Think of all that cheese.

But we already learned there is no cheese there, that’s why we never went back.

Thank you for this brother, well done

There might be pie on your face but they stole my line, https://github.com/HatmanStack/kill-wordpress

I think you need to account for the base rate. There's a lot of WordPress plugin vulnerability disclosures because there's a lot of WordPress plugins and there are enough deployments of the plugins to make searching for those vulnerabilities is worthwhile.

That site warns that WordPress plugins can be abandoned, but that's clearly not a WordPress specific issue. Sure some site could use SSG, but that's a different design.

I certainly don't want to claim WordPress security is good, but I'm not sure that site is measuring anything meaningful.

Just measured your visit, zing.

Seems crazy to me people aren't already including rules to prevent useless language in their system/project lvl CLAUDE.md.

As far as redundancy...it's quite useful according to recent research. Pulled from Gemini 3.1 "two main paradigms: generating redundant reasoning paths (self-consistency) and aggregating outputs from redundant models (ensembling)." Both have fresh papers written about their benefits.

There was also that one paper that had very noticeable benchmark improvements in non-thinking models by just writing the prompt twice. The same paper remarked how thinking models often repeat the relevant parts of the prompt, achieving the same effect.

Claude is already pretty light on flourishes in its answers, at least compared to most other SotA models. And for everything else it's not at all obvious to me which parts are useless. And benchmarking it is hard (as evidenced by this thread). I'd rather spend my time on something else

No such thing as junk DNA kinda applies here

I take the train to meet Neil Cassidy, still waiting, still trying.

The feed actually surfaced people working on open source projects adjacent to mine, that turned into real collaboration and shaped technical decisions I wouldn't have arrived at alone. It's not all good content, but it's a useful signal source for things outside your usual field of view.

Anybody know if NTSYNC support is why the Chrome OS team moved away from native Steam support?

For me, I just created my own prompt pipeline, with a nod towards GANs all of the necessary permissions get surfaced so I don't need to babysit it, and all are relatively simple. No need for Yolo or Dangerously setting Permissions.

Curious what you mean by "played both agents" and "faster and faster"? API calls are API Calls or are you running an open-source model locally?

Rephrasing of the post in case it's clearer:

"I would love to do something more sophisticated, but it's ironic that when I performed both of the duties done nowadays by agents, the development loop got faster and faster as computers got faster and faster."

For context and curiosity, are you using local inference? Which models?