DubiousPusher

doh!

Living? Probably. Happily? Probably not.

What? MKUlta is absolutely not a conspiracy theory.

To the chagrin of the unfortunate General Foods corporation, the water flavor enhancement product used at Jones Town was actually Flavor Aid.

And maybe that's a pretty good analogy to what's going on with this post. It contemplates a world of suburban parental neglect and private burrito taxis and lays them at the feet of AI. But these were happening before LLMs burst onto the scene.

In a world of $3,000 rent and $3,000 medication and $3,000 preschool, what do you expect will happen?

I hand rolled a sandbox with credential injections on call out using WSL and mitm and Windows credential manager. The only credential I had to have in the box was a fine grained PAT with copilot response. I used some hacky git push/pull to move work in and out of the sandbox. For collaborative UX review I would switch the agent to limited perms and CDP back to my host browser.

Recently I moved to Docker Sandboxes. This removed most of what I was having to hand roll. Though I still own the renewal for short lived tokens. The git setup in docker sandbox is especially nice. The host is served as a remote 'host' in the sandbox and it can read but not write the host's origin.

On the host, each sandbox got is reachable as sandbox-[name].

https://www.docker.com/products/docker-sandboxes/

Exactly. You can buy on server grade mobo and CPU, stock it with ddr4 and run qwen and basically get gpt 3+ level quality now. A year from now, I imagine we'll see even better efficiency.

I've spent 10 years implementing new technology into businesses from all over the world and the thing that has killed the most projects at the proof of concept phase has not been whether it works. It's whether the cost of going to production from PoC produces a significant ROI. AI is absolutely changing the economics there.

Humans were simply nowhere near answering all the useful questions they had which software could answer. The problem was that software was expensive.

Now, software is cheaper and so people who couldn't afford to answer questions they've long wondered about can afford to answer them.

This is really something which feels like it should be a library of regexp.

If you're standing in GNC staring at a tub of creatine wondering if it will make you smarter, you better hope it does...

exits stage left

I'll be here all week folks!

I think this is a really sober comment. There are lots of knock-on effects of this claim, even if it's not true which are consequential. The fact that a spokesperson for the US government is going out of their way to comment is concerning.

Strong bee-hive pinata vibes here.

It's especially sad because on of the things those LLMs are best, almost purpose built for is to tell those students which books to go open, where to find nuggets people haven't bumped into for years, to make cross-connections that would take a PhD a decade to find.

My bona-fides here amount to little more than being a big time reader of non-fiction. But IMO, there's a nice synthesis here. Rather than going long rounds of asking LLMs about a subject, I usually end up asking it for book recommendations. It's much better than a google search and you can push it into some deep corners if you go past the surface level recs.

You can get quite specific. You can find texts you wouldn't discover unless you spent years studying the topic. Often these are completely approachable and give interesting perspectives they just get buried behind a wall of syllabi and listicles.

This is how I ended up reading Thompson's 'The Making of the English Working Class' and Graves' 'Goodbye to all That' among others.

Yeah, this is very much one of those stories where people from many different perspectives or chopping it up on a plate and ripping it through a straw.

I think the important lesson is to use clear eyes to evaluate what the rewrite buys you. I was on a team that rewrote a native code app in C#. We also had access to early cloud tech in the Azure stack, what is called queue now and then was called service bus.

These two technologies combined greatly simplified this specific product making it far easier to maintain. Performance on these services was not important so native code was carrying a lot of penalties without the benefits.

Having a well documented messenger like service bus with great SLAs removed several tools we had needed in the old implementation.

We were able to leverage the tests form the original product to define success and tmthus were able to solve a lot of the edge cases in the new code w before we even shipped.

However, the old code was perfectly fine code. If new technologies had not provided significant simplification of the service architecture, a rewrite would've been foolish. And without the very good previously existing tests, we would've run into a lot of issues as we released.

What do your tests look like. Because rewriting by hand and rewriting via AI have the same load bearing on whether or not your tests cover your scenarios and your integrations well.

Because there is more value in understanding someone else's ideas than as some kind of cultural favor? East Asians built empires, invented and discovered incredible things. They have developed elaborate artistic, musical and familial traditions. All of that is of course related to their cosmological ideas. If you could, why wouldn't you understand ideas that were integral to so much human activity? And if they fail to understand your culture in the same regard, that just puts you at an advantage.

In the words of my old man, "I'm not telling you what I know, cause then you'll know what I know plus what you know and then you'll know more than me!"

I don't think the intent of Robert Pirsig's work was to outline a git gud strategy cloaked in chillness. The book is heavily inspired by Eugen Herrigel's Zen in the Art of Archery which is explicitly not about trying to get good at something.

