feva

Growth Engineering at Co-Founder at

[feva @fevadev]

@thdxr this only works for technical folks

[feva @fevadev]

@Cloudflare damn that's one hell of a pull

[feva @fevadev]

@ThePrimeagen hear the wsl gospel

[feva @fevadev]

@thsottiaux share this with the pro plans! what's stopping you guys?

[feva @fevadev]

@ThePrimeagen @kenwheeler I feel like it does speed up data analysis, not to the point of 100x but around 1.5 x or sometimes 2x when the data sources are very varied in shape

[feva @fevadev]

originality is a lost cause

but interestingly enough, regardless of that statement being true or not, people will not stop striving for it

[feva @fevadev]

@pewdiepie about to discover the burnout of open source https://t.co/bDa2YbTpH1

[feva @fevadev]

@thsottiaux can I please just make tools available to codex like in pi? I hate the mcp constraints, I just wanna have something quick to iterate with

[feva @fevadev]

@IterIntellectus I think you'd fall into that bucket

[feva @fevadev]

@cremieuxrecueil in regular cohort analysis (sign-ups, business, etc.) there's no such collinearity, and that's perhaps why the agent is struggling this much

[feva @fevadev]

@badlogicgames that's a funny name in spanish

[feva @fevadev]

@thsottiaux @StoicYield this is only used if you refer to a streamer

[feva @fevadev]

@theo that's how great things get started, just look at pi coding agent

[feva @fevadev]

@_chenglou not really, fails a lot in windows specially the zenbook duos

[feva @fevadev]

here's what you need to fix @sama

[Zacariah @ZacariahHeim]

I've found that instead of looking at the first principles cause of a problem, when codex finds a blocker it immediately tries a half-assed work around. For every blocker. It's super annoying, and akin to a doctor only treating symptoms instead of causes. There is zero causal reasoning in OpenAI models. This compounds if codex finds a blocker during a workaround of a precious blocker.

[feva @fevadev]

@ZacariahHeim @justalexoki yeah, this shit is super annoying
well put

[feva @fevadev]

@IterIntellectus you overreact 99% of the time

[feva @fevadev]

@thsottiaux it constantly hangs in windows, im forced to use it via the terminal

[feva @fevadev]

@mattparlmer if the goal here is to surpass human performance then yes, I'd agree. but I don't think that's the real goal

[feva @fevadev]

@paulg its simple in theory but in practice it would go more like: make something people want that you can do while either loving or not hating, that enough people are willing to pay for, for an extended period of time without dying for it