SwellJoe

I suspect the public model will refuse. Anthropic models have gotten extremely strict on biology and security work.

I'd be happy to be wrong, though. I've never tried to do biology with Claude, but I have gotten many refusals and downgrades for security work.

Yeah, without the ability to search the web, a very small model is going to be too dumb to be useful, and maybe even dangerous due to hallucinations. But, there is a point where the knowledge of self-hostable models will surprise you. That point is probably not runnable on the average laptop, though. It's maybe in the ~30B range, but more realistically in the 128B MoE range. I guess in their tests Qwen 3.8 27B got as many right as the much larger Nemotron Super, but I'd bet Qwen 3.8 Flash would be better than either, but it needs 128GB of unified RAM or a big GPU and lots of system RAM to run the 4-bit version.

I think if I had to build an emergency LLM today, that had to run on modest hardware, I'd bet on Gemma 4 12B. It's got excellent reasoning and good vision/audio and speaks 140 languages.

But, I don't know about the "classic" knowledge base theory, though. Is there a high quality curated pile of survival information that could be bundled into a web UI and made searchable in a knowledge base? The LLMs aren't focused on that topic, so there's a lot of wasted space, but they know a little about a lot of things, including survival topics. Combined with Wikipedia, and maybe a few other sources, you're probably better off with one than without.

I guess one could use some huge models plus web search to compile/distill a focused survival knowledge base or LLM.

Edit: Project NOMAD seems to mostly be exactly that. It has authoritative sources in a searchable knowledge base and the tiny LLMs are an afterthought, which is probably what they should be. https://www.projectnomad.us/

This is the worst kind of slop. The kind where someone doesn't exhibit any concern for quality or user experience. I know that's so, because it's a gazillion unrelated apps that clone existing huge apps, built by a couple of people and Claude.

The reality of launching a good product with AI is that the coding is very fast, but the QC, the documentation, the refinement and user testing, isn't all that much faster, if you care about it being good.

This is a mountain of code, full of bugs and weirdness that users will be the first to find, because nobody else is looking at it.

My process for building with AI is "intense weekend of vibe coding" and then several times that time spent on refinement and testing that comes from actually using the software a lot. A couple of devs can't be responsible for every major application.

With AI, you can make anything you want, but you can't make everything.

Because society breaks down when there is an elite class of people who are so wealthy the law no longer applies to them, while a significant portion of people are on the brink of being homeless, and many more are one health emergency away from it.

I use Hugo published to Github Pages for my blog. I've never thought about performance (it's Fast Enough™ when I visit it), but I just checked and it's 100 on pagespeed. The magic of a static HTML blog is you don't have to think about performance. An entire category of problem just disappears.

The surveillance capitalists have made it hacker news, by putting their thumb on the scale for fascists.

I love it when democracy punches a fascist in the mouth.

There's no reason to wait until a child is six to teach them to read. I was reading much earlier, before formal schooling, because my parents were readers and read to me regularly. I had a tremendous enthusiasm for books because books were important to my parents.

Plenty of research indicates reading to kids from a very young age improves their education outcomes later in life.

I'm sorry your parents didn't know to do that. Hopefully now that you know, you'll read to your kids (if/when you have any).

Nobody's running GLM 5.3 on a Strix Halo. But, yes, I'm using cloud models for everything hard, including coding. I use local models for smaller API tasks or sub-agent tasks and experiments with fine-tuning and benchmarking.

"Any suggestion that Meta favors one side is false"

Weird how it keeps happening (e.g. just last week, Instagram and the No Kings account), and it's always to the benefit of right-wing extremists. I'm sure it's just an accident, though, surely they wouldn't lie on the internet.

For folks with 128GB inference machines that's definitely the more interesting model. 27B is dog slow on a Strix Halo. And, while Qwen 3.8 Flash is quite snug in 128GB at four bits (a bit more comfortably at three bits, but intelligence is really dropping by then) but is notably faster than the dense model. It thinks a little less and thinks a little faster, adding up to a real improvement. At four bits, it feels a little bit smarter than 27B even at eight.

If someone has one or two 32GB GPUs with decent bandwidth (faster than the Strix Halo or DGX Spark), the dense model is the obviously better choice, and I think that case is more common for the average developer.

