discussed thesis is already laughable - decent LLMs have been out for 3 years now and unemployment (using US as example) is up around 1% over the same time frame - and even attributing that small percentage change completely to AI is also laughable