Hacker Newsnew | past | comments | ask | show | jobs | submit | adamgordonbell's commentslogin

What makes prompts like 'you are a book researcher' an agent?

Isn't this just some loops and joining with some changes in prompts?

Can't you write this in a for loop calling the open AI API directly?


Yes. Calling prompts in a for loop is what makes an agent. Usually tool calls are also involved.

> simultaneously extremely similar to and extremely different

yeah, I don't understand the change tbh.

It's said Eric Heisserer spent years and years on the screenplay so I'm assuming he couldn't sell the original version. But it's a bit like making fight club and removing the big reveal. It ends up feeling the same, but not having the same impact and meaning almost the opposite.


Also this:

> The best reason to take multiple life extension supplements is to hedge our bets, because we really don’t know which of them are effective in humans.

And earlier:

> Personally, I take large doses of rapamycin 2 days a week, 8 weeks per year. For personalized recommendations, you can consult your favorite life extension doc.


I recently saw a patient with overwhelming MRSA sepsis with multiple foci of infection including epidural abscess (around the spinal cord), and meningitis. This person was taking rapamycin presumably for "life extension" purposes. Almost certainly the immunosuppression from the rapamycin made the infection much worse.

I'd be very wary of taking an immunosuppressive drug as an otherwise healthy person for theoretical life extension properties.


Don't come and spoil our nice individualism with populational effects, you filthy rationalist !

What was the dose and frequency? I bet it was rather high. Or do you really think that 1 mg once per week will suppress the immune system?

Rapamycin modulates the immune system. I get that he's probably consulting a doctor but can you imagine taking this risk during a pandemic or even in older age? It makes me uncomfortable to play around with these very powerful drugs.

The dosage for longevity is supposed to be low enough that this risk is minimized. Lots of things you do modulate your immune system (including e.g. exercise). It's a risk/reward thing, every time you get into your car you're also taking a longevity risk.

I think there are some proper human trials happening but the jury is still out.


> I think there are some proper human trials happening but the jury is still out.

That's exactly my point. No one really knows the risk that they are taking.


People are still getting nerve damage from too much vitamin B6 in energy drinks and vitamin supplements, and that's a well known and widely taken vitamin. The idea that you can take experimental drugs your entire life at little risk is optimistic.

I had no idea. At points in my life I consumed a lot of nutritional yeast.

Surprisingly, many people seem to think that pushing a few random pills into a machine optimized over some million years of evolution will tune it so it works better. Go figure...

It works for the majority of modern medicine, so it's not all that black and white.

Yes, although even for modern medicine curative and preventative strategies are very distinct. Sure, they'll give you pills to compensate for a problem you already have. But there are few meds that protect you against stuff you'll maybe catch in the future. Vaccines and antibiotics are obvious examples, but I'm not aware of many others. The rest of preventative strategies overwhelmingly consists in correcting deficits or excesses (calories, vitamins, sleep, exercise etc.)

These roads people go down always arrive at eating collidal silver...

Get with the times, methylene blue is the new it girl.

As a party trick, it'll make people pee blue. But don't do this, it isn't safe. Especially without consent

How to hedge a bet 101:

1.you bet on risky stuff using something of value (money, health,...)

2.since you're unsure whether your bet will pay off, you bet some more on some other risky stuff, just to be sure.

BTW if you were wondering, of course all those proposed weird life-prolonging treatments are totally devoid of side-effects.


Never put 100% of your savings into a single slot machine. Take 10% of your savings to 10 different casinos and distribute them to 10 slot machines in each, in order to hedge.

Oh there's plenty of people selling "side effect free" life extension supplements. But there's another name for side effect free medication: effect free.

Not doubting all this, but the possum thing is interesting.

They were in southern ontario in my youth in essex county ( late 80s ). And google says they were reports as far back as the 60s of scattered sightings.


