heruvim

Typescript, Python, Golang (+AWS)

[heruvim @__maicl]

@Ananth7e Copeeeee

[heruvim @__maicl]

@TimXu222575 Same, it's not bad, but a pain to work with compared to 5.5

[heruvim @__maicl]

LLMs are probably obese, cause they love the "vertical-slice" idea

[heruvim @__maicl]

@VictorTaelin @giordanorandone Hahaha love the villain arc

[heruvim @__maicl]

Preference for Claude vs ChatGPT seems to correlate with political leaning

[heruvim @__maicl]

5.5 (reasoning: low for planning)

"It's a good model, Sir"

[heruvim @__maicl]

Planning with LLMs is so dopaminergic:

"Excellent idea, yes, this is how you can do it, let's build this!"

(Reality: Complexity of task is measured in years)

[heruvim @__maicl]

@VictorTaelin @Vinibi90 It's very interesting though, because most people in my timeline fanboy one of the two and all conversions I've seen have been from Claude to GPT

I guess, after seeing Opus < GPT output couple of times, I gave up and never thought to tell it "don't be lazy", assuming skill issue

[heruvim @__maicl]

@VictorTaelin So, the trick is to babysit Opus and then it's equal (or better) than 5.4?

[heruvim @__maicl]

@effectfully "Simply telling the agent what to grep for", I don't get it.

Do you tell it the files you'd like it to look into or the lines of the files too or the function names that are relevant?

That could be easy if your prompt is very targeted, but not for investigative ones, right?

[heruvim @__maicl]

De-escalation skills are a must in corporate

[heruvim @__maicl]

@IterIntellectus Agreed. How do you move out of the cities if that's still where young, high-intellect people surround you?

Remote solves the money issue, but similar humans to build community and family away from cities might be scarce

[heruvim @__maicl]

1. Like the post (assume true)
2. Check notifications for community notes
3. Mute/Block the account that misinformed you
4. Enjoy more truth in your timeline

[heruvim @__maicl]

@adonis_singh Or read it:

https://t.co/RXxOwpg3fv

[heruvim @__maicl]

I asked the LLM why it gave me code that fails in some edge cases, response was "Because it is consistent with current codebase patterns"

We are being roasted by bots now..

[heruvim @__maicl]

@DrJSchulte @cursor_ai Can we no longer include the git diff for the working directory or specific commits? It seems only diff with main is allowed now, which is completely useless for me

[heruvim @__maicl]

Noone holds more power over you than your upstairs neighbor

[heruvim @__maicl]

Started responding in meetings with:

"Excellent question, you are absolutely right to..."

[heruvim @__maicl]

"That's nothing

When I was your age I had to write HR reviews without AI.

Go play now"

[heruvim @__maicl]

It seems it never really "goes without saying,..."