MangoCats

It can be like that, and other times it can spit out perfectly good work that similar jobs have taken me a week in the past in under an hour. Depends on the task, depends a bit on how you ask, and depends on the model. Claude Sonnet/Opus 4.5 and higher have gotten pretty good about actually saving time and producing useful results.

Except when trying to draw 3D cats in Blender, I can say with authority now: Opus 4.8 on High/Max thinking still can't pin the tail on a cat correctly without a half dozen very specific annotated views showing it where it goes. It claims it's having trouble because the cat is lying down... our cat lays down 22 hours a day, suck it up and learn what they look like already.

I started by designing all those files around last September-October timeframe. By November I was realizing: the AI knows better how to make those files than I do, so instead of writing SKILL.md or whatever, I describe to the agent what I want it to configure and explain to me how it's going to do it. It makes SKILL.md for me, I review it - correct the (usually few and far between) things that are misquoting my intent - and tell it to install it. In areas like softtware development that's been working pretty well, and getting more and more invisibly automated by the tools since then.

Claude Opus 4.8 dropped a few weeks back "best graphical understanding ever" - well, I'm trying to use it to do some Blender work, it sucks - it's worse at it than the code writers were in January 2025.

Those are the threats, how often does it happen? How often is it blamed on software from a company that has somehow become untouchable? The day before I was talking with the guy that makes the software for gas station interface panels, I had one of those interface panels hit me up for my zipcode as they all did back in the day... I accidentally, but quite certainly, typed it in wrong and hit enter... 3 seconds later I'm approved and pumping gas. Software guy initially said that shouldn't happen, but when I told him it happened to me at such and such gas station last Thursday he started hand waving about how sometimes the information isn't actually verified...

The AI company marketing (and development) I see still seems to focus mostly on the "we can give a really non-specific prompt and get a functioning app out of thet" - which is missing the point for my uses of it.

My company is very interested in leveraging the new tools where we can, but not laying anybody off (yet) - I think the target is hoping that our exploration time is being roughly balanced with increases in efficiency, which is more or less how we're managing it for the past few months.

How it’s being utilized should be the target of ire, not the technology itself.

try talking with an out of work actress about how it's being utilized, their only answer is to ban it all.

That actress should have access to Universal Basic Income

As should we all have had for the past 25 years... keep wishing.

I can guarantee, the code coming out of that shop was slop, 20 years ago.

I have had a fair amount of success getting AI to do those refactorings, reducing 2000 lines of code to 400, and generating 3000 lines of documentation (including flowcharts) explaining how the 400 lines work, adding 1200 lines of automated testing to prevent regressions, etc. etc.

There's a lot of existential dread out there... try talking with an out of work actress about AI and find out how she really feels...

It comes down to risk-reward. If the risk is low enough, they take it - assuming the additional reward outweighs the consequences.

When your decision makers can just declare corporate bankruptcy when the risk finally happens, with no personal exposure other than loss of future income? You can bet they'll take that risk every time.

Finance software is astoundlingly sloppy.

I was working in a university town, happened to get hired in at decent market rates by a biomed startup that didn't mind paying for me. When they left town, I stayed, and a precious few other companies would pay "my rate" - so I ended up cold calling on quite a few places just to see what they were about. I stumbled into the software development manager's office of a company that did ATM and POS software - they used the same tech stack I was using for biomed. After a few minutes the manager stopped the conversation and said "sure, fine, I want you, but: can I afford you? What's your current salary?" I told him, he laughed and said: "Well, I'm the highest paid software guy in the building and I don't make half that. Mostly we hire kids from the Uni who think they want the experience, they turn over every few months on average. I've told management how bad that is for the quality of our software, they don't care."

empirically derived principles and best practices exist and that software engineering is a thing.

The thing I find most vexing about "software engineering" is that the majority of it comes down to sociology/psychology more than it does science. People make mistakes. They mis-communicate, under-specify, assume, overlook, forget, and screw up.

Programmers practice somewhere between lawyers, authors and graphic artists, and other than the graphic art side of their endeavors, most people never "read" their product. The most valuable principles of software engineering have nothing to do with the complexity of sort algorithms, logic trees or other abstract concepts they were teaching in "computer science" back in the 1980s. The most valuable principles come down to: how do you manage the problems inherent in the situation of human beings writing a bunch of code that almost nobody ever sees which can be fraught with problems that almost nobody will detect until years after the original authors have all but forgotten what they did?

ultimately about critical thought and solving problems/achieving functionality with limited resources

I find in software engineering that the resources tend to be ample, it's the capacity for critical thought that's constrained. Predicting the users, predicting the future, predicting what users will do and want to do in the future... get that right and you've got the requirements for good software. Without good requirements, your software can build all kinds of fancy bridges to nowhere.

At one point, about 10 years after graduating with my Masters' in Computer Engineering, I looked around about getting a PE license and the reality was: it had (and still has as far as I can tell) no value in the software field. I have a BS in EE, and if I wanted to start signing drawings for building electrical systems, a PE is just the thing for that. Around here, you need to apprentice under a PE for a time to get them to certify you as a PE, and the PEs we have aren't in software, they wouldn't know how to evaluate your software skills or professionalism. Reminds me of high school where they recognized that about 6 of the students knew far more about computer programming than the best (and only) teacher we had for it, so we were put in an "independent study" class to learn what we could from the equipment that various local businesses had donated to the school. Even as a practicing EE in the biomedical device design field, there was really no value to the PE license - for similar cultural reasons: the best biomedical engineers are in a different world from our existing PEs.

you will also be held accountable if something goes wrong.

I graduated before the internet. I had researched local companies the old fashioned way, and the first one I drove to to ask about a job, when I got there the parking lot was empty and there was a padlock and chain on the door. Guess I need to go to #2 on the list... turns out they (a pacemaker company) had been reprocessing faulty devices and shipping them with inadequate testing after rework, leading to the devices going bad shortly after surgical implant, requiring additional surgery for replacement. A whole chain of technicians, engineers, and executive management were culpable for the expense and risk they were causing for the users of their pacemakers. Other than the FDA shutting them down, there was a bunch of blow-hard talk about accountability, fines and jail time for management, but neither even came to a court hearing. Our system is, frankly, still very wild-west in terms of accountability for engineers in emerging fields.

it’s critical that we decide how software engineers play a role in preventing those things and how we hold them accountable when they don’t.

Agreed, but software has already had life-safety-critical and massively financially impactful roles in society for 50+ years now, and I see precious little progress toward formal accountability.