I wait for the day when the employer, the management, the business analyst, and the customer can get to state expected behaviour. Nevermind using AI. On all my projects programme was never a problem, it was…
I don't think anyone killed old school engineering, whatever that means for you. But if someone indeed did kill it, incompetence, management and incompetent management is the culprit
Well, as a software engineer from a very poor part of Europe, I can testify that you know jackshit about both.
> keep that which works you forgot the "pretend that everything works" part
misanthropic programmers say no
I've found that most of LLM generated docs are diluted and unfocused. Spending 3 paragraphs on some quirk of a library, then 2 simple examples of a command. I write README and docs by hand, thus only important stuff…
we can drop the I from AI then
How does my browser authenticate to a website/service? Can't agents have session storage to store such information?
Yes and harnesses can't provide any interface for an agent to send REST requests for example.
It's a fun project without bad intentions. Crucify someone else for using AI. Your comment serves only selfish purposes.
Hi! I've dabbled in implementing an MCP server/client back in March. To me a proper REST API and/or cli tool seems sufficient enough, agents use them with good efficiency. Any reason not to provide CLI or REST interface…
yeah, except throw a tantrum and the towel in
how so?
I wait for the day when the employer, the management, the business analyst, and the customer can get to state expected behaviour. Nevermind using AI. On all my projects programme was never a problem, it was…
I don't think anyone killed old school engineering, whatever that means for you. But if someone indeed did kill it, incompetence, management and incompetent management is the culprit
Well, as a software engineer from a very poor part of Europe, I can testify that you know jackshit about both.
> keep that which works you forgot the "pretend that everything works" part
misanthropic programmers say no
I've found that most of LLM generated docs are diluted and unfocused. Spending 3 paragraphs on some quirk of a library, then 2 simple examples of a command. I write README and docs by hand, thus only important stuff…
we can drop the I from AI then
How does my browser authenticate to a website/service? Can't agents have session storage to store such information?
Yes and harnesses can't provide any interface for an agent to send REST requests for example.
It's a fun project without bad intentions. Crucify someone else for using AI. Your comment serves only selfish purposes.
Hi! I've dabbled in implementing an MCP server/client back in March. To me a proper REST API and/or cli tool seems sufficient enough, agents use them with good efficiency. Any reason not to provide CLI or REST interface…
yeah, except throw a tantrum and the towel in
how so?