It's difficult to be very specific, because this was not a formal experiment.
I was using LLM collaboratively to help me setting up and document a home server. I was using DeepSeek for that matter. I tried some tasks on Claude Code and some on Pi.
Subjectively, I felt that it was marginally "smarter" on Claude Code. It would figure things out better, that sort of thing.
I am still using Pi btw. My current set up is using MiMo on Pi as a planner, ans DS in Claude Code to validate/execute the plan.
I may try moving it all to Pi, but I wonder if I should learn how to better configure the things there.
I like the Pi approach, but I think I didn't "hold it correctly" so to say.
I would like to migrate away from Claude Code and use Pi as my "peimary" harness. I really like in particular how it manages conversation trees and branches.
But I think I didn't do a good job in customizing it for my work. While nothing dramatic, I think the LLM I was using did a better job on Claude Code than on Pi a couple of time when I tried giving it the same work.
> We do not know whether subscription plans are unprofitable at all.
That's pretty much certain. It's sort of cute when people like to pretend otherwise.
> Many seem to confuse API prices with the actual cost to serve the models, and thus reach the conclusion that subscriptions must be deeply unprofitable.
I don't make that mistake. I actually suspect that the actual costs may be higher than the API prices. I think those may still be subsidized.
> Anthropic is officially citing capacity constraints with the intent to bring the Fable model back to subscriptions plans as soon as capacity allows.
Yeah, I don't think they are being truthful at all.
> I’ve done a number of interviews in my career. You don’t have to be a genius to see through the candidates who play this game where they tell you a perfectly sanitized, idyllic response that they’ve calculated as the optimal phrasing that you want to hear.
I worked in multiple companies in my multi-decade career, including FAANG (or whatever acronym is used now). I was even an intervewer for one of those
The people that give the sanitized calculated responses are actually what employers are typically looking for. It shows the candidate is willing to do the job without causing problems by confirming as a good worker bee.
Your workplace is not somewhere for real conversations.
Honestly, this is a criticism I agree with. I really would prefer if the EU councilor for my country was either voted for (or even indirectly picked by the EU parliament members for my country). At least this would ensure some sort of alignment with EU policies I care about.
The fact that the head of state is on EU council sort of sucks, because when I vote on national elections people are looking at internal issues, and EU policy is more of an afterthought.
But that doesn't align with morons claiming that those are "unelected officials" or that the EU is somehow undemocratic.
Problem is that you can't do a FOMO-fueled hype IPO that gets a trillion dollars if your argument is "this is a tool that can improve the quality of work your employees output".
It needs to be a "we are building a doomsday weapon here, give me money" argument. Even if it is false. Especially if it is false.
Europe is not a country. If you meant the EU, it is also not a country.
You are comparing the US to a bloc.
Each member state will likely take a different approach to independence from the US, and the bloc as a whole may offer some incentives in that direction.
One thing is for sure, any talk about independence from the US 10 years ago would be looked at with complete skepticism. People that said anything in that direction was looked at as a crank.
Now it is a much more palatable position. Change starts like that.
Will it hold? I can't tell. I think it will be very unlikely for things to go back to the previous state.
> I think those people are largely in your imagination.
Nope, they are in this very thread, complaining about "unelected" officials.
Initially I dismissed this as a product of ignorance, but they keep repeating the same bullshit after being corrected. It is clearly bad faith.
> You seem to be assuming a whole lot of dark motives or unsavoury opinions in reaction to people simply saying the EU is not perfect.
That is not the argument. The EU is far from perfect, and if that's the discussion, I wouls have a lot of things to say about it.
> but I wonder what your political leaning is, just to understand where this aggressive defense of the EU is coming from.
I tend to see myself as left of center, although I did drift further to the left over time.
I am not from the UK to describe myself in in the UK political spectrum, although looking from the outside I have the impression Labour is largely ineffective and Starmer is (was?) running the government pretty much as the tories would have.
I am also not French. My understanding is that for French standards Macron is center-right?
No complaints so far.