They just parrot you. Take a step back and a actually look at the session and you’ll see its just trying to figure out what the fuck you want so it cab give you the code snippet which matches your needs
Your billing support email forwards to a google group which rejects the email entirely. So i embedded my question inside the websites sales enquiry form and received multiple rounds of emails that couldn’t be further from human.
It’s not why we started using posthog but it definitely sealed the deal when you see how simple and reliable that experience is
I just want to say i appreciate you wrote the article and do your own writing. I dont really understand what your trying to say (something analogous to omc/ulw?) but i appreciate it
It can only result in more work if you freelance because it you disclose that you used llm’s then you did it faster than usual and presumably less quality so you have to deliver more to retain the same income except now your paying all the providers for all the models because you start hitting usage limits and claude sucks on the weekends and your drive is full of ‘artifacts’, which incurs mental overhead that is exacerbated by your crippling adhd
And then all of a sudden you’re just arguing with the terminal all day - the specs are written by gpt, delivered in-the email written by gpt. Sometimes they dont even have the time to slice their prompt from the edges of the paste but the only thing i can think of is “i need to make the most of 0.5x off peak claude rates “
The removal of sort by date makes any search result algorithmic and thus can be manipulated to match advertiser or paid boosting. No doubt the team doesn’t want this. It’s just enshittification in motion
Its too late. Marketplaces and storefronts are neck deep in slop and generated content, with information that is so derivative, unhelpful, and constructed with get-rich-and-get-out motivations at every step. This is just another layer of obfuscation and opportunity for hallucinations to manifest themselves into the models.
If the information being consumed is biased because its sponsored content or whatever, then we may as-well just let OpenAI run their own ads platform with responses. At least then they can take some responsibility for it.
They have to introduce human oversight somewhere.
It reminds me of what was ultimately the solution to gold farming in WoW; Blizzard had to start selling it themselves. The system had been gamed, it wasn’t solvable through engineering. Botting is a human problem.
Can we just take a breath and think shit through instead of creating solutions to problems to solutions to problems to solutions?