superturkey650

I think he’s saying that’s it’s dense and _too_ full of meaning. So, while terse, it can also hide extra meaning in its density.

No, but MCPs aren’t free to build either. So if you need to build an API on top, why would you build an MCP instead of using one of the existing standards that both LLMs and humans already know how to work with?

But the agent harness is still handling the session token for you either way. MCP might be an easy way for agent harness creators to abstract the issue away, but I don’t want to lose all REST conventions just to make it a little easier for them to write an agent harness.

It makes it harder for the LLM to understand what’s going on, not easier.

All MCP adds is a session token. How is that not already a solved problem?

Isn’t that point of design docs and not the commit log?

Yup. I’ve been using CLIs with skills that define some common workflows I use and then just tell Claude to use —help for understanding how to use it. Works perfectly and I end up writing the documentation in a way that I would for any other developer.

How do you manage auth for services that use OAuth?

I’ve been wrapping the agent’s curl calls in a small cli that handles the auth but I’m wondering if other people have come up with something lighter/more portable.

This is what I’ve been doing too. Give the LLM a link to an OAS for an API and let it use curl for everything after that. I don’t even wrap the API or use restish all, the LLM knows how to use curl well enough.

This lets me add quick skills that are essentially just: “this is the OAS link, this is how you store and use the authorization, this is when I want you to use it”. That combined with pointing it at the documentation for common workflows and usage examples, and it’s been great.

The only thing I’ve had trouble with is auth really. MCPs are treated as first class citizens by most model provider’s agents and trying to provide a shell-based alternative for hiding the secret credentials from the LLM has been difficult.

But _T_wo is also before _F_our

Why can’t he discriminate on political affiliation?

I don’t believe you’re being against a specific person, so you don’t have a 1-1 incentive based on the bet you’re placing.

My cattle dog will be begging for food and giving me all the looks that she's hungry, but if I put a bowl of food down and then grabbed a ball she wouldn't give the bowl a second glance. I can't even give her a treat for bringing the ball back and dropping it, she's too focused on the ball. As soon as I put the ball away, she'll do anything I want for the treat. I think she considers the ball her job and it overrides anything else.

I think the most likely case is that electricity prices go down but demand goes up as devices more eagerly use power so you end up with an electricity bill that stays consistent.

Children of Time by Adrian Tchaikovsky explores exactly this, though less lost and more accidental exalter.

Isn’t that what government grants essentially already are?

Depends on if the computer programs might respond in an interesting way or if my comment might help them respond in an interesting way in the future. Same as when interacting with humans, I guess.

The biggest cause of regime change seems to be the succession of power and the fears around change occurring during succession of power. A ruler dying through old age is a common source of regime change in history as people with varying interests start vying for that position and ensuring the new ruler holds their same interests.

It also seems to remove my ability to contextualize things which means I can't find flaws in my understanding of something as easily. This works for both good/euphoric things, where I feel like I know something (but really I can't find the flaws in my reasoning), and for bad/anxiety things, where I can feel really bad and spiral on something because I get focused on one particularly bad aspect and can't see the full picture.

I feel like this is why drugs can sometimes help with creative things, especially if you're familiar with the drug, as long as you can harness this decontextualization to put more of your focus on one thing, kind of like clearing your mind. However, its usually fruitless/harmful in anything requiring complex reasoning/judgement because it is reducing your ability to see the big picture.

I don’t think it’s a very valid concern, but LLMs can already do a limited level of reasoning to create information not directly loaded into them. Sometimes that reasoning is even correct! The idea here would be that even if you didn’t load that kind of information into them, at a certain level of advancement, they can determine the necessary plans from other information that has been loaded into them.

Not who you’re replying to, but that’s what I have been doing for about 15 years now.

This is for how visible the solar panels are to people, not for how much sun they will get.

They’re empowered to regulate the instruments and compounds used within medical procedures though.

Why do you say there is a finite amount of work needed? There might be, at any one time, a finite amount of work someone is willing to pay x > 0 dollars for, but as x goes to 0 I’d intuitively think the amount of work increases indefinitely.

I made a similar mistake with AWS where I have $0.50 monthly charge. I called and they want me to go through a lengthy processes including getting documents notarized to handle it. So instead, I just canceled the card and am patiently waiting for them to shut down the account from failed charges. It’s been about a year now though and it’s still going.

It’s not irrelevant as a ratio. 2.5 billion to 8 billion is very comparable to 500k to 1.7 million. The population tripled in 70 years and, in the current times, you also have to deal with all the existing architecture and infrastructure in the city that wasn’t built for anywhere near that population level.

I agree, and I am not saying that AI should be unregulated. At the point the government started regulating flight, the concept of an airplane had existed for decades. My point is that until something actually exists, you don’t know what regulations should be in place.

There should be regulations on existing products (and similar products released later) as they exist and you know what you’re applying regulations to.

> If you wait until a new technology definitively exists to start caring about safety, you have guaranteed it will be unsafe.

I don’t get this perspective. The first planes, cars, computers, etc. weren’t initially made with safety in mind. They were all regulated after the fact and successfully made safer.

How can you even design safety into something if it doesn’t exist yet? You’d have ended up with a plane where everyone sat on the wings with a parachute strapped on if you designed them with safety first instead of letting them evolve naturally and regulating the resulting designs.

Most people don’t rely on ChatGPT for production work flows like they do for GitHub. Of course users are going to have different expectations for different services.

Just reading this comment made my lungs feel constricted and caused a subconscious deep breath to fill them up.

Bigger groups of people allow for better economies of scale and allow for a wider variety of businesses and interests to be catered to.