cultofmetatron

I've been relying primarily on deepseek-v4-flash for 90% of my work. It sips tokens. that model will run on 128gb. not a cheap configuration for a consumer but within the budget of a developer relying on it for work.

Ive only been using kimi 2.5 and deepseek pro for reviewing PRs for security issues. less than 10% of my workflow requires a full powered frontier model.

I think the issue is overblown by people who think claude code is a good harness and use opus for everything. opencode is objectively better. its much more verbose about what its doing, you have more control when it comes to offloading to subagents with targeted context (crucial for running through larger jobs) and I can swap between codex and open weight models.

the ship has sailed on my handcoding at work. the AI is producing stuff thats more bulletproof than what I can do in the same timeframe and if my competitors are using it, the pressure to ship is that much higher.

Personally, I've taken the time its freed up to spend more time on mathacademy and reading more theory oriented books on data structures and algorithms. AI coding systems are at their best when paired with someone with broad knowledge. knowing what to ask for and knowing the vocabulary to be specific about what you want to be built is going to be a much more valuable job skill going forward.

One example is a small AI based learning system I have been developing in my free time to help me learn. the mvp stored an entire knowledge graph and progress in markdown files. being an engineer, I knew this wouldn't scale so once I proved the concept viable, I moved everything into sqlite with a graphdb. then I decided to wrap some parts of teh functionality in to rust and put everything behind a small rust layer with the progress tracking logic still being in python.

someone with no knowlege of graph databases or dependncy graphs or heuristics would not be able to build this even if they had AI. they simply don't know what they dont' know and AI wont' save you there.

That said, I think its important to also spend time in the dirt. I've recently started pickign up zig as my NO AI langauge just to keep. those skills sharp.

well I could start with feminist marginalization of male role models from early education. The school to university pipeline is highly weighted in favor of giving women success. If we recognized that boys and girls are different, we could continue pushing women to success without pathologising male traits by giving each what they need to succeed. instead we have a one size all box that helps one at the expense of the other.

The fact that teenager boys can't tell that Andrew Tate is a characture of failed masculinity or that looksmaxxing is straight up idiotic is a pretty glaring example of that.

one of the many reasons america is so screwed up right now is because of our insistence on ignoring the very obvious statistically significant dimorphism between genders.

that doesn't' mean trans people and nonbinary dont' exist. We need to make accommodations for them where appropriate. However, it doesn't do any one any favors trying to homogenize how we teach kids. you inevitably help one at the expense of the others.

The fact that a small group of special interest groups have made "boys and girls are different" into some divisive political issue is absurd.

heres a fun one for you https://www.youtube.com/watch?v=kYkIdXwW2AE&t=315s

> basically you're speed running yourself into harder decisions when using AI.

on the contrary, I freed myself from the burden of having to find all the places in the code base where we used stripe and patched them in one go along with the tests to prevent regressions. That represents DAYS of work that I condensed into a few hours.

who cares if it can't know good structure and how to handle failures? I know how to do that. I have a skills file I created that tells stripe our policy for handling error failures, defaults for structures as well as guidelines for how we should deal with communications between different systems. Before i spent hours building this stuff out. now I just spend 20-30 min reviewing a pr to make sure it follows my directives and move onto other problems.

Thats said, i agree with you on principle. I hand coded an app from a solo dev to now managing a team and gettin ready for an imminent series A. AI doesn't save you from scaling issues, you still need to have a clear idea of what you want from the ai and build processes that give it the context to do its job.

I call that job security :)

venture capital are the real enemies here. valve has stayed out of that game which is why they've managed to focus on delivering value to their users. as soon as venture capital gets involved, investors are now the customer and the customers are effectivly the product.

2 days ago, we updated a stripe library which broke everything. With AI, I was able to one shot wrapping all of the calls into a shared service, patched the broken api contract across the entire app and got our signup and payment flows working again. solid day and a half of work. this would have taken a days of back and forth debugging previously. AI is not a panacea for everything but its doign valuable work right now.

> The original challenge was more in line of "I wonder if CC can do this now?"

well, I can respect that for sure

> Less memory footprint. No reliance on libs.

rust can do that. You can run a hyper stripped down rust that was made for embedded devices specifically because those devices don't have room for a runtime.

