News for hackers. Stuff that matters.
Re:Bloom Filters by londons_explore on Friday May 02, 2025 @05:19AM (#43867695)
A whole load of data structures, like bloom filters, are 'efficiency tricks'.

For example, "check if we might have Mr Smith's data cached by looking in this bloom filter". As Long as the answer is usually right, that's good enough.

I do wonder if in the future we'll use a mini online-trained AI to achieve the same thing. "Ask the AI if we have MR Smiths data cached".

Rather like you might ask an office clerk "Is Mr smith that troublesome customer you were dealing with last week? Do you still have his file on your desk?"

Re:Bloom Filters by nkrisc on Friday May 02, 2025 @06:30AM (#43868053)
Why would that be better than a bloom filter (or similar)?
Re:Bloom Filters by chupy on Friday May 02, 2025 @10:46AM (#43870557)
Because it has AI in it's name /s
Re:Bloom Filters by esafak on Friday May 02, 2025 @09:25AM (#43869433)
The way that would work is that the LLM would translate that sentence into a tool call, which would query a data store that does the heavy lifting. Also, there is an ML task called "Learning to hash", which is about optimizing the hash for the task: https://learning2hash.github.io/
Re:Bloom Filters by ozgrakkurt on Friday May 02, 2025 @10:40AM (#43870452)
There are actually “learned” bloom filters if anyone is interested in machine learning/bloom filter relation. but it is not related to chatbots
Re:Bloom Filters by hinkley on Saturday May 03, 2025 @03:21PM (#43881408)
I would imagine a heuristic to keep enough of the filter in L2 cache to avoid pipeline stalls might be useful. Sort of a double bloom, but weighted for common lookups.