[echelon]

If you think about LLMs as new types of databases, it's quite obvious that they'll start winning over many types of legacy systems.

They ingest unstructured data, they have a natural query language, and they compress the data down into manageable sizes.

They might hallucinate, but there are mechanisms for dealing with that.

These won't destroy actual systems of record, but they will obsolete quite a lot of ingestion and search tools.

[int_19h]

LLMs don't make for a particularly good database, though. The "compression" isn't very efficient when you consider that e.g. the entirety of Wikipedia - with images! - is an order of magnitude smaller than a SOTA LLM. There are no known reliable mechanisms to deal with hallucinations, either.

So, no, LLMs aren't going to replace databases. They are going to replace query systems over those databases. Think more along the lines of Deep Research etc, just with internal classified data sources.

[msgodel]

Maybe query UIs but RAGs like Deep Research depend on old fashion query systems.

[int_19h]

You're right, "subsume" would be a better word here. Although vector search is also a thing that I feel should be in the AI bucket. Especially given that SOTA embedding models are increasingly based on general-purpose LLMs.

[ericmcer]

arent they complete trash as a database? "Show me people who have googled 'Homemade Bomb' in the last 30 days". For returning bulk data in a sane format it is terrible.

If their job was to process incoming data into a structured form I could see them being useful, but holy cow it will be expensive to in realtime run all the garbage they pick up via surveillance through an AI.

[andai]

Most LLMs I use would respond to this by writing a Python program to run the query.

[moomoo11]

And that program would be written different each time and sometimes fail.

[sshine]

...and the LLM, given an agentic loop, would ingest its own error message and correct itself...

...and eventually it'd persist some knowledge in a context window to not make that mistake for a while...

...and then it'd forget and make the same mistake again...

[moomoo11]

exactly