I have a bespoke memory system that I wrote myself and it avoids this problem entirely by making every memory a contextual search space. The “don’t use stripe” memory would only be recalled into context if the model was prompted to do something with payment processing.
I don’t really write code with it at all, and that’s why I burn so many tokens.
I like writing code, I’m good at writing code. What I hate doing is dredging through logs, filtering out test scenarios and putting together disparate information from knowledge silos - so I have the AI doing that. It’s my research assistant.
Effectively I’m using it like an automated search engine that indexes anything I want and refines the results by using the statistical near neighbors of how other people explained their searches.
Finance professor Aswath Damodaran, and others, have made many useful insights as to how AI as an investment is likely to pay out.
One technique is, instead of trying to pick individual winners, look at the total addressable market. Then compare the market size with the capital being pumped in. If you look on this basis, Aswath concluded that collectively AI investment is likely to provide unsatisfactory returns.
Here's a recent headline: "Nvidia’s Jensen Huang thinks $1 trillion won’t be enough to meet AI demand—and he’s paying engineers in AI tokens worth half their salary to prove it"
There are two parts to this. 1. A staggering $1t is expected to be invested in AI. Someone worked out that this was more than the entire capital expenditure for companies like Apple. We're talking about its entire existence here. IOW, $1t is a lot of dough. A LOT.
Secondly, this whole notion that AI is such a sure thing that half the salary will be in tokens should ring alarm bells. '“I could totally imagine in the future every single engineer in our company will need an annual token budget,” he said. “They’re going to make a few 100,000 a year as their base pay. I’m going to give them probably half of that on top of it as tokens so that they could be amplified 10 times.”'
I recall from the dotcom fiasco that service companies like accountants and lawyers were providing services to the dotcom companies and being compensated in stock options rather than cold hard cash like you'd normally expect.
Very dangerous.
As another poster pointed out, this really boils down to FOMO by big tech. I'm expecting big trouble down the line. We await to see if I'm early or just plain wrong.
Neither. It's the most severe FOMO in history. The best case scenario is equivalent to attempting to pick future winners just prior to the industrial revolution really kicking off. Except this time around the technological timelines appear to be severely compressed and everyone is fully aware of what's at stake. And again, that's the best case scenario.
I doubt it. And as I said, telcos have ceased new sales of ISDN and will be shutting down copper networks within 3–5 years.
Therefore if there are still TV and radio stations still using it, they will be forced to stop using it by circumstance, i.e. they will find their ISDN will cease working after the telco shuts down the kit in the exchange.
You can doubt it all you want, ISDN is used internally in broadcast all over the world. Telcos shutting it down has nothing to do with them and won’t affect them.
>You can doubt it all you want, ISDN is used internally in broadcast all over the world
Since you claim to be a domain expert, give me hard named examples with independently verifiable links. At this stage I want facts, not anecdotes.
Because right now, my semi-educated guess is they are all using IP-based streaming codecs and protocols for remote contributions, outside broadcast, studio links and pretty much everything else under the sun.
No, he's right. I have a friend who does voiceover work and is and announcer for the UK Channel 4. He does all his work from home using an ISDN link. It's a huge pita for him because the telcos don't want to know indeed, but it's the usual story with legacy workflows.
I think it's also a fully switched system so you are guaranteed bandwidth with no packet drops or buffering which is clearly useful for broadcast work.
> No, he's right. I have a friend who does voiceover work and is and announcer for the UK Channel 4. He does all his work from home using an ISDN link.
But how much is this to do with either Channel 4 not supporting (in the "assistance" sense of the word, rather than "interop") his move to IP or potentially his personal reluctance to change ("ain't broke don't fix it" mindset).
Given he is in the UK and the incumbent telco (BT) are switching off ISDN in 2027, I really suspect there is more than meets the eye to your friend's story.
I am not seeking to judge, I just feel realistically that it highly unlikely that at this late stage (1 year to go to 2027) there really is no other option other than ISDN when collaborating with Channel 4...
The reason I say this is because even the briefest of internet search throws up hard publicly-available evidence that the broadcast world have indeed moved on in the world ....
Way back in 2008 the BBC were already investigating options to move away from ISDN...[1]
... and evidence is out there the BBC are using SIP for critical things like remote Radio contributions[2]
> guaranteed bandwidth with no packet drops or buffering
I assume they have a migration plan or already migrated. I don't know, he told me this years ago. It wasn't his choice it is/was just the standard in the industry. I'm sure they're moving to IP at the moment, I was just pushing back on the idea that broadcast doesn't use it. If they've moved away from it, it's a relatively recent change (last five years or so).
