When I read her campaign site, it was just a bunch of generic feel good happy bullshit without any specific stances or commitments. That’s when I knew I was voting for El-Sayed in the primary. Glad I was able to see through her worthless bullshit. Go fuck yourself sideways, Hailey. I voted today and couldn’t be happier to cast mine for El-Sayed.

I’m not sure if I’m a normie or weirdo here. Like I enjoyed the internet when it was just a bunch of tech nerds sharing their geekery with one another. And I hate that now it’s full of morons who inundate the rest of us with their love of sportball and reality tv and fucking mundanity. But also there are weirdos here that I want nothing to do with. So this all strikes me as very perspective-dependent.

Can you imagine how much dirt an fbi under direct control of Trump must have on him? He knows how fucked he is when accountability comes knocking.

Unless you have insomnia, anorexia, and sleep apnea.

It is even a parenting technique using the illusion of choice on children to force a decision that was never a choice to begin with.

I raised my children to be unafraid to question or challenge authority. And I fucking regret it. I hope they’re happy I did in ten years but it sucks right now.

Do this for me: hold your phone 9-12 inches from your face and stare at it. Then alternate closing your left and right eyes. See the screen jump left and right? That jump is the amount an image can appear to leave the screen. The photograph is showing you the image of the phone the left eye sees and the image of the fish the right eye sees. The image itself is a fake of course, but it’s likely somewhat close to what it would be like to view the actual 3D display.

I wish he’d come to Michigan and joke about the Epstein files and how he doesn’t care about affordability. Abdul El-Sayed could use the boost.

If this recession hits enough people as hard as it seems, I’m going to have to invest in a prosthetic just to make sure folks like you can have the pride of earning money with your handjobs instead of accepting handouts.

Between this, someone stealing 2.5 billion from Binance, and the whole running America gig, I’m rethinking my life of not-crime.

My nickname for the guy is

Nobody <clap> gives <clap> a fuck.

Trump is obsessed with belittling people with mean nicknames. But they are fucking tired and you don’t have a tenth of Trump’s brazenness to be endearing. Fuck off to whatever country you hole up in while your state suffers climate disasters, you toad-faced suppository.

That’s my nickname for you, Ted.

buys someone else’s good idea

You only forgot to mention the part where he does this not with cash, but with his shares in his failing companies as collateral.

Hahaha. No. Management is not losing jobs over this. Not in the quantities needed.

For now, that’s not crazy. I have a company-provided api key and subscription. Now maybe they bumped me to the a $100/mo tier without telling me, but as far as I know the lowest tier keeps me in tokens heat about all month and I use it a lot. I switch over to API for a few hours per month and probably spend more in that time than my sub costs all month.

I spent about $2k developing a set of tools and AI orchestrates them for me, and I can add new tools to orchestrate as needed. Caveat: I do more production support and my teams do the production development work. We are all on subscription plans, but they do more hand development than I do.

Point being, you can easily spend >$1k/mo and me and several people on my teams did before we got subscriptions, but the subs give some AI assistance without going all-in on AI coding, which is the sweet spot IMO.

I don’t and wouldn’t bother, but I don’t see the point. If this is a sign of sociopathy, removing the account doesn’t cure the mental illness. If it’s being fed back into training data, stop. This seems needless, though it’s likely to lead to increasingly strict but completely vague usage requirements. How do I know exactly what behavior falls under this? So I have to over-moderate just in case.

Not in this case but this could lead to that sort of thing.

I bought and needed a hybrid. I had a 212 mile round trip to work when I bought my Volt. Today I have a quarter tank of gas I’m afraid will go stale. Winter is coming, though, and I’ll need the engine for heat and because the mileage drops to about 20 — less if I get on the highway.

I’m still leery about range and heat issues, but at least my wife bought a Tahoe so we have distance trips covered. That frees me up to buy an EV next go round and I guess if the heat sucks it’ll be a decent fair weather car.

Writing a threat is not illegal. Hell people vent all the time, threatening to do things they know damn well they never will. The law says transmitting a threat to another person is illegal because it can be used as intimidation or conspiracy. I think there’s a damn good argument that she didn’t knowingly transmit it to anyone. She thought she was writing in confidence to a non-person. And if it’s not her first time expressing outrage to AI, she would know it would only try to deescalate her.

Who knows how the case will go. I can see it going either way — probably depending on how much money she has. Laws are going to have to catch up to technology in this case, and it’s going to be bumpy. I definitely agree with erring on the side of caution. Private, local AI is far safer, but of course it’s less capable for now.

I almost never use AI to write my words. And when I do, it’s heavily hand edited. Every single word of my above comment was hand written. No AI was used to summarize or reply to your post. I did use fair fewer profanities than my usual style (which helps a reader hear the human behind the words) because I didn’t want to come across as aggressive or insulting, especially with English not being your first language, I erred on the side of caution.

This is where the open spec tries to help/solve. But this is a bandaid. Without a lot of hand-holding the models will make shity decisions/code. And this is cumulative, the more you try to steer the wheel, the worse it gets. I can specify details, but a 3 years old project is in this shape, and no amount of LLM will solve/help.

