Joined January 2023
1,077 Photos and videos
WebDevCody retweeted
Fable 5 Claude Code just built what might be the most detailed solar system sim I’ve seen from any AI model. 92 celestial bodies. 122 walkable surfaces. Real physics (eclipses, barycenter wobble, seasonal caps, plasma tori, sodium tails). 17 time-travel events. Live spacecraft. Even predicted real future transits on its own. 1 prompt. One codebase. This is actually insane.
5
5
60
37,719
/goal optimize my codbase until it reaches 0 loc
8
2
23
2,390
/goal "optimize my codbase until it reaches 0 loc"
13
1
58
5,275
running a test now
7
1,771
It's funny watching devs say ai can't replace judgement when most of you select "recommended" during your plan mode.
13
2
103
7,656
I have a $100 / month CC sub and have used over $300 just this afternoon in tokens... I'm curious when this golden era will end
20
99
13,577
ideate with composer 2.5 for a feature. ask it for a prompt describing your needs. throw it to CC Opus 4.8. fix its output in Gpt 5.5.
11
57
7,247
so.. for those trying to break into the software industry, what's the interview experience like? are they still asking leet code questions?
20
2
74
21,887
the biggest obstacle for ai development is the years of red tape and process we put into place to require tons of human checkpoints because that one dev accidentally dropped the production database 10 years ago.
6
1
32
3,499
yes, everyone uses it on the job, I want to see how someone interacts with their favorite cli tool, what questions they ask, what questions they forget to ask, do they have decent workflows to verify the output of the agents, etc.
SOFTWARE ENGINEERS ONLY Should companies let candidates use AI during interviews?
5
2
37
6,724
it depends, do you get fired if you cause a critical prod issue or security issue because you didn't review anything, or will your boss just say "lawl claude"
We generate code via AI. We review code view AI. Is your team still doing human code reviews? Why or why not?
1
26
4,460
is there a way to just quickly disable all skills or sub agents? like I just want to make a quick ui tweak and CC tries to kick in 5 different skills and sub agents I don't need at this point.
11
27
5,448
my workflow is prompt -> verify -> repeat until it works. even with these latest models, I constantly have to verify the work as it never seems to get it right. is this the same experience others are having?
71
3
154
16,282
I've been adding sandbox support into Mission Control. You can spin up as many remote EC2 instances on your own AWS account, clone your code, and start prompting Claude Code in your isolated sandbox.
3
24
3,089
cooking up my own coolify
14
80
9,072
with enough time and tokens it'll converge
2
1
956
do y'all run ai agents in isolated environment (vm, sandbox, container, etc), or do you just run them on your personal or work laptop?
91% laptop
9% sandboxes
96 votes • Final results
28
1
21
8,914
opus 4.8 probes hard
3
19
5,670
you just needed a "double check you didn't miss anything" prompt and you'd be good
cancelled after 30 min of using composer 2.5 is fucking retarded
1
15
4,525