You seem to be suggesting he's writing from a place of not knowing about the benefits of one-on-one learning and the "two sigma problem" when this is something he frequently writes about.

My understanding is Math Academy is like combining anki with direct instruction.

It's a business premised on teaching people things faster by understanding research around learning.

If the math it teaches is the math you need or want to learn, its likely an efficient way to learn it.

So, you are paying for efficiency. Like using Pimsleur rather than spending a year in France.


You can do that manually. Say for example you learn integration by trig sub today and you do 30 problems from a book. Next week you do some more trig sub problems. Then 2-3 weeks after that you do some trig sub problems and then in a few months you do some. You can do spaced rep manually. Is mathacademy more efficient? I don't know. It's too early to say. But what I do know is millions of people have learned mathematics with books, pen and paper for hundreds of years.

> You can do that manually.

Absolutely. You can spend time on figuring out what to do next, and how, and how to do spaced repetition for the material and test yourself effectively. There are aspects you'll do better than a set curriculum because you understand yourself, and there are mistakes you'll make because misunderstandings and errors.

Or you can pay an expert to do that for you, and just use the time on learning.


You think the tariffs will hurt people you don't like in your country ( those from Ontario and Quebec) more than yourself so you are in favor of them?

Patriotic of you.


I think it is worth it if it stops the bad policy of supply management that harms everyone except a small group of farmers. Quebec and to a lesser extent Ontario being full of wankers is why we have supply management when it is obviously stupid, not who will be hurt by tariffs (although they will hurt from the tariffs and they have earned it, unlike the rest of us who are hurt by the same tariffs)

I can agree about the odd supply management rules.

People use it in much smaller dosages then it's usually prescribed to apparently beneficial effect.

I believe its also in the water supply in certain places, so if it works for dementia there are natural experiments already running on this.

https://www.psychiatrictimes.com/view/low-dose-lithium-a-new...


Yes, it's already thought that there's an association between naturally occurring lithium in drinking water and decreased suicide rates:

https://www.cambridge.org/core/journals/the-british-journal-...

I would think naturally occurring lithium in some people's water would give pretty good control conditions to do a wide study of this effect on Alzheimers as well?


(for others like myself)

Results

The literature search identified 415 articles; of these, 15 ecological studies were included in the synthesis. The random-effects meta-analysis showed a consistent protective (or inverse) association between lithium levels/concentration in publicly available drinking water and total (pooled β = −0.27, 95% CI −0.47 to −0.08; P = 0.006, I2 = 83.3%), male (pooled β = −0.26, 95% CI −0.56 to 0.03; P = 0.08, I2 = 91.9%) and female (pooled β = −0.13, 95% CI −0.24 to −0.02; P = 0.03, I2 = 28.5%) suicide mortality rates. A similar protective association was observed in the six studies included in the narrative synthesis, and subgroup meta-analyses based on the higher/lower suicide mortality rates and lithium levels/concentration.



The addition of flouride to tap water supply likely affects brain development. Let's not go adding lithium too.

These things are simple enough to advise the populace to use on their own. The government should never play nanny, ever.


Is advising people to wear sunscreen and not speed also nannying? If the government ultimately bears the costs of poor health of citizens, why shouldnt they embark on public health interventions to lower those costs.

The government should not be bearing that cost. It is idiotic to ever put the state in charge of people's health.

This is fascinating, thank you.

Wow, small world, I just made a podcast episode about the dangers of turning your brain off when using Agentic coding solution and referenced the whispering earring as my metaphor.

I feel like if you use the agentic tools to become more ambitious the you'll probably be fine. But if you just work at a feature factory where you crank out things as fast as you can AI coding is going to eat your brain.

Link: https://corecursive.com/red-queen-coding/#the-whispering-ear...


I recall him mentioning ( thought maybe it didn't make the cut ) that he would be supporting sqlite into his 90s.

That he was contractually obligated to do so, and that he kept that in mind, probably effects his attitude towards shipping certain things.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: