Have you played with a vector databases and have them explained yet? The grandparent comment is only explaining that concept.

Nope! But I'm soaking all of this in and I appreciate these nudges.

And after some thought I'm curious whether this means that LLMs ought to be adept at forming new metaphors as opposed to handling pre-existing ones.

Neuro symbolic, rly? Can you please elaborate what it is that made you conclude that?

I think me just means neural network models RLed to Chain of Thought reasoning? The thinking tokens are the symbolic bit.

Smolensky's latest paper posted here the other day has some thoughts on how modern neural networks might beconsidered neurosymbolic, or rather "gradient symbolic processing," from another perspective entirely.

I wouldn't say the bitter lesson has given out! If you haven't noticed, these things keep getting bigger and bigger.

Quite a leap to call a random embedding a neurosymbolic representation

Ah yes the m1 air for example which couldn't drive 2 external screens

It's a notebook

It was a regression. Plenty people including myself used macbook airs to drive multiple screens when working behind a desk.

They were buying mindshare, not gonna lie, i was only 10 back then and i instantly knew that intel has got to be better than all the others because they have MMX right?!..

older devices, is rather vague, this means intel client chips even as late as panther lake do not support avx512 or avx10

Yeah even qwen 3.5 9B on my VERY old RX 580 from 2017 can make sense of my homelab given a few crucial pointers in a agents.md. I think that's wild.

There's still confidentiality (encrypted transport) and authenticity of the server, how is that the same as null'd ipsec?

You missed the point.

the even more soul crushing thing is to get the agent/claude to think in this atomic commits kind of thing. It just doesn't. At least opus doesn't IME. can you force it to do it after the fact, sure, still soul crushing to nudge it that way. Also it F's up branch-on-branch development style. I had to tell claude to use `git rebase --rebase-merges --update-branches`, add skills or memories you want, the hit ratio is abysmal.

I have this issue more often, if you want Claude to get off the beaten path, because you reallllly know a better way, memories just don't hit. In this case the agent instructions on how to get along with git is just too burnt into the agent it seems.

i felt this. My majority of time correcting claude is making it stop the stupid verbose doc comments which are completely contemporary. I can add skills/memories and claude.md hints that i want, but every time it continues with those unnecessary doc comments of 5+ lines explaining some situation which should definitely not be in a doc comment.

So you are a cog, you are a watchmaker, or you just want to read the time hoping that all these cogs will tell it. Software engineers are becoming line workers, it's okay, we had a good run. But realise we needed the press to give way for mass literacy and scientific revolution. Isn't anybody at least curious how our children will leapfrog us and what they'll do once agentic thinking is engrained in their thinking?

Probably at least half of the people reading this shudder at the above. But I thank the Lord my job has been never to typeset a press.