Way off topic, but I enjoyed Amiga E. And, I reckon you're one of a handful of people I would take seriously when they say, "I made a new programming language."

"I had a friend once that kept using open-ended phrasings and ambiguous descriptions"

A failure to express intent, not a failure of grammar. Perfect grammar can mislead just as easily.

I consider that among the unsavory use cases, I think. I'm not sure how I feel about its use in art, exactly, but I'm confident this tech will most often be used for propaganda (because that's how it has already been used most broadly). It is currently possible to detect AI video and audio, with reasonable confidence. I mean, unless you're a facebook boomer, in which case nothing is too ridiculous to be believed.

But, a world where billionaires can make ads showing candidates saying and doing things they've never said or done is a very dangerous world, and being able to fabricate a podcast or whatever very convincingly is going to empower the very worst people. Blurring the line between fact and fiction, so nothing one sees or hears is really believable anymore, serves fascists and autocrats, exclusively.

https://www.usatoday.com/story/news/state/texas/2026/09/09/k...

When one interprets grammar rules as prescriptive rather than descriptive, it is easy to fall into the trap of believing in "correct" and "incorrect", when expressing intent is the single most important thing. Expressing intent is not a thing AI can do, thus far, as they don't want anything...there is no intention.

I'm certain there are folks out there who have a hard time with written English that could benefit from an AI editor, but I would almost always rather read casual English written by a human, even if idiosyncratic and "incorrect" sometimes.

And, to be clear: Hard to read English can never be correct, no matter how carefully it follows grammatical rules, and AI often writes hard to read English.

It's one particle. It's not a bomb.

I have a DeepSeek account and almost always use it when I need something with API access. I consider it Good Enough™, if not competitive. I also have a MiMo token plan, though that's weird in that it's not a monthly subscription, it's just a bulk buy of tokens that expire after a year, but still seems to be a pretty good deal on a pretty good model.

When I've most recently done the same tasks across multiple providers I have a subscription to, I found the order of generosity of them was something like Gemini->Claude->ChatGPT->Kimi. OpenAI used to be a lot more generous than all of them, but that ended recently, and now it's quite stingy in the $20 plan. What competitive model has a more generous subscription than Gemini?

I immediately thought, "Nicolas Cage". Turns out he's only seventh, but still a lot closer than Kevin Bacon.

Yeah, the $20 Claude plan is stingier than one might like, but not as stingy as Kimi. I think the best $20 subscription deal these days is probably from Google, now that Gemini 4 Argon exists and is an acceptably high quality model for coding. It's got quite generous usage and includes some other Google account upgrades (though I know some people don't use their regular account for Google AI for fear of account suspension or whatever, so the extra storage and other account upgrades are not a useful thing). I can use it pretty heavily without ever running into caps. The $20 ChatGPT plan used to be similarly generous, but no more.

So, I tolerate the "ums" and "ahs" and "uhs" in conversation from humans because they're human. If an AI is going to speak to me (gods forbid), it better be concise and clear and focused, or I'm throwing it out the fucking window.

It is interesting that they've done this reasonably successfully, impressive technology. Novel ideas can have inherent value, absent direct uses they may have, as they can be a stepping stone toward other inventions. But, I'm having a hard time coming up with a use case that isn't predatory or intentionally misleading. Company support agents pretending to be human, for instance. Or, taking the next step on AI girlfriend/boyfriend type interactions. Or, outright scams. Models already do an excellent job with voice cloning, at least for intonation and timbre, adding realistic conversational tics makes it even more likely grandma is going to fall for it when her "nephew" calls needing help.

But, that seems to be extremely common with new tech these days. There's always an angle that is unsavory. Marketing, scams, propaganda, surveillance, killing, that's where the money is, so everything bends toward them.

Same experience. I had the $19 monthly plan for experimenting and running benchmarks, but it was a uselessly small amount of usage, a single task would blast through the whole five hour limit and a big chunk of the weekly limit. All of the US provider plans are remarkably more generous (though OpenAI plans have gotten a lot stingier lately, where they used to be the most generous).

