Re:Hybrid Reasoning Agents: LLM agents that think in latent ...
by unsnap_biceps on Sunday October 18, 2026 @06:50PM
(#50146307)
I agree with you but our current understanding of the biological brain is pretty much an organic neural network. What's the thing that actually differentiates the two and makes a neural network not thought but our brain is? I don't know.
[ Parent
| on HN ]
Re:Hybrid Reasoning Agents: LLM agents that think in latent ...
by emkoemko on Sunday October 18, 2026 @07:51PM
(#50146720)
i can give you a random number between 1 and 10, mean while all the LLM's will say 7 every time... because they are language models that look like they can reason and "think"
Re:Hybrid Reasoning Agents: LLM agents that think in latent ...
by AspireOne on Sunday October 18, 2026 @08:26PM
(#50146946)
There's no "every time" for a LLM. It's weights are frozen. You're asking it for the first time, again and again.
A human will also say 7 disproportionately often. Clearly, our output is statistically constrained and we don't actually think, right?
... Besides, how do you even make the jump from "LLM picks 7 when asked for a number between 1-10" to "llms don't think"?
Just... Nothing actually makes sense in what you're saying. You didn't define "think", you didn't actually make an argument, you didn't present evidence, there's just nothing but empty words.
Re:Hybrid Reasoning Agents: LLM agents that think in latent ...
by BoggleOhYeah on Sunday October 18, 2026 @08:23PM
(#50146932)
>our current understanding of the biological brain is pretty much an organic neural network
This is just plainly wrong.
Re:Hybrid Reasoning Agents: LLM agents that think in latent ...
by unsnap_biceps on Sunday October 18, 2026 @08:26PM
(#50146950)
So what is correct?