What would an EV muscle car look like? Tesla Model 3 seems to check a lot of boxes. Definitely not noise or muscle car power delivery, but those seems like unrealistic goals for an EV
Truly appreciate the perspective. Any pointers to previous work on dealing with stochastic systems from the past? Part of my work is securing AI workloads, and it seems like losing determinism throws out a lot of assumptions in previously accepted approaches.
I read the full article (really resonated with it, fwiw), and I'm struggling to understand the issues you're describing.
> Yes of course relationship questions don’t have a “correct” answer. But physics questions do. Code vulnerability questions do. Math questions do. I mean seriously?
Can you say more? It seems to me the article says the same thing you are.
> I don’t actually think the above paragraph makes any sense, does anyone disagree with me? “Instead of planning we observe and hypothesize”?
I think the author is drawing a connection to the world of science, specifically quantum mechanics, where the best way to make progress has been to describe and test theories (as opposed to math where we have proofs). Though it's not a great analog since LLMs are not probabilistic in the same way quantum mechanics is.
In any case, I appreciated the article because it talks through a shift from deterministic to probabilistic systems that I've been seeing in my work.
You’re implying any real system can have a single top priority, which is equally false. There are always multiple priorities, and the one sitting at the top changes based on the context
> We really need better ways of measuring economic health.
What would that look like to you? It seems to me no single, measurable metric is going to tell you economic health. They're a bunch of indicators that need to be interpreted.
Do you think Iran will have nukes in the near (20 years, just to put a number) term? Your position really only makes sense if that's not the case. By whatever means, the goal now seems to be to prevent that.
I think this downplays the security issue. It's true that scoping the token correctly would prevent this exploit, but it's not a reasonable solution under the assumptions that are taken by the designers of MCP. LLM+MCP is intended to be ultra flexible, and requiring a new (differently scoped) token for each input is not flexible.
Perhaps you could have an allow/deny popup whenever the LLM wanted to interact with a service. But I think the end state there is presenting the user a bunch of metadata about the operation, which the user then needs to reason about. I don't know that's much better; those OAuth prompts are generally click throughs for users.
This makes a lot of sense to me. As an individual, how do I help move along the transition to smaller communities?
The answer cannot be ‘you can’t’. Certainly what you said resonates with a fair number of people, and it only takes a small community to create a small community, right?
I think the trouble is that most teams don’t need this level of performance. They don’t need the top .0001%. Those teams are the edge cases not even worth talking about.
And more importantly, not the ones you want to model your team after.
Nothing I don’t think. The average is of the two scores: attitude and aptitude. The average of the two must be at least 7.
Unless you’re taking about how each interviewer calibrates. In which case it’s common for interviewers to be coached on how to rate candidates. Your calibration indeed seems too harsh for this parents system
Some qualifiers would be helpful to engage with you. Certainly threat of punishment shouldn’t be the only motivator in a healthy society, but it probably needs to be one.