sibeliuss

In my opinion he nailed the timeline. It just needed to take off, and it is.

McKenna to Alex Jones? That is an offensively bad comparison for someone as philosophically astute and well-rounded as he was.

And tripping to a fever dream... You know, sometimes it's best to just not respond if you know nothing about a subject at all.

I can. An OBE feels utterly real, minus the "oh shit... this is happening!" aspect of it all. It is not like a dream, even a lucid dream. And like a cliched cinematic experience you lift out of your body intact, as if there were two of you, one there and one here. It is legit and strange and the 'reality' of it is a lot to handle, after the fact.

These newer models are a f'ing nightmare. I hate it so. I'm never moving off of Opus 4.6.

I'm fully on the agentic coding train and haven't manually typed code in a while so I understand the sentiment around moving beyond this level of analysis. However, how can this advice work practically speaking, day to day? Especially at ones day job?

I'm sitting here working and just caught a handful of really bad decisions by the agent, one right after the other, cascading from an assumption that was incorrect. My ideas and architecture are sound in this codebase! Are those things simply to remain in the code if they work 'good enough', or are there consequences right around the corner?

The problem is that you need to twist the cube

If you try to quit something, you need to be patient. Like really patient. You can't know what its like until you've given it a few years -- especially if you've been taking them since you were a child. A whole new world might await you if you can figure this bit out.

Well the answer is easy, don't vibe code then?

Maybe a lot of this comes down to people are having fun building stuff in a way they weren't before? But i imagine this will all die down.

I'm not being literal. Revolutionary technology arrives on the scene, is extremely visible, changes a whole industry and frankly creates an entirely new economy. All eyes on Anthropic.

They don't get enough credit for being right in the middle of a revolution, yet still managing to ship something that largely works incredibly well, because this thing is a workhorse.

Is it that, or is it just that every software developer, enterprise, dev and non-dev alike has their eyes on Claude Code as the most popular software project ever? Software in general has tons of bugs. People need to understand scale here, and what this looks like in practice. They're doing an incredible job given the circumstances.

Even clearer, if you don't adapt to the changes taking place in the field there might not be a future for you. Its not about age, it is about attitude and flexibility (which are, admittedly, issues when getting older).

In other words, if you want to continue stubbornly typing out code by hand, the person right over there has already mastered agentic tooling and is doing vastly more than you, more quickly, and with greater precision, and will simply be a more fit candidate to hire. Roles for this type of legacy stubborn personality will be less and less, and you will age out as part of the old school.

He just means: by this age you've probably found your preferred title and level, unless you want to rise to more C-level / executive positions, which are rarer in any case and most folks don't want.

Get this ai writing slop outta here. People have zero shame anymore.

This is all so speculative and whatevs

It saves so much time! Think of the best find and replace and autocomplete and macro and every other possible super tool you use and roll everything into one. The design phase of any significant feature pales in comparison to all of the (now fully automated) tasks that you can just hand off to the agent to do nearly instantly and perfectly.

This is precisely why these types of articles don't make any sense to me, and strike me as case studies on human laziness. If you want good output, you'll review the output and iterate. If you want good foundations, you'll write them, and then later those foundations will prevent, to a very great degree, bad code from getting written by the LLM.

These articles frustrate me greatly. That said, the author's point about token cost is real, and a risk.

As someone who works from home, and has for a long time, and would do it no differently -- and also as someone who has been up in the chain a bit and had an opportunity to look closely at things like productivity and other working patterns -- I can tell you that I've seen the most deeply unethical things, things that could never ever happen in an office. The whole "Quiet Quitting" movement, and just taking advantage in all kinds of ways. I've seen it again and again, particularly with younger employees.

If you are a remote work company and hire someone who is not passionate about what they do, they will, for certain, take advantage. And why wouldn't they? So it is easier to just lean on the side of caution, especially if the management chain isn't entirely on top of things (which is common, because everyone is busy).

This thing is horrible.

If you have it installed, it will silently inject a warning into claude that you should use tailwind, even if your app is not! Then every single request will silently question the decision as to why yr app is using one thing, rather than another, leading to revisions as it starts writing incorrect code.

I couldn't believe it when I discovered it. For so many reasons I am vehemently anti Vercel. Just discovered this two days ago, after installing their frontend skill.

Cmd+Tab skills! But mainly, its a matter of only ever doing one thing at a time and optimizing for that in lots of little ways.

This "rule" is especially useful now that I'm coding primarily through agents. Secret weapon number 2, while everybody else is getting burned out running ten agents at once and producing slop, while I'm now writing more (and better) code than ever.

This was my secret weapon for years. My coworkers could never understand my focus and productivity and were always surprised when I said that it was due to working from a tiny laptop screen, and no more.

To appear as a strongman in the eyes of those in power, those who are clearly incapable of introspection. And by such moves he himself gains power.

His statements about this were purely politics, and nothing more. He himself does not believe this. It's political revisionism.

Why must everyone preprocess their blog posts with ChatGPT? It is such a disservice to ones ideas.

This ^ Exactly it. This will be the change.

I'm extremely cautious about complexity, yet have adopted a claude-based dev flow. It comes down to watching and guiding it, and not letting it run autonomously. At a certain point your codebase will tip over into the patterns you've defined and claude will recognize and follow them. Just treat Claude as a vim editor mode and you will see a big difference, and your relationship to the tool will change.

Happy to see a new CSS-in-JS lib. All of this madness about runtime performance costs does not apply to 99.9% of the population. But good abstractions do. And then there's latency, and machines are getting faster, and browsers getting better, etc etc. This whole argument and the related FUD was all a non-issue to begin with, at the great cost to DX.

This utterly boring AI writing. Go, please go away...

Biome missed the bus by not getting mixed language formatting in soon enough. Oxfmt got it, and then won.

Appreciate this take. It makes a lot of sense and can see this happening all over right now.