i figure out the niche ffmpeg commands various chain filters, etc
then expose them from my python cli tool with words similar to what this gentleman above has done.
If one has fewer such commands its as simple as just bash aliases and just adding it to ~/.bashrc
alias convertmkvtomp4='ffmpeg command'
then just run it anytime with just that alias phrase
i use ffmpeg a lot so i have my own dedicated cli snippet tool for me, to quickly build out complex pipeline in easier language
the best part is i have --dry-run then exposes the flow + explicit commands being used at each step, if i need details on whats happening and verbose output at each step
Built out this service you can just copy three bash/python files and the .claude/settings.json to your different repos and just plug them to turn on in background by just one command, and then ask Claude Code to do something, close your terminal on phone and roam about grab coffee, chit chat, come back once it notifies for input or anything
Im using it with WisprFlow on my phone, to do marketing tasks on side, while coding or just do marketing tasks and research on my way to work in my cab stuck in peak traffic, and then once im at office i can just focus on coding.
The biggest joke is most of the proprietary routers both consumer and enterprise grade often are running some old outdated version of custom tuned openwrt lol, this goes for tp-link, and everyone else almost.
Experience working with doctors a few times, and then we’ll see all the bias if one is still surviving lol. Doctors are some of the most corrupt professions who are more focused on selling drugs they get paid commission for to promote, or they obsess over tons and tons of expensive medical tests, that they themselves often know is not needed, except they ask for it, simply out of fear of courts suing them for negligence in future or because again , THEY GET A COMMISSION from the testing agencies for sending them clients.
And even with all of that info, they often come out with the wrong conclusions at times. Doctors do a critically important role in our society and during covid they risked their lives for us, more than anyone else, i do not want to insult or bring down the amount of hard work doctors do for their society.
But worshipping them as holier than thou gods is bullshit, that almost anyone who has spent some time with going back and forth with various doctors over the course of years will come to the conclusion of.
Having an AI assistant doesnt hurt, in terms of medical hints, we need to make having Personal Responsibility popular again, in society’s obsession for making every thing “idiot proof” or “baby proof” we keep losing all sorts of useful and interesting solutions because our politicians have a strong itch to regulate anything and everything they can get their hands on, to leave a mark on society.
And you’d be right, so society should let people use AI while warning them about all the risks related to it, without banning it or hiding it behind 10,000 lawsuits and making it disappear by coercion.
Same here, Youtube and Social Media algorithms driven by outrage to boost statistics, has made it unbearable for me to watch news or read it online, everything is framed and created with maximum outrage in mind.
I added a DNS level blocker on all news app and restricted youtube itself to stop myself from watching news no matter what, and I only use chatgpt advanced voice mode now and sometimes perplexity pro to get my news for the day, and ask questions, around news, I stopped reading everything news related outside of purely business and tech related articles curated and sent to me via either my rss feeds, or via newsletter, nothing else.
It feels amazing to get briefed on the days news by ChatGPT, i intuitively ask it stuff around what my interests are and nothing else.
As someone who uses ChatGPT around topics I'm relatively experienced about, it seems absolutely insane to me to put your entire worldview in its hands.
It told me the other day that on a multiple hard drive/SSD system I could set secure boot on each drive independently.
Of course this is nonsense, since secure boot is set in the BIOS.
Whatever, Chat GPT got it's engagement metrics.
I'm going to predict within the next few years someone's going to lose a billion dollars relying on Chat GPT or another LLM.
It's still at the level of an energetic junior engineer, sure it wants to crank out a lot of code to look good, but you need to verify everything it does.
I was game jamming with a friend last weekend and I realized he can manually write better code, lighter code, more effective code than I was having co-pilot write.
Which sounds safer, an elegant 50 line function, or 300 lines of a spaghetti code that appears to work right.
The manager( and above)level is all about AI though, let's cut staff and have AI fill in the gaps!
> I'm going to predict within the next few years someone's going to lose a billion dollars relying on Chat GPT or another LLM.
I strongly suspect this has already happened, possibly even multiple times. Some inbred oil sheikh fatfingering some insane sum of money because "the computer told me, and computers are always correct" is completely believable scenario. Now that I think about it, doesn't Line city fits it perfectly? :)
What will happen in the next few years is probably not just a cash loss, but some large industrial accident with dead people, due to relying on the LLM bullshit. Now that would make headlines (at least until next Truth Social post).
>Some inbred oil sheikh fatfingering some insane sum of money because "the computer told me, and computers are always correct" is completely believable scenario.
No need to degrade people, if anything the highest class with hop on the AI train. Why trust an expensive human when an LLM will give you unlimited "advice" ?
LLMs can serve as a fall guy, but what's the old IBM quote. Something like a computer will never be responsible for an executive decision.
Then again LLMS making stupid mistakes is the only thing keeping most of us employed
I read comments like these and feel like I'm taking crazy pills. Alice in Wonderland moment, truly. Like, we are all engineers here, even if just a little. Willingly and knowingly constraining your information intake to a random character generator is a bold move. Incomprehensible for me, but definitely bold :) .
I know it’s controversial i know sometimes it’s inaccurate i honestly don’t care anymore i just don’t want the outrage inducing news content / videos / etc.
News is no longer the same everything is structured to maximize clicks , reactions, etc. Most news is misinformation or ideologically slanted anyways i just ask it to curate from feeds im interested in now, ive shifted to it only a few weeks ago, honestly its not as bad as people here are commenting it out to be.
i get it sounds dystopian but so does what i used to do previously. I dont need to know everything about everything, business & tech news i still read and watch myself as it tends to be fairly pleasant and inviting.
For me this is how the cons compare:
- Occasional inaccuracy from AI summaries < constant psychological damage from outrage algorithms
- Missing some nuance < being manipulated into anger and anxiety daily
- Imperfect information filtering > perfect exposure to toxic information delivery
I didn’t want to make this change i had to for my mental health sorry. Chatgpt can hallucinate a ton , claude is way more accurate and fair , i experiment with both.
works perfectly, i just say what i want coded, press enter, and Claude Code just does it in my server over Termius app
reply