SGML (ISO 8879), the markup meta-language on which HTML is based, has that, as well as many other things, such as type-checked templating.
Hence HTML as a mere vocabulary making use of SGML's facilities didn't need to define its own ad-hoc mechanism.
Btw the construct is also derived from SGML. In SGML terms it's a "processing instruction" rather than an "entity reference", the latter being the basic means for content inclusion.
Tried this (a CSS renderer specifically) two years ago, but the LLMs at the time weren't up to it and would either pull-in external libs or tell me "it's a very complex task" and generate a mere skeleton for a simplistic case of default layout.
Postgres does have pg_fts (tsvector/tsquery/tsrank) which is a quite sophisticated full text search package integrated with functional indexing and query optimization. Why would I use something vibecoded that isn't part of core Postgres instead?
Yes it's bad and it'll only get worse but how about thinking positive and towards ways out of the crisis? If your problem is with social media specifically, you could join the Fediverse (Mastodon, Piefed/Lemmy and co.) which while not perfect by any means is a bit more resilient and can be used to continue participating in niche interests while avoiding tribalism, doom, and propaganda.
If you mean letting an LLM generate code for a Prolog planner from an English problem description, that has been done successfully already with last year's models eg [1].
Appreciate the link! That is not what I had in mind though; for them, the Prolog Code is the goal, for me, Prolog is an interface language within a system I build. That code could be generated on the fly, but I lean more towards fixed templates that can be instantiated by input some variables by the LLM that is doing agentic code, rather than having that LLM reproducing that query code completely on the flow.
The reasoning behind it is that I want to put as much logic as possible into the harness where it is deterministic, controled and fast - My goal is to make agentic coding usable for my purposes even with small local LLM models. Those might botcher generating Prolog queries sometimes, but they might might be able to used my API/interface/whatever reliably (and then the harness does everything else under the hood, including instantiating the Prolog templates and running the queries)
Hence HTML as a mere vocabulary making use of SGML's facilities didn't need to define its own ad-hoc mechanism.
Btw the construct is also derived from SGML. In SGML terms it's a "processing instruction" rather than an "entity reference", the latter being the basic means for content inclusion.
reply