When I read the translated version, I felt a flush of relief, because I finally could confirm that it built the right thing and properly implemented the requirements.

I then asked in a fresh session which version was better for it as a reference for future work. It unequivocally voted for the human readable form, and gave it's reasoning with specific examples why.

So, I have a hunch that this "packing of lots of signals into fewer words" isn't really better. The incomprehensible prose just makes us think it knows what it's doing, like some mysterious magic that is only smoke and mirrors.

But I'd like that skill to only be used at the final step, when it finishes something.

I do feel that it's exciting to see what AI will be able to do to help research and discover new things.

My gripe is with their messaging. Because a lot of people will misinterpret that, including politicians, possibly to the detriment of good science.

They are occupying a term in their headline messaging that is much broader than they can actually cover.

A common pattern these days. Overclaim, attract attention, iterate.

The LLM is trained on the past. The capabilities have leapt forward, but its stance is pre-AI. Probably by definition, since that is the bulk of its training.

It frets about changing code. It prefers incorporating workarounds rather than recognizing the need to refactor things. Always minimizing the "blast radius".

Behaves like a junior engineer that is hesitant to take on responsibilities.

"Surfaces" and "Flags" things without giving the context, laying things out, but not zooming in on what's relevant, leaving it open ended without a call to action, or a call to action without substance, garnished behind convoluted AI-speak. Like a junior who doesn't know how to communicate into a team.

Endlessly buries issues that are trivial one-liner fixes as deferrals that "land" in session remarks, PR comments. Prefers to pile up technical debt than to fix it and move on. Probably stems from being trained as a junior that must not extend the scope of any task.

But wraps everything in an endless, complex, dense prose that you are constantly having to sift through and try to understand. Bloats code, comments, and documentation.

It's been said already a year ago that AI coding agents are like genius idiots. With each release of an Anthropic model, its personality doesn't really change, it just gets better at producing content.

No amount of CLAUDE.md and rules tuning changed that.

Is there a way?

Comments URL: https://news.ycombinator.com/item?id=49190381

Points: 1

# Comments: 1

I must be a crap developer, because I probably spend twice as much time bugfixing and testing than "coding". (Both of which actually involve coding stuff, so I really don't like that distinction they make)

This is stuff AI can be really good at, so brushing that part under the table distorts the picture.

Having said that, I do agree with most of the myths they present.

claude has this maddening principle of wanting to minimize the "blast radius", do the least amount of coding changes to get something done, happy to pile up technical debt by "deferring" problems encountered as side notes somewhere. No amount of CLAUDE.md tweaking, and setting .claude/rules seems to get rid of this attitude.

To me it appears like something deeply ingrained in the model itself. Kind of makes sense, since the bulk of the training data is pre-AI, so that it retains an approach of the past, where these facets were driven by completely different cost and time factors.

The past months, I've been hoping that the next model that comes out properly reflects the new reality of agentic development, so that it takes on a more natural stance compatible with how things work today, and we don't have to constantly fight against its fear of change, its drive to minimize coding efforts, refusing to recognize a design flaw and trigger discussions rather than baking in workarounds.

I can't pin it down precisely, but my feeling is that it doesn't fully recognize the fundamental shift taking place. In a sense it's not radical enough, trying more to keep a system afloat whose foundation is being dismantled.

The forces that gave rise to open source will find a new way, because they are based on the nature of the human spirit. We just don't know what it will look like yet.

And here I was using my claude dialogues as a way to refine my speak and better connect with the heartland of innovation.

:-P

Not an active Windows user, but I can't imagine any sane person working on Windows OS without malware protection.

Business objects as state machines.

The idea is to reduce the number of moving parts and simplify processing architecture when building apps that need to be transactionally rigorous and scalable.

It stems from the patterns we used to successfully apply in banks, which worked really well. I believe it's an effective way to get shit done in a broad class of systems. You just need to first get your head around it.

https://medium.com/@paul_42036/whats-an-entity-database-11f8...

But, I think the underlying problem is that we don't understand how this sh*t works. So, it's just an empirical, iterative mess.

Like physics in the the years shortly before relativity and quantum mechanics.

Count me in!

I think that the issue is in part due to the variables. Plotting the mean request time is less intuitive than plotting throughput.

If you plot throughput vs number of servers, it'll be a straight line. And asking people that, I think most would agree on a straight line. But who knows!

Economics will invariably alleviate the memory crunch. It just takes long and requires a huge upfront CapEx.

They have been burned in the past and are hesitant to over invest, worried that the bubble might burst.

I expect high prices to stick around for a while, but I would be surprised if this was permanent.

Which means to me, that price pressure probably won't be the driving force for writing more memory efficient software.

For those who want, I expect AI to make it easier to do that, assuming it's done right, i.e. not vibe coding it.

If you have a subscription to The Economist, I recommend listening to this Money Talks podcast. They talk about the shortage and the economics behind it.

Can anything stop South Korea’s bull run?

https://www.economist.com/podcasts/2026/05/21/can-anything-s...

I have been drawn to coding from the first day I took a course at college learning Pascal and assembly on an IBM PC. Hell I even wrote an IEEE/488 driver for an Osborne 1.

As an experimental physicist, coding was always central to my work. I always felt guilty because I had more pleasure coding than tackling the physics itself.

This is a new age we are entering. AI changes how we do things, but I believe that the human passion to be creative and do intellectual work will always be part of it. It's in our nature.

So I'm not worried that we'll all dry up and turn into zombies.

I'm probably losing some coding skills, but replacing them with different ones, and honing some others.

I used to manage dev teams of 20+ people inside high pressure, high stakes projects.

I've been coding all my adult life, on big things and small.

To me, agentic engineering is a deja vue of managing teams, except in real time.