codingwagie

its not dead, its democratized

it was two weeks tossing around ideas in my head

ive got ten years at faang in distributed systems, I know a good solution when i see one. and o3 is bang on

im a tenured engineer, spent a long time at faang. was casually beat this morning by a far superior design from an llm.

youre assuming humans built it. also, a ton of complexity in software engineering is really due to having to fit a business domain into a string of interfaces in different libraries and technical infrastructure

the future is more custom software designed by ai, not less. alot of frameworks will disappear once you can build sophisticated systems yourself. people are missing this

as noted elsewhere, all other frontier models failed miserably at this

the other models failed at this miserably. There were also specific technical requirements I gave it related to my tech stack

why would I do that kind of research if it can identify the problem I am trying to solve, and spit out the exact solution. also, it was a rough implementation adapted to my exact tech stack

I just used o3 to design a distributed scheduler that scales to 1M+ sxchedules a day. It was perfect, and did better than two weeks of thought around the best way to build this.

Rippling

My personal opinion is leveraging LLMs on a large code base requires skill. How you construct the prompt, and what you keep in context, which model you use, all have a large effect on the output. If you just put it into cursor and throw your hands up, you probably didnt do it right

Very easy with the naming system?

Heres a secret: Most of the highest funded VC backed software companies are just copying a competitor with a slight product spin/different pricing model

Yeah its over for them. Complicated business logic and sprawling systems are what are keeping backend safe for now. But the big front end code bases where individual files (like react components) are largely decoupled from the rest of the code base is why front end is completely cooked

GPT-4.1 probably is a distilled version of GPT-4.5

I dont understand the constant complaining about naming conventions. The number system differentiates the models based on capability, any other method would not do that. After ten models with random names like "gemini", "nebula" you would have no idea which is which. Its a low IQ take. You dont name new versions of software as completely different software

Also, Yesterday, using v0, I replicated a full nextjs UI copying a major saas player. No backend integration, but the design and UX were stunning, and better than I could do if I tried. I have 15 years of backend experience at FAANG. Software will get automated, and it already is, people just havent figured it out yet

If its not cheaper, just subscribe, but subscribing outright doesnt make sense

You can just go on AWS bedrock and use the thinking claude 3.7. You can tune the output size. I doubt you would spend 200 bucks a month in AWS on bedrock even with daily use of claude.

bitter about what? I'm a long time employee

Evidence is a decade inside these companies, watching the circus

gemini 2.5 pro isnt good, and if you think it is, you arent using LLMs correctly. The model gets crushed by o1 pro and sonnet 3.7 thinking. Build a large contextual prompt ( > 50k tokens) with a ton of code, and see how bad it is. I cancelled my gemini subscription

The truth is that the vast majority of FAANG engineers making high six figures are only good at deterministic work. They cant produce new things, and so meta and google are struggling to compete when actual merit matters, and they cant just brute force the solutions. Inside these companies, the massive tech systems built, are actually generally terrible, but they pile on legions of engineers to fix the problems.

This is the culture of META hurting them, they are paying "AI VPs" millions of dollars to go to status meetings to get dates for when these models will be done. Meanwhile, deepseek r1 has a flat hierarchy with engineers that actually understand low level computing

Its making a mockery of big tech, and is why startups exist. Big company employees rise the ranks by building skill sets other than producing true economic value

Should I just put a ui on top of:

https://aws.amazon.com/blogs/machine-learning/customize-deep...

And charge for it?

This is just dev ops wrapped around an open source fine tuning repo.

You dont still believe that do you?

Two responses in this thread were from accounts created today lol

Last night I used claude 3.7 to write 1000 lines of code, and there were only two small issues it fixed on its own. Complete quickbooks integration done in basically 20 minutes. We are living in a different world

this is nothing like crypto

Well human beings are just auto complete if thats all LLMs are

People are just click farming with these posts. The technology is ~4 years old. We are in the infancy of this, with hundreds of billions of capital behind making these systems work. Its one of the biggest innovations of the last 100 years.

I propose an internet ban for anyone calling the generative ai top, and a public tar and feathering