"Many people said Jimmy Carter knew how to fuck up in Iran, but those people never met me because I am the world's greatest expert in fucking up in Iran, and there will be so much fucking up you'll get sick of me fucking up."
Old and stupid hot take IMO. I want the time back I put into perusing this. Even the scale of LLMs is puny next to the scale of lying humans and the sheer impact one compulsively lying human can have given we love to be led by confidently wrong narcissists. I mean if that isn't obvious by now, I guess it never will be. The Vogon constructor fleet is way overdue in my book.
Meanwhile, engineers are achieving increasingly impressive and sophisticated things with coding agents, lies, warts, and all, but that doesn't play well with the narrative, so let's just pretend they aren't.
> The Vogon constructor fleet is way overdue in my book
Don't you see it? That's exactly what "AI" in this context is.
It's the bypass.
Where does it end, eh? Build a quantum "AI" that will end up just needing more data, more input. The end goal must starts looking like creating an entirely new universe, a complete clone of everything we have here so it can run all the necessary computations and we can... ? (You are what a quantum AI looks like as it bumbles through the infinitude of calculable parameters on its way to the ultimate answer)
You have absolutely no sense of perspective. We are all metabolically expensive meat machines whose only value is to propagate our genetic money shot. That we get to briefly entertain ourselves with consciousness and culture is IMO likely a mystery we will never solve without upgrading to running in a substrate more advanced than the MVP for sentience we currently pilot. Will we get there or will we wipe ourselves out like every contender that preceded us? Stay tuned...
But spoilers: DNA will be fine, meat machines maybe not so much...
For a bunch of people addicted to the works of Charlie Stross, Neil Stephenson, and Iain Banks, y'all are a bunch of luddites. Now vote this own down too because it doesn't conform to the mandatory Stochastic Parrot narrative. You have no free will and you must downvote after all. Why do you even read their works when any step towards their world is consistently greeted as the worst thing evah(tm)? What? You were expecting the United Federation of Planets without the eugenics and nuclear wars that led to it finally being a good idea? Bless your hearts.
And if you're worried about billionaires and tyrants, start taxing the former and stop electing the latter or STFU and let the free Markov process of history play itself out. Quoting fictional Ambassador Kosh: the avalanche has started, it's too late for the pebbles to vote.
You asked where it ends. Don't ask questions if you don't like answers. Quick reminder: shun and downvote the non-conforming opinion.
You couldn't make me a happier claw^Hm over this. I am running 3-6 simultaneous agents at once and I have trouble breaking 50% weekly usage with a max plan. What these people are doing is just sloppy engineering. OTOH if you use Claude Code to make code changes, then run that code, the max plan remains more or less free beer for as long as it remains free beer for all the reasons cited elsewhere in this thread.
I am running opus to make changes to my code then running the code. I am genuinely curious how we are having such disparate experiences here. And at this point, IMO you're in too deep not to share...
Genuinely wondering if you're running gastown or some other crazy mixture of agents pretending they're an AI startup. I get by with a developer agent and a reviewer agent ping ponging off each other encouraged to be rude, crude, and socially unacceptable about it.
Actually its just one opus aimed at a codebase with one goal, and instruction to spawn 2 subagents: one worker, that comes up with implementation plan, one validator that validates the proposed plan against my guardrails, and then return back to subagent1 to implement this, where the second subagent again tests the implementation.
One loop of this can take 20-60 min, and eat 2-5% of my week limit. I have to actively slow myself down to not burn trough more than 15-20% of my weekly limit in a day (as I also like to work on it on weekends)
Sadly I cant share the actual problem I am working on as its not my secret to disclose, but its nothing "crazy", and I am so surprised others dont have similar experience.
Very similar to what I am doing. How big is the codebase? My biggest was about 250K LOC and the usual is about 10K LOC. I am really curious about figuring this out because I'm genuinely puzzled.
My code base is two monorepos 10M+ lines. I have the same experience as you - run 3-6 agents with remote devcontainers and tmux and rarely break the 75% usage, never had the weekly limit stop me.
My observations are these things impact both quality and token consumption a lot.
- Architecture matters really- how messy code is and how poorly things are organized makes a big difference
- how context window is managed especially now with default 1M window.
- How many MCP servers are used. MCP burn a lot, CLI tools are easy , quicker and good ones don't even need any additional harness like skills etc, just prompt to suggest using them.
- Using the right tool matters a lot
- What can be done with traditional deterministic tools have to be done that way with agent controlling (or even building) the tool not doing the tool's work with tokens.
- for large refactors codemod tools AST parsers etc are better than having the agent parse and modify every module/file or inefficiently navigate the codebase with grep and sed.