Yeah, in general, city council members are more accountable than a corporation. I can go to a meeting and yell at them. They're also living with the same service, most of the time, so they have a vested interest in making it a high quality experience. It's certainly possible to imagine bribery and other fuckery going on in local government that would make service worse or more expensive than competition, but corruption is historically pretty rare in the US (though it's been on the rise, as permission has been granted from the top). And, competition is an illusion when it comes to utilities; the competitors are all just competing to take a cut, they're not able to compete on service because they aren't actually the provider.

Texas answers a lot of questions about how well privatization of utilities works (and the answer is often "not very well"). The electric industry in Texas has competitive rates with the rest of the country, but it also has a body count. Putting off repairs and upgrades in order to save money and make investors more money has caused several long outages during extreme weather, including in 2021 when several hundred people froze to death. I have a photo from that year of a thermometer showing 22F (-6C) inside my RV, which I was living in full-time and parked near Dallas, at the time.

And, as a customer, it's a bad experience. I have to switch providers every year, because the rates you get the first year are competitive, and then for the subsequent years they offer much worse rates, 50%-100% higher than the previous year. So, I either have to deal with that annual pain in the ass of picking a new provider and setting up billing, etc., or I pay among the highest rates in the country when the rate spikes. There's also the constant deluge of mailers from competing providers, and gangs of sales people hanging inside Walmart or going door-to-door (I have a "No Soliciting" sign, which is only occasionally respected).

I used to be a free market purist, believing most things would be better with competition, but for a natural monopoly like electricity, it's just forced inefficiency. The law requires the illusion of competition, but the real work of keeping the lights on is done by one entity. All the other power companies are just middlemen, running their own marketing and billing operations, but not doing much else.

I would be very happy to have electricity go back to being publicly-owned and operated, with regulation and oversight.

And, for another data point, the best trash/sewer/water experience is, by far, when the municipality handles all of it and there is a monopoly on those services (even if operated by a private entity). I've lived in places where you subscribed to one of several competing trash pickup providers, and that is always more expensive and provides less (rarely includes regular bulk pickups or recycling in the standard plans, for example). And, you then have loud, smelly, trash trucks rolling through your neighborhood multiple times a week. Admittedly, in those cases, it's often a rural area where picking up is more expensive for the operator due to longer distances, but even in the suburbs it costs more and does less.

Slop all the way down.

Some small rural papers never stopped being primarily print because a significant portion of their readers don't have home internet, but those papers often run as part of a charitable trust, because they can't make enough money otherwise. e.g. the Georgia Trust for Local News owns a bunch of small-town papers in Georgia. And, while you can get access to those papers and some local articles via their web portal the actual paper are PDFs behind a paywall, rather than a website (https://courierheraldtoday.com/e-editions/).

Often those small rural papers are the organ for county or municipal government (e.g. for publishing legal notices and such), and they have print editions because it's required by law.

But, I don't think there's any way to sustainably run a for-profit newsroom in a small town, without grants and large donors, print or web or some combination of the two.

SCOTUS has made a mockery of itself in recent years. Naked partisanship, disregard for precedent and "settled law" (according to their own words during confirmation), openly accepting bribes. It's maybe the worst thing about the degradation of politics in recent years, because they can't be voted out.

If you want to be a writer, leave the court and become a writer. If you want to directly invest in the stock market (instead of via a blind trust), leave the court. If you want to accept a quarter of a million dollar "gift" from your "friend" (who just happens to regularly have business before the court), leave the court and go camping or whatever the fuck.

It's exhausting how degraded everything about American institutions has become, including one that's supposed to be above the fray.

Facebook knows what you want to see, because you can follow pages and individuals. They choose to show those scam/bot posts to you anyway. This isn't to fight bots.

Surveillance capitalists have built a truly miserable internet.

I've been researching local newspapers, and the problems they face, lately, and one of them is that none of the social media sites allow them to get any visits from their followers because they either significantly de-rank posts with links off-site or it costs money to reach followers with links, or both. Of course Google scraping their sites and summarizing is another symptom of the same problem; FAANG wants all the revenue and a monopoly on what you see. Every penny every eyeball. None for small businesses, none for independent media, none for individuals.

"how does any independent forum deal with this at scale without banning links?"

By banning spammers and scammers. Facebook opts not to ban scammers, as it's a significant portion of their revenue, and the latest AI slop is very good for engagement.