Joeri

The vanilla advantage is also there in a pure client-side pwa. Arguably it’s even bigger, because the bundle size ends up way smaller and the agent needs to hold less in context.

Plus all the other vanilla advantages: fewer dependencies, lower maintenance, less retraining, etc…

I still don’t get why apple chooses to devalue their brand so much for so little additional revenue. They’re a luxury goods brand, their whole revenue model is based on the appearance of quality.

Those “small” models take up 25 gb. On an entry level mac that’s a double digit percentage of available space. It is very rude of apple to claim that much space in an OS upgrade and offer no easy way to get it back.

If you’re logged in you get wildly different results from someone else’s. I have turned off history on my google account to make it give me a “neutral” search result, but it still seems to take a lot of info like my location, language and device type into account.

I wonder if they actually broke a law. The CFAA requires knowledge and intent to be present for criminal liability for hacking, and if we have to believe OpenAI they had no knowledge and did not intend.

At a minimum I would expect an FBI investigation, but given that the US government is right now a failed state I’m assuming no such investigation will happen.

Cybercrime legislation in other countries might not require intent, and then I would hope to see some prosecutions. OpenAI has clearly been negligent, and this negligence is causing harm in the world. Someone should be fined or jailed for this.

We got Opus 5.5 just a few days ago so haven’t had time to learn its ways, and Fable was/is too expensive for many people including myself. Insiders have months to learn the ins and outs of new models.

It would be nice if with new model releases claude code also gave a bit of a model 101 that tells you evolving ways of prompting it that the insiders have picked up. I know there’s the prompting guide in the claude docs, but this is often very broad and most people don’t know about it.

Even aside from how aligned the plan is with us, what about how aligned we are with the plan?

I’m always intrigued by the duality and conflict of “I have free will and must choose to act the right way” and “God has a plan so everything will be alright”.

Either free will allows us to deviate from the plan, or the plan will always be carried out and free will doesn’t really matter in the end. Arguing for God’s plan as the thing that will save us is eerily similar to nihilism, because they’re really arguing none of our actions truly matter.

There are companies where the CEO reports to the board, and there are companies where the board exists to keep up appearances. We’re finding out in real time Automattic is the second kind.

This should discourage investors, since an unbridled CEO is bad for them in the long term. But it won’t, because nobody thinks long term anymore.

My experience with opus 5 is that its results are lower quality in dutch, but that its dutch is more readable than its english.

The web’s ad markets bake in a loss of privacy by design, and so every website that wants to participate in those ad markets has to dupe as many users as possible into handing away their privacy. Couple that with declining web ad revenues because of the move to mobile apps, and you get a web filled with malicious compliance cookie banners.

Had google offered a privacy-preserving ad model (basing the ads off the content of the page instead of who the user is) things would be very different.

Why would they? Unless they have lots of unused tpu real estate that they could host it on “for free” they would be bumping more profitable workloads off of machines to give away that capacity to people with zero long term loyalty. There is no business reason for google to subsidize these models.

OpenAI has too much money. They’re spending their money in stupid ways.

For running it in yolo mode I set it up in a devcontainer. It takes a bit of figuring out, but once set up the permission prompts go away and claude has no access to anything I haven’t explicitly added to the devcontainer (unless it hacks its way out).

At one point I ran graphical linux on a 20 mb ram laptop although admittedly that was very tight.

I also remember running nt4 with photoshop, word, and my IDE (borland delphi) all at the same time and comfortably in 128 mb of ram.