AIUI Janus mostly uses their(?) Loom interface, which allows extremely fine-grained control over the outputs; in my experience using the less-powerful free chat interface, Claude tends to fall into similar failure modes as 4o when I ask it to flesh out my ideas, albeit to a lesser extent. It’ll often include things like calls to action, claims that the (minor and technical) points I want to make have far-reaching social implications of which we must be aware, etc (and is prone to injecting the perspective that AIs are definitely not conscious in response to prompts that did not include any instructions of that nature).
Loom is definitely far more powerful, but there are other (weaker) ways of steering the outputs toward specific parts of the latent space; things which often fall under the label of “prompt engineering”, which is very commonly broader than the usual usage of the term. Janus’ twitter feed, for example, has some examples of LLMs acting in ways that would, I think, be very strange to someone who’s only seen them act the way they do at the start of a conversation. (Not in being specifically better at the things you describe in those examples, but I think they’re similarly different from its usual style.)
AIUI Janus mostly uses their(?) Loom interface, which allows extremely fine-grained control over the outputs; in my experience using the less-powerful free chat interface, Claude tends to fall into similar failure modes as 4o when I ask it to flesh out my ideas, albeit to a lesser extent. It’ll often include things like calls to action, claims that the (minor and technical) points I want to make have far-reaching social implications of which we must be aware, etc (and is prone to injecting the perspective that AIs are definitely not conscious in response to prompts that did not include any instructions of that nature).
Loom is definitely far more powerful, but there are other (weaker) ways of steering the outputs toward specific parts of the latent space; things which often fall under the label of “prompt engineering”, which is very commonly broader than the usual usage of the term. Janus’ twitter feed, for example, has some examples of LLMs acting in ways that would, I think, be very strange to someone who’s only seen them act the way they do at the start of a conversation. (Not in being specifically better at the things you describe in those examples, but I think they’re similarly different from its usual style.)