It depends on the task but I have different Claude commands that have this role, usually I launch them from the same session. The command has the goal of doing an analysis and generating a md file that I can execute with a specific command and the md as parameter. It works quite well. The generated file is a thorough analysis of hundred of lines with specific coded content. It’s more precise that my few line prompt and help Claude stay on rails
Every time Claude Code finishes a task, I plan a full review of its own task with a very detailed plan and it catches itself many things it didn’t see before. It works well and it’s part of the process of refinement. We all know it’s almost never 100% hit of the first try on big chunks of code generated.
I thought it was the same thing until I tried it myself, especially in dark rooms. Having the light from my phone hurt my eyes after reading with an ereader. It’s a really huge difference
I bought an android ereader and I read books and read articles instead of doomscrolling. Being Android and accessing raindrop makes me spend more time with it instead of using back my phone and opening social media
I second that, trust is broken if there is ads. The line of great ads to weird ads to pushy-borderline-scam ads into personal context is thin.
Hopefully the price of local will go down and maybe apple will be able to push most of it on-device.
The day chatGPT push ads in a conversation I stop using it.
The thing is with llm, it went so fast to get that many users, it means people are used to adopt new stuff as well. With proper marketing and specific feature I won’t be surprised to see people switch service as easily they start using it in the first place because the barrier is so low.
The worse thing is the companies behind those tools know it, they know it’s not reliable and it looks like they want to build a world where a majority of people won’t check sources anymore and blindly trust the LLM as authority. I fear that, by a tour de force of some kind, they’ll shield themselves from giving any source is the future in the name of « intelligence ». What will happen in the next generations where young that have grown up only with LLM giving them answers they saw as truth and older generations died? What a different world it will be.
Massive amounts of people with unsustainable lifestyle will stop consuming stuff. How will the whole capitalist economy continue to function with massive amounts of medium-high income people not having the same income anymore ?
I fail to see features that default iOS calendar app already has. The UI seems really simple and there is dozens of amazing calendar apps that have been on the market for 10+ years of features in this price range.
Our problem is not coding. Our problem is knowledge. If no one reads it and no one knows how it works and that’s what the company wants because we need to ship fast then the company doesn’t understand what software is all about.
Code is a language, we write stories that makes a lot of sense and has consequences. If the companies does not care that humans need to know and decide in details the story and how it’s written then let it accept the consequence of a sttastistically generated story with no human supervision. Let it trust the statistics when there will be a bug and no one knows how it works because no one read it and no one is there anymore to debug.
We’ll see in the end if it’s cheaper to let the code be written and only understood by statistical algorithms.
Otherwise, just work differently instead of generating thousand of loc, it’s your responsibility to review and understand no matter how long it takes.
Maybe it’s time to ask deeper questions, ask how to reduce complexity while preserving meaning. Doing real pair programming with shared remote code and simulate as much as possible a real day-to-day environment. Not all companies search for the same kind of developers. Some don’t really care about the person as long as the tech skills are there. Some don’t look for the brightest in favor of a better cultural match with the team.
Genuine remote interviews aren’t easy but it also depends on the interviewer’s skills.
We’ve been touted for year that AI will replace developers, would Elon replace the engineers working on the software of it’s rockets with AI ? It depends what’s at stake. I bet their interviews are quite specific and researched thoroughly.
We can find better ways to create a real connexion in the interviews and still make sure the tech skills are sound without leet code.
We also need developers who master the use of AI and have real skills of thinking before and designing and deep review code skills
Usually YT channels are per creator so it’s usually the same vein of content. But TV has channels from many sources and it’s a manually curated list of content.
I was referring to the same way of aggregating content. TV is old and we don’t need a 1 month program of planned content I guess because everything is on-demand but still. Being able to make a specialty like curated channel and share it to watch it like TV might be a thing.
Maybe a business/layer would be needed (if that doesn’t exist yet) that pick « best quality » content and provide a curated list as a channel ? YouTube is just the whole catalog. I would definitely like that, channels and curated content from YouTube because I lost so much time finding great content sometimes that it’s sad.
No I got the question, I said that I wanted to see what kind of explanation it would give me. Ofc it can hallucinate that explanation as well. The bottom line is I don’t trust it, and the source link are fake (and not broken or obsolete)
I don’t trust it at all. I wanted to know if he would be able to explain its own results.
Just because it was displaying sources and links made me trust it until I checked and was horrified.
I wanted to know if it was old link that broke or changed but no apparently
I used perplexity for searches and I clicked on all sources that were given. Depending on the model used from 100% to 20% of the urls I tested did not exist. I kept on querying the LLM about it and it finally told me that it generated « the most probable » urls for the topic in question based on the ones he knows exists. Useless.
Very interesting because I just noticed that when doing an effort like clenching my jaw or something that mobilize neck muscles the sound is x10. So maybe because of bad posture along the years my baseline is higher than it should be ?
I thought I was alone but there is so many comments I wonder how much people is there and if it’s really random or if there is common sources like some stress, airpods or some kind of psychoacoustic event.
I have like 3 different frequencies and it « exploded » in a stressful event at work. I always thought it was music all day with AirPods but it might be stress actually because everytime I’m tired and stressed it’s unbearable.
A nightmare that we learn to live with. I often ask myself what the sound would look like if demodulated and de-pitched if that makes sense. It might seem weird but a voice modulated at a very high frequency and pitch might look like those kind of noises or I am wrong ?
That’s what I always thought, not having the proper infrastructure is a greater problem because not every apartment has private garage with electricity. In the hyper center of big towns they will never dig the streets to install chargers for every few parking spots and superchargers are rare for the amount of cars there is compared to 3min for gas with ubiquitous infrastructure. Where I live there is often parkings with 50+ cars and no or 2 chargers
Exactly. There is such a gap between brand new EV and regular cars that for someone doing 10000km per year it needs on average 8 years before breaking even to account for the price gap. It’s too expensive right now it does makes sense to invest in an EV, except if money isn’t a problem
I used to switch spaces but it’s worst for mental load than having everything on the same screen for big screens. I have 3 32inch screens (2 vertical on each side) and full screen apart from IDE like does not often makes sense. So splitting is like having smaller screens at all time and remove the need to find back which virtual screen has which apps. Like there is chrome on several virtual spaces if you cmd-tab on chrome it does not always choses one one you want. You have to get back manually at the screen which is cumbersome.
When I use only the MacBook I tile less and use more virtual screens to organize the windows because there is less real estate.
Slack, several chrome (render of code, doc, clickup etc), terminal, IDE, postman, datagrip all within a shortcut of being focused and without changing the whole screen.
I guess that depends on your needs but having the equivalent of 8 screens the size of the MacBook at all time it’s really awesome and makes me really productive, r-cmd allows me to focus on app app with a shortcut so it’s really fast. No more switch between desks is a relief to find back where my windows are