I've had the same idea for year. When google released their Fitbit Air few days ago I the first thing I tought was - can it be used as a sensor for weightlifitng and do they have API for that.
It is worse than that. People have been complaining for weeks and Anthropic’s message was basically “you are holding it wrong”. On top of that this misconfiguration somehow makes CC consume much more tokens. How believable is all that?
as soon they do that all kind of companies will start abusing it, for example the sound of all smart phone notification will use exactly that frequency
I think this could be very useful not when we talk to the agent, but when the agents talk back to us. Usually, they generate so much text that it becomes impossible to follow through. If we receive short, focused messages, the interaction will be much more efficient. This should be true for all conversational agents, not only coding agents.
This concept was very popular back in the days when computers used to boot from HDD, but now it doesn't make much sense. I wouldn't notice If my laptop boots for 5 sec instead of 10.
This is a very lame excuse. You can do 100 different things without compromising your shoulder. Try cardio. Or just wight lifting with very light weights. Or group classes.
I have tried Julia few times and each time this is what stops me. I don't understand why they decided to make indexes R-like oposed to "all other languages"-like. My brain just stops working when i need to recalculate indexes and each time I'm wrong.
Some people may not realize it, but when it comes to programming languages, ergonomics matter—a lot.
I’ll never get why people hype up Zed. Sublime Text already has all the same perks—and beats Zed at the very things it claims to improve. Sure, it might not have every advanced feature, but for “vibe coders” who don’t need a full IDE and just want to skim or tweak generated code, Sublime Text is the better choice.
I'm not sure I agree with this. 10x more tokens means leaaving the agent to work for 10x longer, which may lead to bugs and misintepretation of the intention. Breaking the goal into multiple tasks seems more efficient in terms of tokens and getting close to the desired goal. Of course this means more human involvment, but probably not 10x more.
There is no way for this to be true. I read his book about vibe coding and it is obvoius that it has significant LLM contribution. His blog posts though are funy and controversial, and have bad jokes, and he jumps from topic to topic. Ha has had this style like 10+ years before LLMs came around.
If i remember correctly Feynman said in one of his lectures that we know the mass of the electron with much greater precision than the proton, which may mean that it electrons are easier to study. I don't know if this is still true though.
I have quetion - slightly off topic, but related. I was wandering why is pyhton interpreter so much slower than V8 javascript interpreter when both javascript and python are dynamic interpreted languages.
Yes, but I suppose there shoudln't bee too many things happening in order to acknolege them, preferebly only the things in you mind.
I've been trying somithing similar, but more active - beach walks in the in the early eavning. there are still people there but not too many. my goal was to acknoledge everything and enjoy the moment. i was not quite successfull though, it was still too much for me to acheive tranquility :)