@Kalshi obviously. cloud compute -> OpenAI/Anthropic inference endpoint provisioned in the cloud provider
It's beneficial for aggregated billing, and it's where hosted agentic workflows naturally live for enterprises
Claude will bloat your codebase with pointless tests if you don't set up some basic scaffolding:
-- e2e first
-- isolation only where E2E can't reach
-- guardrails are lint rules, never tests
-- root cause, never masking: no skips, retries, longer timeouts or looser assertions
-- documented testing rules (e.g., docs/agents/testing.md)
Once you've refactored, ask it to create a skill that decides whether or not a feature, branch, diff or whole codebase follows your rules
@alexanderrX_ it's nice but only practical if a majority of your friends / family live there & maybe you work around there too
personally i would hate to live there
claude code's ultracode feature used to kill my sub limits with just 1-2 dynamic flows
With the intelligence, speed and usage limit uplift in opus 5.5, it feels like driving a ferrari that doesn't run out of gas so quickly
for anything you want to quickly create, your prompt is now:
<simple idea> + with ultracode
then you just kick back, relax and wait for the agent swarm to give you an artifact that brings your idea to life
@rehan_shei@mightyfog got you with https://t.co/tXOHtgWowV! point your agents at it. There is also an sdk for leaderboards, signins, and game state (which it seems like you need). dm me if you wanna chat about it
I already listed it for you, go claim it https://t.co/PgerGVv7rK :)