> If they've moved away from it, it's a relatively recent change (last five years or so).
So the TL;DR is we are not disagreeing then ? ;)
I never expressed any doubt that traditionally ISDN absolutely was the lifeblood of broadcast, there is zero doubt about that.
What I am saying is that was then and now is now. We are now sitting here in 2026 and the world of comms has moved on dramatically and the broadcast world has moved along with it and that those people still clinging on to legacy ISDN will be forced to shift to IP-based technologies because they will be forcibly disconnected by their telcos very soon (1–5 years).
The reality is also that here in 2026 we live in a world where (a) you have a 4k tv and high-end audio system in your home ... so there is a natural limitation on what utility ISDN has in this world, and (b) the general public is increasingly consuming the media produced by the broacaster via IP means (streams over 5G-IP to mobile, streams over IP to Apple TV boxes) ... so if a broadcaster can escape the un-necessary complexity (and cost) of transcoding ISDN-received content to IP and shift to an IP-to-IP environment, why would they not want to do that ?
I have taken 4-5g in a day while suffering from intense pain before.
There is a limit to the amount of opioids they will prescribe you, even if you are in mind shattering pain. For instance while attempting to get your dental insurance to actually cover a treatment you may find yourself between risking organ damage or risking $5000+ in ER visit bills only to have them refuse to give you anything but Tramadol.
> I guess it is much better than the situation before that, where you paid $5000+ and they also gave you an opioid addiction.
Having a condition that actually warrants strong opioids and not being able to get them at any price is definitely not an improvement.
The problem is fundamentally that we want to pretend doctors can always distinguish two people describing the same symptoms when one person actually has them and the other is trying to get drugs. The often can't, so you can either make it hard for people to get pain medications even if they need them, or you can make it easy for people to get them even if they don't. And between these the second one is unambiguously better, because the first one is the government screwing innocent people and the second one is guilty people screwing themselves.
> And between these the second one is unambiguously better, because the first one is the government screwing innocent people and the second one is guilty people screwing themselves.
Could not agree more. Depriving people with legitimate pain of opioids is IMHO legitimate torture. It's a bit of a variance on the trolley problem in that the doctor/government isn't causing the pain, but their inaction is prolonging it.
Brother (or sister), you were simply not trying hard enough. I live in a very clean, safe, expensively-policed county, and even I know where to buy fentanyl for much lower cost than a hospital. I would happily turn to that than take 20(!!!) advils in s single day.
Let's review the policy options in light of your suggestion:
1) We make it hard to lawfully acquire pain medications. You pay $$$ to see a doctor and you pay it even if they refuse you. If they do, you then have to pay $$ to get them from Stringer Bell, or start there to begin with if you didn't have $$$, and hope they're not cut with drain cleaner or unevenly mixed so that some days you get 100% corn starch and other days you get a fentanyl overdose.
2) We make it easy. Anyone can get them from Walmart. The people who need them pay the same $ they do for a bottle of Advil/Tylenol instead of paying $$ to murderers or $$$ to waste scarce medical resources that could have saved someone else's life. The bottle from Walmart always has a consistent amount of the drug in it and neither the dental patients nor the addicts get a surprise fentanyl overdose.
Whenever people here mention to my critique of US healthcare how its now mostly solved problem now, its 'good' to see the other side and reality. It certainly doesn't seem solved unless you have a million or two just laying around on the account, while mortgages and kids tuitions are paid. And I can easily imagine a long term condition or 10 which, if unlucky in terms of treatment cost coverage can wipe out that sum in a decade or two, for a single person.
Seriously, how can you guys consider this acceptable. I am not of faith but doesn't bible teach to be kind to your fellow men above all? One would expect more adherence to such basic moral rules in such conservative christian society.
I don’t know a single person in my life who thinks US healthcare is good, so that’s weird. And many my peers a have good jobs with good health insurance. Everyone I know has at least one bad story about insurance, if you’ve ever had more than really basic checkups.
The problem with the US system is that it doesn't know what it's trying to be.
If you did a socialist system then everything is "free" but possibly slow and expensive on the back end when the government isn't efficient.
If you did a libertarian system then everything is cheap but it's caveat emptor because nobody is stopping you from buying morphine for $10 from Amazon.
The US system isn't either one. It pretends to be a market sometimes but then has a bunch of rules to thwart competition. Doctors are required by law to do residency but the government limits the number of residency slots in response to lobbying from the AMA so there aren't enough doctors. "Certificate of need" laws explicitly prohibit new competitors for various services. Insurance is tied to employment to make it hard for individuals to shop around. Laws encourage, require or have the government provide "prescription drug coverage" to make patients price insensitive so drug companies can charge a huge premium for patenting a minor improvement or simple combination of existing drugs and have the patient will something which is marginally if at all better even if it's dramatically more expensive because they don't see the cost when the insurance/government is required to pay for it.
