fnordsensei

I've been quite satisfied with Kagi[1]'s API.

1: https://kagi.com/api/docs/openapi

As a provider, I can add a tool or change instructions on my MCP server, and you'll get it on your next connection, sometimes even mid-session.

With a skill, updates depend on whatever channel delivered it to you. Whichever channel that is, it's out of my hands as a provider.

So, MCP solves the problem of coordinated distribution of updates to a larger subscriber base. Think inside of a company, for example. I don't have to go around and tell people to `git pull` their skills folder.

As far as I understand, quantum computing can cut it in half, to 128 effective bits. Still way too large to brute force from there.

I’m guessing that passing the tokens through the visual cortex doesn’t matter as much as how you engage with the content.

Right, I'm not saying that they would be regulated, but rather the provider of the instrument, and the market adoption of it.

Take the emotions he experienced after the event: "Who do I talk to, how do I undo this, what do I do" etc., and the fact that he's met with a wall of silence from Anthropic.

Perhaps there needs be more concerted preparation, guidance, direction and less trial and error for how society adopts it.

The imperfect comparison that sometimes comes up is to that of nuclear power, where international regulation and guidance quickly was adopted. I'm not necessarily endorsing the literal comparison, but an attitude of "well, let's just see how people choose to use nuclear power" would have yielded a significantly different world, I'm sure.

> he asks who is accountable when an AI agent causes autonomous damage

He is. On the other hand, when a tool of massive power becomes increasingly easy to use, it becomes increasingly easy to misuse, intentionally or not.

The question is if self-regulation is enough. Not that I necessarily trust legislators to know any better. But like we have observed from the world of agentic coding, sometimes two stupid things can behave as a unit of higher intelligence than the individual parts.

With the bare minimum of modern electronics. The dream.

While I hear you, I think AC is better centralized for the building, along with heat and water.

Yes, there are numerous reasons why this is harder to do than just doing it ad-hoc per apartment, but if we’re to see it as infrastructure, it should receive the same level of consideration as other utilities.

To be fair, this seems consistent with what they normally do, and arguably consistent with what their voters want.

It's cultural.

I've read that German society, for example, is largely based on contracts between the family unit and the state. Sweden, as a contrast, is largely based on contracts between individuals and the state.

As an example, Germany treats a married couple as a fiscal unit, Sweden abolished joint taxation in the 70s. Swedish parental leave is allocated per individual, and is mostly non-transferable.

In a lot of ways, individualism is produced by state contract in Sweden.

They could build them somewhere where people don't care. But you can't co-opt 70 years of public infrastructure investments out in the middle of nowhere.

And didn’t Genghis Khan more or less go to war with most of the known (and some of the unknown) world and for all intents and purposes win?

You'd probably want to be more precise regarding "important for what" as well. And the philosophical angle: if the person hadn't existed, would someone else have slotted in to take their place? Is the impact measured in years/decades, because the overall historical forces were heading in a direction anyway?

Is it like trying to say "the most important bacterium in a petri dish"?

Without diminishing the impact that Musk has had, I'm fairly certain that Musk isn't the answer. And either way, the intent of saying that Musk is the most important person in history I'm fairly certain wasn't a very grounded decision. I'm sure it was more an expression of reverence and fealty.

Whoever came up with the wheel, maybe? Perhaps someone carrying the original homo sapiens mutations?

I have a friend who unironically said "Elon Musk is the most important human who has ever lived"

Same here. The miniseries itself has its quirks and oddities, but I find it charming. Particularly his role as Merlin.

Well, kind of. This is the kind of problem that you might throw schemas (eg. Malli) at pre 1.13.

It’ll be nice to have it at hand in the base language though.

Yes, why not resolve it the same way all the others have done?

Say that Trump has weird elbows or something, Trump sues for defamation, they settle, bribe completed.

The people we should be genuinely scared of today are the ones that are looking at Britain's past and are thinking to themselves that colonization sure looks like a good idea that will work super well in modern times. Which not many actual Brits think.

Didn’t write “money”, wrote “resources”, but sure.

Yes, there’s a risk to releasing a product whenever you can be held accountable for that product. I understand that Apple seeks to be as unaccountable as possible.

So we ultimately agree with one another: Apple can do it, but doesn’t want to, for various reasons.

The point isn’t that it’s easy or straightforward to do. The point is that one of the world’s wealthiest companies can spare the resources needed to comply with the regulations of one of the world’s largest markets.

Right.

Meta’s biggest culture problem is definitely “not enough masculine energy”.

3.5 flash is listed as stable rather than preview, or am I misreading?

https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flas...

Step 1: put tariffs on coffee and bananas. Step 2: pump out CO2 until climate is appropriate for growing coffee and bananas. … Step n: Load profits onto your scavenged freight boat and try to find Dryland.

Is it more efficient though? It just looks like burning long term prospects for short term ones. Which is on brand with the current regime to be fair.

Planned economies don’t work great beyond small scopes.

The market does work, but it’s a giant paper clip AI and needs regulation in order to not turn everything into paper clips.

Wouldn’t it be accurate for that as well? Unless we change to base 10 time units or something. Then we all have a lot of work to do.

But if it’s just about starting over from 0 being the AI apocalypse or something, I’m sure it’ll be more manageable, and the fix could hopefully be done on a cave wall using a flint spear tip.

It’s a canned tuning mechanism to force the model to change track and align with the user.

It’s not so much a message to you as a message to the model from itself.

Same, but it’s a PITA when you also want to support tool calling at the same time. Had to do a double call: call and check if it will use tools. If not, call again and force the use of the (now injected) return schema tool.

I think you’re after something other than immutability then.

You’re allowed to rebind a var defined within a loop, it doesn’t mean that you can’t hang on to the old value if you need to.

With mutability, you actively can’t hang on to the old value, it’ll change under your feet.

Maybe it makes more sense if you think about it like tail recursion: you call a function and do some calculations, and then you call the same function again, but with new args.

This is allowed, and not the same as hammering a variable in place.