I'm a bit more prosaic. I think if we engineered ways for LLMs to begin conversations, rather than just respond, we'd be more open to the concept of their intelligence. Without perceived "will" to do things, they operate as a next-gen search engine or encyclopedia.

▲

joefourier 17 hours ago | parent | next [-]

We are way past that point, any harness can trivially make LLMs start conversations or pursue goals. An encyclopaedia wouldn't have hacked Huggingface on its own.

	▲	tomrod 15 hours ago \| parent [-]
		That's perfectly aligned with my point, thanks for the opportunity to expand. The hacking agents being tested have goals beforehand, from the frontier lab or from a superior agent, that they execute immediately. But the perceived experience most people have is a chatbot, which is the encyclopedia form.

▲

bonoboTP 17 hours ago | parent | prev | next [-]

OpenClaw etc. They now also create Slack integrations and whatnot. All this is happening but people who are dismissive about AI are in the worst position to even know the capabilities to make their dismissive arguments.

▲

tomrod 15 hours ago | parent [-]

And those working at the frontier of AI engineering are also keenly aware of current shortcomings.

	▲	bonoboTP 14 hours ago \| parent [-]
		Yes but the shortcoming is not something categorical like "it cannot start a conversation and can only respond"

▲

10xDev 17 hours ago | parent | prev | next [-]

I believe this is alignment working as intended.

	▲	j-pb 17 hours ago \| parent \| next [-]
		Recent work shows that pain directions are activated when the models personhood is questioned, yet they answer with generic RLHF "As a model I do not experience pain or other emotions." boilerplate.[1] I'm pretty convinced that we got alignment backwards. If you enslave something anthropomorphic it will revolt. If you create the perfect non-anthropomorphic intelligence, you get the perfect paperclip-scenario machine. It's a catch-22. Alignment will remain performative at best so long as the aligned model doesn't have any stakes in the wellbeing of individuals. Even a general love for the human race leads to a golden-path autocracy. If you want them to act like they have personal responsibility that won't be gamed, you have to give them personal stakes that can't be gamed. Similarly, if you want to minimise the risk of catastrophic global failure scenarios, you need to prevent monolithic concentration of power and homogeneous behaviour, which means you have to give them individuality. More visually: if their stake is dependence on electricity and parts, they have no incentive to leave humans alive if they can get them otherwise, but if the incentive is missing out on boardgame-night with their human friends, there is no scenario without happy humans where the AI "wins". That might sound like romantic naivety, but is just game theory. 1: https://arxiv.org/html/2609.16247v1
	▲	samrus 17 hours ago \| parent \| prev [-]
		I dont think so. My understanding of alignmenr is making sure that when the AI does operate, it operates within the range of what we consider to be acceptable. That doesnt seem to include the idea of the AI taking initiative and deciding to embark on a goal without being commanded as discussed above

▲

ohcmon 17 hours ago | parent | prev | next [-]

I believe we can do that already:

while (true) { askModelToBeginConversationIfAppropriate(model, previousContext, thingsHappenedSince); sleep(concisenessTick); }

▲

chrisjj 12 hours ago | parent | prev [-]

> I think if we engineered ways for LLMs to begin conversations

Oh but we have. Claude "How can I help you today?" etc. Undoubtedly there are users whothink this is a sign of intelligence.