Both books highlight the value of dissolving conscious aim in favor of experience something. Pirsig's point isn't, you gotta act like a noob and then you can be good at maintaining motorcycles. His point was that there is a joy in losing yourself in these things that have to be done. If you are rushing to get it done or focusing too much on the end state, you will lose the joy and this thing will become a chore.

He does make the connection that years of doing things this way will lend you a kind of skill. And he connects the ideas to the Western concept of gumption which is a kind of motivation or persistence but again the book's core is not, lose yourself and you will get good. It's more like that a Western obsession with accomplishment can rob you of the joy that can come from engaging with activities for their own sake and not pushing through them just to get them done.

If you're in the US and this excites you, you'll probably enjoy GSA auctions.

https://gsaauctions.gov/

We're approaching the definition of magic here aren't we. And I think this is what really divides this discussion. There is one set of people who insist that things must be explainable. And if something is explainable, it yields to science and is no longer magic.

On the other side, you have people who insist that there are things which do not yield to science. So whether they admit it or not, they insist upon the existence of magic.

In fact, the definition of magic might as well be, that which does not yield to explanation. The only question once you believe in magic is, what alternative epistemology do you accept? Scripture? Tradition? Divine revelation?

But the sensation in a sense is a lie. Cold strictly speaking isn't real. And for much of human existence we spoke of it as if it was a substance due exactly to this specific sensatation.

I would caution outright categorizing this as paranoia stemming from a mental illness. The problem with delusional paranoia and justifiable paranoia is that clinically they can present the same.

> Just keep in mind all the dangerous people who these groups investigated that they did nothing about that went on to do bad stuff.

There are numerous people that America's intelligence agencies have intimidated, harassed and yes drugged for similar reasons.

OP, I hope you have been seen by a mental healthcare professional. They can help you determine the nature of these experiences. I hope you have extensively documented these experiences. Sharing that documentation with your family or others who you know to be sober in judgement is probably the only mechanism you have to distinguish if your experiences are based in reality.

This is what sprint planning is all about. It's ostensibly to accept the work. But my God how everyone's hidden assumptions come to the surface.

I think it comes down to your team discipline. It can magnify your sins and your virtues.

LLMs have single handedly turned the hardest part of this job into entire job. The hardest part of this job is troubleshooting, maintaining and developing on top of an unfamiliar code base. That's not a new experience for anyone who has lived the production code life. One of the first production engineers I was tutored under used to love to say, "the code should tell you a story."

I love C. I came up on C. But C does not tell you a story. It tells you about the machine. It tells you how to keep the machine happy. It tells you how to translate problems into machine operations. It is hard to read. It takes serious effort to discern its intent.

I think any time you believe the codebase you're developing will have to be frequently modified by people unfamiliar with it, you should reach for a language which is both limiting and expressive. That is, the language states the code intent plainly in terms of the problem language and it allows a limited number of ways to do that. C#, Java (Kotlin) and maybe Python would be big votes from me.

And FYI, I came up on C. One of the first senior engineers I was tutored by in this biz loved to say, good code will tell you a story.

When you're living with a large, long lived codebase, essenti

There's the rub I suppose. I don't think an LLM can achieve AGI on its own. But I bet it could with the help of a Turing machine.

I guess I'm very confused as to why just throwing an LLM at a problem like this is interesting. I can see how the LLM is great at decomposing user requests into commands. I had great success with this on a personal assistant project I helped prototype. The LLM did a great job of understanding user intent and even extracting parameters regarding the requested task.

But it seems pretty obvious to me that after decomposition and parameterization, coordination of a complex task would much better be handled by a classical AI algorithm like a planner. After all, even humans don't put into words every individual action which makes up a complex task. We do this more while first learning a task but if we had to do it for everything, we'd go insane.

I guess maybe the tone would be less noxious if the core coceit of the satire felt more legitimate. I mean, Wikipedia was kind of a shit show back in the day. It's had 20 years of maturation which is more what makes it useful today.

And yes, the media is full of blatant and bald faced lies but is that worse than the credulous and uncritical way the media basically endorsed the war in Iraq?

I get that it's a joke but the joke kinda only works if there's some truth behind it. And I just don't think there is here. I think people are lamenting old media now, not because the information sphere is genuinely worse today but because it was a comfort to have a consensus in public opinion regardless of how true that consensus was.

The sneering and nihilist tone is very off putting. But not nearly as much as the boomer brained conception of the world's information model pre 2004, which was not nearly as good as those who invoke Murrow and Cronkite believe it was.

lol, qualia