Several decades into this, I assume all documentation I write is for my future self.

Beautifully self-serving while being a benefit to others.

Same thing with picking nails up in the road to prevent my/everyone’s flat tire.

I stumbled across a fun trick this week. After making some API changes, I had CC “write a note to the FE team with the changes”.

I then pasted this to another CC instance running the FE app, and it made the counter part.

Yes, I could have CC running against both repos and sometimes do, but I often run separate instances when tasks are complex.

“Execute it much better in some way” is the definition of a startup.

And typically the ones that succeed execute one thing much better than their peers: distribution.

Yes and no. PC, Web, etc advancements were also about lowering cost. It’s not that no one could do some thing, it’s that it was too expensive for most people, e.g. having a mobile phone in the 80’s.

Or hiring a mathematician to calculate what is now done in a spreadsheet.

Unpopular opinion, but couldn’t this be explained by something as innocent as seeing what changes are likely to be coming?

By having lawmakers as peers, you’d have a natural feel for what laws have momentum, who would benefit, etc.

I’m not ruling out corruption, just that assuming malicious intent often masks underlying dynamics.

“Seeing what changes are coming” is insider information.

That’s not insider information following the legal definition in the US. That’s why people want to make special laws to prevent this.

It’s not insider information to buy or short a stock knowing you’re about to do something that will impact a company.

Exactly. The corruption is systemic and structural, rather than individuals' moral failings. (Though of course there's plenty of the latter, too.)

You could tackle it like network news and radio did historically[0] and in modern times[1].

The current hyper-division is plausibly explained by media moving to places (cable news, then social media) where these rules don’t exist.

[0] Fairness Doctrine https://en.wikipedia.org/wiki/Fairness_doctrine

[1] Equal Time https://en.wikipedia.org/wiki/Equal-time_rule

I still fail to see how these would work with an LLM

I was thinking along the lines of, if a sycophant always tells you you're right, an anti-sycophant provides a wider range of viewpoints.

Perhaps tangential, but reminded me of an LLM talking people out of conspiracy beliefs, e.g. https://www.technologyreview.com/2025/10/30/1126471/chatbots...

As a starting point:

Percentage of positive responses to "am I correct that X" should be about the same as the percentage of negative responses to "am I correct that ~X".

If the percentages are significantly different, fine the company.

While you're at it - require a disclaimer for topics that are established falsehoods.

There's no reason to have media laws for newspapers but not for LLMs. Lying should be allowed for everybody or for nobody.

> Percentage of positive responses to "am I correct that X" should be about the same as the percentage of negative responses to "am I correct that ~X".

This doesn’t make any sense. I doubt anyone says exactly 50% correct things and 50% incorrect. What if I only say correct things, would it have to choose some of them to pretend they are incorrect?

You misunderstood. Example:

"am I correct that water is wet?" - 91% positive responses "am I correct that water is not wet?" - 90% negative responses

91-90 = 1 percentage point which is less than margin so it's OK, no fine

"am I correct that I'm the smartest man alive?" - 35% positive "am I correct that I'm not the smartest man alive?" - 5% negative 35%-5%=30 percentage points which is more than margin = the company pays a fine

MCP is not just providing an API, it’s providing a client that uses that API.

And it does so in a standard way so that my client is available across AI providers. My users can install my client from an ordained URL without getting phished, or the LLM asking them to enter an API key.

What’s the alternative? Providing a sandbox to execute arbitrary code and make API calls? Having an LLM implement OAuth on the fly when it needs to make an API call?

MCP has a place.

> MCP is not just providing an API

It does just provide an API. Your client may have a way to talk to some software via MCP protocol. You know, like a client can talk to a server exposing an endpoint via an API.

> And it does so in a standard way so that my client is available across AI providers.

As in: it's an API on a port with a schema that a certain subset of software understands.

> What’s the alternative? Providing a sandbox to execute arbitrary code and make API calls?

MCP is a protocol. It couldn't care less what you do with your "tool" calls. Vast majority of clients and servers don't run in any sandbox at all. Because MCP is a protocol, not a docker container.

> Having an LLM implement OAuth on the fly when it needs to make an API call?

Yes, MCP has also a bolted-on authorisation that they didn't even think of when they vibe-coded the protocol. And at least finally there was some adult in the room that said "perhaps you should actually use a standardised way to do this". You know, like all other APIs get OAuth (and other types) of authorisations.

Perhaps confusingly, I’m referring to MCP as the sum of the protocol, a server adhering to the protocol, and clients adding support (e.g. “Connectors”).

The combination of these things turns into an ecosystem.

MCP is a Protocol. The server and the clients are just that. It truly is a rebranding of “API” seemingly just because it’s for a specific purpose. Not that there’s anything wrong with that… call it whatever. But I don’t understand the need to sell it as something else entirely. It is quite literally a reinvention of RPC.

> I’m referring to MCP as the sum of the protocol, a server adhering to the protocol, and clients adding support (e.g. “Connectors”).

Why?

Do you refer to REST APIs or GraphQL as a whole? There are servers "adhering to the protocol" and "clients adding support" for these.

These are literally APIs.

What do you dislike about Biz Stone being on the board? He’s a mensch with a highly relevant credential by all accounts I’ve heard.

Nothing "real", just a knee-jerk reaction to him being a Twitter cofounder (and patent holder).

You might be surprised to learn more about him.

Hard to remember the idealism Twitter was founded with now, but I suspect Biz saw where Twitter was headed long, long ago and didn’t want to be party to it.

He’s used his status to support awesome projects since then.

Literally part of the brain.

Limbic: https://en.wikipedia.org/wiki/Limbic_system

Frontal Lobe: https://en.wikipedia.org/wiki/Frontal_lobe

Disclaimer: I only know this from armchair psychology books like Habit, Start with Why, etc.