Token based extraction around the @ is definitely one way that can work with a few tweaks.

This looks nice.

Can a successor for Wordpres shave some amount or type of import, conversion, or backwards compatibility?

Can there. ba way to tie in wordpress plugins or their functionality through a secure interface/translation layer?

Adoption for new projects is one thing, migration is another.

There's some cms that pretty much build in some core amount of main plugins right into the core cms.

Clever architecture often can still beat clever programming.

Non-exact software will be causing sleepless nights for non-exact legal writers.

Asking a non deterministic software to act like a deterministic one (regex) can be a significantly higher use of tokens/compute for no benefit.

Some things will be much better with inference, others won’t be.

Asking the LLM better will return better than average and bland and mainstream results.

How does one ask better? Does better vary per model?

Yes, its context based.

It's like asking a coworker. Providing too little information, or too much context can give different responses.

Try asking the model to not provide it's most common or average answer.

Been using it this way for 2, almost 3 years.

Why would they return "better" results?

Because AI is not a search engine. It does not return the best search result every time.

What it considers best, is what occurs most often, which can be the most average answers. Unless the service is tuned for search (perplexity, or google itself for example), others will not provide as complete an answer.

How well we ask can make all the difference. It's like asking a coworker. Providing too little information, or too much context can give different responses.

Try asking the model to not provide it's most common or average answer.

Been using it this way for 2, almost 3 years.

Reminds me of a Pentium Pro router put into a datacenter, two 2GB mirrored scsi drives, two nics, happily running a hardened pfSense, ran with zero issues for the better part of a decade.

It just wouldn't die.

The suspicion was because the electricity going to it cleaner than average, in a datacenter, the normal wear and tear on electronics may have been reduced.

Respect was paid at it's decommissioning to convert it into a vm, knowing it's luck, chances are it would still boot up and keep on running.

It is much, much easier than it used to be. The documentation and videos alone available make something like this a very welcoming learning experience that anyone can complete step by step by pausing a video and replaying it.

Like most things, really. I used to build routers from old PCs, but eventually those tiny appliances caught up with the performance/functionality I need.

You can do a lot of routing on a $70 Mikrotik, although they might not be "easy".

I really want to end up with one of these for at least a few months: https://mikrotik.com/product/rds2216

At $2k out the door that's way more reasonable than I thought it'd be.

Too bad I can't fill it with old spinning rust.

And no (mention of) ECC.

On printed page five of the brochure [0] it mentions

  Size of RAM   32 GB ECC
  RAM type      DDR4

On the one hand, it'd be nice if that was mentioned everywhere that the RAM size was mentioned. On the other hand, perhaps ECC RAM is effectively mandatory for Enterprise equipment, so mentioning it is redundant? IDK, I don't often purchase that sort of stuff.

[0] <https://cdn.mikrotik.com/web-assets/product_files/RDS2216-2X...>

For sure, it's a path and passage towards devices like that.

Everyone has a starting point, starting with soemone has lying around is one thing.. the quicker they can get going the more they can get to leveraging the real power in most devices.

This was a pleasant surprise to enjoy, I was surprised to discover a font I wasn’t aware of.

Seeing all the fonts listed here it would be great to be able to add user submissions into the mix.