It's a big pile of corruption, because all that money is going to places. But then if you try to fix it, half the population insists on doing the first one and the other half is only willing to do the second one, and the industry capitalizes on this to prevent either one.
Maybe instead we should do both rather than neither. Have the government provide a threshold level of services, like emergency rooms and free clinics and anything more than that the local government wants to fund, and then have a minimally regulated private system that anyone can use if the government system doesn't satisfy them.
I think you're trying to apply ideology where it doesn't belong. Nobody on earth would advocate for such extensive spending to facilitate agreement on financing. It's extremely, extremely inefficient. (But it does produce jobs, which makes politicians super horny.)
The market also won't assist us, as we can't exactly compete future treatment costs against unknown illnesses.
Merely providing emergency rooms and "free clinics" will ensure that people only use these services.
A public option eliminating profit margin seems to at least be sane, and ideally would starve private funding from existence. Any remaining options would highlight deficiencies in the existing system.
A schumpeterian system, if you must slap an ideology on it.
> Merely providing emergency rooms and "free clinics" will ensure that people only use these services.
Emergency rooms operate by triage. If you're having a heart attack, you're going in right now. If your shoulder has been bothering you for six months, you might have to come back multiple days in a row and spend the whole day waiting before there is a slow enough day that you can be seen. There is then an obvious incentive to go pay a private physician to be seen immediately instead. Free clinics are similar: There are no appointments, it's first come first served, and then most people prefer to pay $100 to schedule an appointment rather than wasting an entire day waiting in a queue, but you still have that option for people with no money.
Emergency rooms are also a natural monopoly because in an actual emergency the primary consideration is which one is closest, which doesn't make for a competitive market. So it makes sense to have the government do that. Whereas non-emergency care (which is the large majority of medical expenses) would allow people to compare prices or make cost trade offs against distance or convenience etc., if we would actually expose people to pricing. For example by requiring price transparency and then having insurance pay the second-lowest price for that service within 100 miles of your location, but then letting you choose where you actually want to go and make up any difference yourself, or choose the lowest cost option instead of the second lowest and then put the difference in your HSA.
> A public option eliminating profit margin seems to at least be sane, and ideally would starve private funding from existence.
It's not clear how a government option that doesn't have taxpayer subsidies would do this any better than a private non-profit. There are many existing non-profit healthcare providers and they don't have meaningfully lower costs than for-profit ones.
The general problem is that "non-profits" and government-operated services still have money flowing through them and "profit" can be extracted in all manner of ways other than paying dividends to shareholders. The officers can just pay themselves high salaries, or whoever is in charge of the budget can take bribes/kickbacks to shovel money in the direction of the contractors or unions paying them off.
Meanwhile the nature of "profit" in a competitive market is largely misunderstood because of accounting differences. If a non-profit wants to buy an MRI machine, they have to take out a loan, and then pay back the loan with interest which they account for as an expense. A for-profit company might get the money to buy it by selling shares to investors, and then paying dividends to the shareholders instead of paying interest on a loan, which goes on the books as "profit" instead of interest expense. But you couldn't just replace them with a non-profit and then lower prices by the amount of "profit" they were making because then they also wouldn't have had private investment and you're back to needing the loan and paying the same money as interest to the bank.
The thing that requires providers to be efficient is competition, because then the ones wasting money or taking bribes have to cover the amount wasted/embezzled by charging more to customers and then the customers don't choose them because they have higher prices. But that's the thing the existing regulatory system goes out of its way to thwart.
Interesting, I rarely go to Walmart if I can avoid it, but I've noticed the stores here seem to only have a couple staffed checkouts left. There's 14+ isles of self checkouts.
This is way more interesting to me as well. I have projects that use small limited-purpose language models that run on local network servers and something like this project would be a lot simpler than manually configuring API clients for each model in each project.
The solutions these scientists need are bespoke and share little in common. They also have fixed grant funding.
In 2009 I made $15/hr working with some PhDs and grad students in a couple different labs to automate their workflows - I was the highest paid person in the room most of the time.
A lot of the work I have done for scientists when I was a contractor (and a bit while working for bespoke software consultancies) was quite literally just making programmatic applications out of Excel sheets.
In one case, we used mdftools to literally use the original excel spreadsheet as our logic engine.
reply