I’m interested in open spec since reading your article. I wasn’t aware before. It might be helpful to my efforts. In all cases when we run into a decision point or problem, we update the documentation first, and then implement.

To be honest, with a large enough project a decision will take longer, if not impossible in a LLM driven codebase. It will be years to debugging, breaking down and rebuilding to even get close.

It depends what you think is large enough. I work in microservices where the effort is far beyond simple Python scripts at which LLMs excel, but not at the level of a full product. Our process is not nearly so messy. But it does require a lot of up front work, and a lot of intermediary steps to make sure that every problem, every judgment call however big or small is formally documented into the spec.

Wrong, from the experiments on the academia, we get the fact that engineers with AI are often slower, because the problem was never in the code

I challenge this notion. I have real, measurable productivity gains of 20-30% which is double what I expected. I believe the key factors are experienced developers and critical thinking, but I’m aware of that research and it doesn’t align with my experience, so there is some difference at play. I’ve seen many examples of it going wrong, but with caution and skepticism, we are finding success that defies that research.

But I think you missed my larger point, which was that the developers grow and become more capable in general, where even with our system, the AI can only grow more capable within one particular project and you’re largely starting from scratch on the next.

I try to keep around 1.5k to 2k words a week. It’s not always the case, some weeks I’m somewhat more inspired, sometimes I need some refinement, but this is a personal view, I want the reader to have a “conversation” with the author. This is the type of metaphor I try to use.

I applaude your commitment. I can’t do that. I’m always afraid I won’t have anything worth saying on a regular schedule. That said, the current document is not a conversation but a lecture. Splitting it up allows a reader to say, “interesting, tell me more about this.”

Again, all human words. No ai involved. Probably you’ll find some typos if you look. No matter how hard I edit, I always do. Good luck. Hope to read more from you.

I’m going to break this up into two. Feedback on content and feedback on style and presentation.

Content

LLMs didn’t create cognitive debt, but they do make it worse. Cognitive debt is paid every time a team member leaves or is promoted to a non-contributing role.

The interesting thing to me is that, in order for an LLM project to be successful, all of that cognition has to be done up front, and written down. If done well, you aren’t relying on the LLM to figure anything out, and it’s just rote execution by a simpler model. The build process then exposes holes in the initial design which must be plugged within the documentation until all of the cognition has been performed and the LLM can execute.

The beauty of that model is that you can be 2/3 of the way through a project, realize you missed something foundational and rearchitect and rebuild the whole project in hours instead of weeks. LLM saves no time or money if you have perfect planning and execution skills, but it does enable you to make significant pivots far faster than a human team.

One of my teams just finished a project that took two massive pivots just as design was finished and execution was underway. The result was all the time explaining v1 was wasted and left confusion for the developers, v2 was continuing to be developed even after v3 was provided, and months of time were wasted understanding and building the wrong thing. This was a six month effort when it could’ve been two.

Now, with a real developer, they eventually build their own cognition and their own mental model and are then capable of cognitive work — LLMs can assist documenting the cognitive work, but they are piss poor at performing it. LLMs can’t cognate and they can’t replace developers — but they can change the shape of development work to be more about requirements analysis and architecture, and if used well can improve efficiency of teams.

I could write a whole article on that — I could write a book — but I don’t have time and AI would completely fuck it up, so it’s just in my head, still taking shape.

Presentation

I might have more specific feedback on your points, but I’d forgotten them by the time I got to the end.

I’d suggest moving your analysis of the examples to their own post which you can then link to support your points. The concept you are trying to convey isn’t difficult, but this article is about 10x the length it needs to be. You basically write well enough, and you attempt to engage the reader well, but this article is like having a chat with someone and they just launch into an hour long impromptu lecture and giving you no chance to absorb or respond.

By breaking it up into smaller chunks, you can give a reader an opportunity to engage with an idea fully, and then they can decide if they want to follow the links to read your takes on this project or the, or simply accept a one sentence reference in the primary article at face value.

There is writing out there so enchanting that you don’t mind investing the time because the reading is as much entertainment as it is learning. This article aspires to be that, but isn’t there.

This weekend I wanted to set up my raspberry pi with a LLM multiplexer so that my wife, my kids, and I could share a single subscription but still have our own customizable memories and instructions. Needs a web chat interface using codex as the inference provider. Some day when I have the cash to set up a local LLM server, I’ll switch the back end over.

I don’t have time in my life to create it, so either LLM can do it or not. No downside to letting it try. I gave it barely any instructions beyond that. I wanted a Java microservice. A handful of hours and a couple of usage resets later it’s done and tested.

Allegedly there is a Java repository somewhere on my pi, but I haven’t seen a line of code, and that service is running. Now, I haven’t tested it, and I won’t use it until I’ve reviewed the code, but shit I see how seductive this is for folks who don’t know how to code themselves. And how dangerous because I’ll bet when I look at the code I’m going to have alarm bells ringing.

It’s not that my brain is tired or even that I trust LLMs, I just don’t have time and either an LLM can create the thing I want or I do without. If the project fails, nothing of value is lost. But the difference is I’m looking deeper than if the thing does what I want — I need to make sure it’s done in a safe, extendable way.