▲ 9 ▼ Lobsters Vibecoding Challenge (Winter 2025-2026) (gist.github.com) submitted 7 months ago by corbin@awful.systems to c/notawfultech@awful.systems 9 comments fedilink hide all child comments I’m tired of hearing about vibecoding on Lobsters, so I’ve written up three of my side tasks for coding agents. Talk is cheap; show us the code.
[–] BlueMonday1984@awful.systems 8 points 7 months ago* (last edited 7 months ago) (4 children) There's already a couple of 'em - one of 'em, as expected, is being a sneerable little shit: permalink fedilink source parent hideshow 4 child comments replies: [–] V0ldek@awful.systems 14 points 7 months ago* Vibe coding is of course a less than optimal process for the kind of tasks you've specified here Oh no, tasks that have actual concrete outcomes and requirements! Vibe coders biggest nemesis! permalink fedilink source parent [–] blakestacey@awful.systems 8 points 7 months ago Here's something. It doesn't follow your rules. Then why did you submit it, dipshit? Given your tone in these posts it seems unlikely to meet the kind of standards you are looking for. That "kind of standards" being basic competence. permalink fedilink source parent [–] corbin@awful.systems [S] 7 points 7 months ago I've started grading and his grade is ready to read. I didn't define an F tier for this task, so he did not place on the tier list. The most dramatic part of this is overfitting to the task at agent runtime (that is, "meta in-context learning"); it was able to do quite well at the given benchmark but at the cost of spectacular failure on anything complex outside of the context. permalink fedilink source parent [–] istewart@awful.systems 6 points 7 months ago it was worth trying to start from my phone permalink fedilink source parent
[–] V0ldek@awful.systems 14 points 7 months ago* Vibe coding is of course a less than optimal process for the kind of tasks you've specified here Oh no, tasks that have actual concrete outcomes and requirements! Vibe coders biggest nemesis! permalink fedilink source parent
[–] blakestacey@awful.systems 8 points 7 months ago Here's something. It doesn't follow your rules. Then why did you submit it, dipshit? Given your tone in these posts it seems unlikely to meet the kind of standards you are looking for. That "kind of standards" being basic competence. permalink fedilink source parent
[–] corbin@awful.systems [S] 7 points 7 months ago I've started grading and his grade is ready to read. I didn't define an F tier for this task, so he did not place on the tier list. The most dramatic part of this is overfitting to the task at agent runtime (that is, "meta in-context learning"); it was able to do quite well at the given benchmark but at the cost of spectacular failure on anything complex outside of the context. permalink fedilink source parent
[–] istewart@awful.systems 6 points 7 months ago it was worth trying to start from my phone permalink fedilink source parent