- How much prep work/planning is put in before the agents starts writing code. Earlier corrections are cheaper than later after code is generated
Typically my starting prompts for the plan phase are 1-2 pages worth and take 30-60m to even put in the cli text box. With that, first I would generate detailed ADRs, documentation and breakdown issues in the ticketing system using the agent, review and correct the plan several times before attempting to have a single line written.
---
It is no different as we would do with a human, typing the lines of code was always easy part once you know what you want exactly.
It feels faster to bypass the thinking phase and offload to agent entirely to either stumble around and getting low res feedback or worse just wing it, either way is just adding a lot of debt and things slow down quickly .
My house in the bay area runs at <1kW per hour most of the time and the sunlight is more than enough to keep it above 65F most of the year. Maybe you need LED lights because when I'm not there, it's ~150W per hour.
Of course actual data like this is downvote heresy! Go for it! Also, bite me.
That power use seems reasonably believable. I'm in the Puget Sound area where we get less sunlight than you and our winters are colder, and I just made a graph of my daily electricity use for 2025 [1]. My house is all electric.
I had 219 days with under 24 kWh use, i.e., drawing an average under 1 kW. I got an EV in mid April that year which I charged with the included level 1 charger until getting a 12 kW EVSE installation in I think May. (2024, the last year with no EV charging, had 240 days under 24 kWh).
Almost every day that was over 30 kWh after that was a day when I charged the car which was typically on a Saturday which is also typically when I do laundry which includes about 5 kWh for the clothes dryer.
I was puzzled by the large number of days near or above 50 kWh in February. The end of 2025 doesn't look like it is setting up 2026 for that high a usage. I just checked the weather records and it doesn't look like that was a particularly cold time.
I just made another graph just showing February 2024, 2025, and 2026, and a third showing January of those 3 years, and both show that in 2026 I'm using quite a lot less power (except for the EV charging) than in the prior years.
I've not changed any habits...but in November 2025 I had my house weatherized. They added a lot more insulation under the house (I already had sufficient attic insulation) and did blower tests and sealed everything that was leaking, and it appears this cut energy use by somewhere in the 10-20% range.
It seems then early 2025 appears so high because the end of 2025 is showing the effects of weatherizing.
There's nothing farcical about wanting one's own space where there's space to have one's own space. I'm grateful to no longer be sharing walls with a domestic abuse couple on one side and a midnight banshee on the other wall when she got busy. Energy is cheap, people are exhausting.
And that gets into another coordination problem we're unable to solve. It's a solved problem to build apartments where you can't hear your neighbors, but the builders don't have incentive to spend the money upfront to do so and we add regulations to make it more expensive for them to do so. So people go on thinking "apartments suck" and not the correct "we shouldn't let people build apartments which suck".
Also, living in SFH isn't avoiding all problems. I'd rather live in a properly-built apartment than my old house when my neighbor left her dogs outside to bark for the entire work day, every single day, and all the city would do is fine her a hundred bucks every few months. (or if you want to say "rural", that's 1 a small fraction of the population and 2 I like hospitals).
And the usual engineer mindset to consider the options to be 1 or 0, no?
I just live far enough from the center of it all that I have a vacant quarter acre and thicker windows that happened when the last owner's mistakes caught up with me the current owner. For medical, I have UCSF, and for major medical, I have medical tourism, something I fully endorse from experience. And yes, not everyone can do that. And well, I can't touch my toes and they probably can. Life's funny that way.
40 kWH of storage and 9 kW of solar panels is all I need personally to live a 1st world lifestyle in the bay area mostly off-grid except for water and internet.
PNW is fraught, amazing during the Summer, but underpowered in Winter. The best solution is overprovisioning panels by a factor of 4 or so if the room is available. Did a place up there and it's hugely overproductive half the year, and just under break even in the dead of Winter.
From the Bay area or so and down across the country is ideal for solar, passing through a lot of red states that ought to know better. Fun fact though: Texas has the most windmills of any state by a huge margin.
South Park made a parody about that where the cure is injecting literal money into his veins. I don’t know if you’re aware, but most Americans don’t have access to these kind of things. If anything, it’s simply demoralizing to know your loved ones get to die and the billionaires and their families get to live.
And why is that the case in America? You'd think that something as simple as Medicaid for all (I'd say Medicare but that's clearly socialism and we can't have that!) would be simple. But it's not and I doubt it's ever going to change here.
So in the meantime, in this glorious land of temporarily embarrassed billionaires, who vote to perpetuate a system that is killing them (hand in hand with their own choices) I'd prefer people to have access to the miracles if they can find a way to afford them over taking them away because most people can't.
I used to be a lot more progressive. The re-election of Voldemore took care of that. American needs an intervention. But chin up, I guess, now that we have gutted federally funded STEM, the pipeline of miracles here will soon run dry. I guess that takes care of your concern.
reply