I have no problem with these AI summaries but someone needs to make a law requiring the AI provider to generate links to the primary source as part of the output. If a human writer ripped off someones work and didn't attribute, it would be a huge scandal. when an AI does it, its expected.

seriously.... we already have a constellation of good deterministic tooling for taking a relatively high concept spec to low level assembly. what does an llm offer in generating optimized asm that rust wouldn't??

> We’re a long way from figuring out how to get flow state with agents

its been the opposite for me. being able to create things with almost zero friction has lead me to have to slow down for my own sanity at times. I've had to setup "handcoding time" as a way to keep me touching virtual grass lest I completely lose myself building stuff at all hours.

literally thinking of taking up Haskell just to have a language that forces me to slow down and think in my off hours.

Imagine if they did and then redirected the heat from those data centers to warm their greenhouses and then to warm homes.

honestly really surprised they haven't gone full ham on AI data centers.

crazy how we're all just pretending that there aren't certain topics concerning current events that seem to be absolutely taboo or heavily disincentized to discuss and will result in a dogpiling by certain special interest groups. we all know who they are and yet we all tacitly accept it.

if only there was a place that was naturally cold to take advantage of airflow for cooling and cheap renewable electricity thats always on...

> Surely run by lawyers?

they do the dirty work

china is run by engineers, America is run by bankers.

the consequences are significant

I really wanted to get excited about opus but in my own real world usage, I wasn't getting much out of it before hitting my limits. meanwhile i can abuse codex on 5.5 for hours getting a whole lot of work done. Plus, open code and PI are much more fun and interesting harnesses to work from than claude code imho.

I will however say that claude work and design are really great up until i blow its limit.

cod fishing boats used to have to be wary of the catch being so big that it would tip the boat.

We have no real frame of reference for what we've already lost.

I'm in a similar situation

1. Even really novel projects have large chunks of glue code and boring infrastructure that the novel bits depend on. claude means I spend 10% of my time on the borng stuff and 90% of time on stuff I previously onky had 10% of my day to work on. In my experience the software picked up our idioms fast and for context, we have a skill file explaining code standards.

2. codex and gemini are comparable when paired with a good harness (pi.dev). if things ever get really bad, I'll drop 8k on a dedicated agent coding server and run it locally. I tried it recently with my current system and it was sub par but I was running a drasticly simpler model.

My startup just rolled out MAX plans for our engineers. we literally jumped into AI last week. Been in operation for 6 years and are profitable.

on the same day the new framework pro launches...

this just reinforced my recent belief that the best way to handle the AI boom is to pivot into robotics

what are they talking about product teams needed to justify themselves? a good product guy's job is to talk to the users and figure out what to build. My job is to figure out HOW to make it happen. Neither side need to justify themselves. Good product people are vital to making sure engineers don't spend months building the wrong thing.

> The standard for large chain hotels in the US are much, much lower than everywhere else in the world.

this is true for fast food as well. mcdonalds in poland and spain were MUCH better than the slop in america. I had taco bell here in srilanka recently. it was DELICIOUS and tasted like real food. same goes for popeyes and pizza hut here. pizza hut in america on the other hand tastes regrettable and left me feeling like shit.

seriosuly underrated comment. I finished a 20 min bike ride and feel clear headed. Havent' consumed anything other than black coffee. Most people are so used to eating continuously and never train their bodies to be metabolically flexible. Doesn't help that the "most important meal of the day" shtick was invented by cereal companies trying to sell us crap dessert masquerading as health food.

> There seems a fair enthusiasm in the UI of these to hide code from coders. Like the prompt interaction is the true source and the actual code is some sort of annoying intermediate runtime inconvenience to cover up.

I've finally started getting into AI with a coding harness but I've take the opposite approach. usually I have the structure of my code in my mind already and talk to the prompt like I'm pairing with it. while its generating the code, I'm telling it the structure of the code and individual functions. its sped me up quite a lot while I still operate at the level of the code itself. the final output ends up looking like code I'd write minus syntax errors.

all power to them but I'll never understand the urge to rest your bare taint on a tiny saddle while your balls slosh back and forth. that sounds awful in private. in public just sounds like a humiliation ritual.

to all of you that enjoy this, I respect your right to do it but hot dammnnn.

If only I could elect to send 4000 to NASA and not to enable israel's genocide in the middle east.

edit: bring on the downvotes, israel is committng a genocide and doing it with out tax dollars.