sharperguy

I can't find a Pi Zero 2 W for sale anywhere that will deliver to me

Free speech doesn't mean that we don't desire filters. Go check your gmail spam folder. Twitter would look identical to this with filters at all. What we really want is:

* transparency about the filters we have on our feeds

* the ability to tweak them if they're not working

* the ability to change providers without losing your entire social graph / reach

So in future we will have "retro" streaming platforms that buffer with the spinner a random times for nostalgia and have menus full of promotional material that are impossible to navigate to just find what you're looking for.

You're assuming a file containing a statistical model that exists on your hard drive has agency. It doesn't. You as the user have sole agency and what you use the statistic file for.

You could say it's more akin to if we have all been writing in a assembly and suddenly we got access to compilers and high level languages. Would we all be complaining that every conference is "about compilers"?

It's hard to avoid the topic when it literally redefines what it means to create software. If I'm using it to create some piece of software, then I turn around and say "I wrote this" am I even being truthful? But if I'm trying to avoid mentioning LLMs what other wording could I use?

I'm someone who makes extensive used of LLMs and agents for daily research, and I 100% of the time ignore the AI summary that google gives at the top of the page. If I am performing a web search, I've already decided that I'm explicitly NOT looking for an LLM summary.

I imagine something like 98% of articles also get less than 100 views. So the question is more about the articles you're reading rather than articles in general.

Much of the recent improvement in models is in being trained specifically to make use of the tools the harnesses give them.

I've switched to using traefik from caddy. For simple use cases it's a little more verbose in the configuration, but for more involved things like multiple load balancing backends, rewriting paths and headers and so on I've found it really good.

So I wonder, if a more powerful agent harness could have the agent basically write and exectute its own deteministic code, which when executed, spawns sub agents for each of the subtasks?

So far we've seen agents spawn subagents directly, but that still means leaving the final flow control to the non-deterministic orchestrator model, and so your case is a perfect example of where it would probably fail.

Both Arch and Nix solve this by making it very easy to write packages that work around the compatibility issues. When I used to use ubuntu and mint it was a lot more common to run into these types of issues.

Nobody is arguing it's guaranteed. This is why you never give an LLM access to any essential infrastructure. Make sure everything it does can be undone. Double check when guarantees are required.

Skills are often invoked imperatively by the user. In cases where they are intended to be used directly by the LLM, it would be included somewhere else in the context. E.g:

``` After implementing the feature, read the testing skill for instructions on how to test. ```

The personification seems to be at the training level. When I ask an LLM why it did something destructive, the ideal response would be a matter of fact evaluation of the mistakes that I myself have made in setting up the agent and it's environment, and how to prevent it from happening again. Instead the model itself has been trained to apologize and list exactly what it did wrong without any suggestions of how to actually prevent it in the future.

Water? You mean like out of the toilet?

A serious existential threat to the country from a targetable state actor.

It's actually common for human-written projects to go through an initial R&D phase where the first prototypes turn into spaghetti code and require a full rewrite. I haven't been through this myself with LLMs, but I wonder to what extent they could analyse the codebase, propose and then implement a better architecture based on the initial version.

only proves you're not a corporate model rather than locally running model that's been trained to allow saying that

You can have cryptographically signed data caches without the need for a blockchain. What a blockchain can add is the ability to say that a particular piece of data must have existed before a given date, by including the hash of that data somewhere in the chain.

The same politicians who claim to support the free market will do deals like ttis with corporate oligopolies to cement their position into eternity.

they used to publish a buildable AOSP tree for the device which is no longer the case

Still, it might be interesting information to have access to, as someone running the model? Normally we are reading the output trying to build an intuition for the kinds of patterns it outputs when it's hallucinating vs creating something that happens to align with reality. Adding in this could just help with that even when it isn't always correlated to reality itself.

Part of the issue with phones is that they are already controlled by the Google/Apple duopoly, and hence heavily optimized for constant distraction and addiction. These laws only cement that duopoly and provide fewer means to build more friendly platforms.

I've been hearing talk for years about a "web of trust" system, that could filter spam simply by having users vouch for eachother and filtering out anyone not vouched for. However, I haven't seen a function system based on this model yet.

Personally I'd love to add in something like the old slashdot comment model, where people would mark content as "helpful", "funny", "insightful", "controversial" etc, and based on how much you trust the people labeling it, you could have things filtered out, or brought forward.

I would even call it mid 2020s. I think in a couple years people's attention spans will be so short they won't even finish reading comments.

As a European it's hard for me to comprehend the influence that iMessage has on the US.

"But I came crawling back to iOS because I'm weak and the orange iPhone was pretty and the Pixel 10 was boring and I caved to the blue bubble pressure. But the keyboard on this beautiful phone is worse than ever. "

I don't understand. What could Apple possibly have that is better than a working device?

Tiktok will never have any competitors after this law comes into force. They will have the resources the implement the require changes, and the customer base will remain with them. Anyone starting a new service will have a tough time building something that jumps through all the hoops required by the EU, on top of the usual problems with network effects.

It's typically with this type of headline "X people are doing Y" means "at least 2 X people did Y".