They more or less had to. The PDF foundation has added JXL into the standard. Even Google can't afford to not display PDFs properly. Including it in the rendering engine is then just the logical next step.

Yer I also use service with zero data retention promises but it is hard to really trust them for me... They trained on basically all of the existing material, legal or illegal already and are starved for true human input. They are also in a heavy arms race were basically only a handful of companies will survive.

Yes. Training is necessary to make an LLM. They don't grow on trees, you know.

Leaving this here: https://youtube.com/shorts/83X79cfuE3k

(yes, AI critique is now also made with AI. We have come full circle.)

Copied from myself above:

That goes against the philosophy of pi. Nearly Everything is a Plugin. Need to set the reasoning effort? Install pi-reasoning. Need subagents? Install pi-subagents. Need permission gating? Install one of the permission extensions (otherwise the agent can do everything).

A feature like cache warming on Anthrophic feels very strange in this environment. NOT saying that it is not useful. It just should be a plugin.

That's your philosophy of pi and it seems you are taking it from deepseek. It's stated that pi wants to keep the agent loop minimal, not the code around the harness. Also those extensions in pi can sometimes be very bad, as it depends on the maintainer. And when it comes to cache handling of the best frontier coding model, it's much better that pi itself maintains it rather than some rando online.

No I did not ask AI for this. This is the understanding I have from working with PI for a year.

They also say so on their website ( https://pi.dev/ ): "Pi ships with powerful defaults but skips features like sub-agents and plan mode. Ask Pi to build what you want, or install a package that does it your way."

I fully agree on the quality of the packages. Can vary quite a bit. I stick to very popular ones.

Changing the reasoning effort is built in and doesn't require a plugin.

Yer, that is my bad for not updating myself, sorry. I did miss the introduction of Alt + Tab or /thinking command for switching this.

Good thing I can remove another package.

Pi with Caveman Plugin :D

That goes against the philosophy of pi. Nearly Everything is a Plugin. Need to set the reasoning effort? Install pi-reasoning. Need subagents? Install pi-subagents. Need permission gating? Install one of the permission extensions (otherwise the agent can do everything).

A feature like cache warming on Anthrophic feels very strange in this environment. NOT saying that it is not useful. It just should be a plugin.

I wouldn't touch fields or canals. The US has incredible amounts of parking lots. They are also mostly built in very developed parts of the land with a lot of users for electric power in close proximity. And a parking lot is already "sealed ground". Might be less problematic to get a permit there?

Additional plus: cars don't heat up in the sun. And at some point you might even charge EVs there.

After reading through the threat here it seems more like a cultural thing. The US has quite a lot of filters for profanity. I remember from my youth that in 2009 Eminem was a guest in a Germany TV show and very happy to swear as much as possible without being censored. https://www.youtube.com/shorts/2OC-yKZ5Yag

Am I, with around 30, in this generation? Putting * in words seems like self censorship to me. Still, might have a cultural component. German here.

It can be used for in-jokey comedic effect. For example, referring to M*cr*sft W*nd*ws or Br*dc*m as though they were offensive terms. Or *r*cl*.

I'm in my 40s and * is self-censorship to me. It must be a cultural thing.

I also no longer trust benchmarks on this one. When the context gets a bit longer and the problem harder low quant models often produce worse output for me. Sometimes they even loop.

Interestingly different formats also often behave differently. GGUF unsloth is so far the best for me.