[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@housecor "@dat_nguyen94 Some parts were harder to prompt. UI was easier. In some cases it would have been far quicker to just write code but that wasnt allowed"
X Link @housecor 2025-10-17T22:13Z 142.8K followers, XX engagements

"How I handled React state over XX years: 2014: Class state 2016: Redux 2018: useState useReducer useContext 2020: React query 2021: Zustand for globals 2024: useOptimistic useTransition useFormStatus useActionState RSC 2025: Tanstack DB or sync engine (Zero Electric Convex)"
X Link @housecor 2025-09-01T13:55Z 142.8K followers, 82.8K engagements

"If Im unhappy with the code AI generates its probably my fault. My prompt is vague. My context is incorrect. My task was too high level. My requirements arent sufficient. My tests types & linting are weak. My instructions file isnt specific. Its not the tool. Its me"
X Link @housecor 2025-10-17T19:33Z 142.8K followers, 10.3K engagements

"@nexiumship Depends on your definition. Their definition: no coding by hand. All code AI generated"
X Link @housecor 2025-10-16T21:21Z 142.7K followers, 1069 engagements

"@jpreagan_ @Squezilia Doesnt really surprise me. A well configured LLM should be able to consistently create code that follows our coding standards. Its mostly a matter of getting instructions files right and assuring rules are enforced via linting"
X Link @housecor 2025-10-17T19:39Z 142.7K followers, XX engagements

"@scasagra Developers"
X Link @housecor 2025-10-17T08:30Z 142.8K followers, XXX engagements

"How I've fetched in React over XX years: 2014: Fetch in componentDidMount 2019: Fetch in useEffect 2020: Custom useFetch hook 2021: React query 2022: React query with useErrorBoundary 2023: React query with useSuspenseQuery 2024: React Server Components 2025: Sync-engine"
X Link @housecor 2025-08-20T18:23Z 142.8K followers, 190.7K engagements

"Is Vibe coding effective It appears the answer is Yes. Just saw a talk from a team that did an experiment to prove it. They built the same app using two teams: X. DIY team that cant use AI for anything. X. AI team that must use AI to write all code. No manual coding allowed. They used XX% Cursor and XX% Copilot. Result AI team was about XX% faster and quality was comparable. A senior dev was shown both codebases and couldnt tell which one was AI generated. The AI team used the Figma MCP to build the pages based on Figma docs which is why the pages were built WAY faster than the DIY team. AI"
X Link @housecor 2025-10-16T20:52Z 142.8K followers, 90.4K engagements

"Picking a LLM model is hard. Speed price and capability are a spectrum and they tend to be tradeoffs. So LLM models are an example of the iron triangle. Good Fast Cheap Pick two. The good news Models are getting better faster and cheaper so the cheapest models are increasingly sufficient. With Haiku XXX you get 3.5x speed slightly lower capability than Sonnet XXX and its 3x cheaper. Pretty compelling tradeoff"
X Link @housecor 2025-10-16T11:48Z 142.8K followers, 7598 engagements

"I'm watching the Remix Jam stream and this little moment is interesting. Since DOM events bubble you can declare event handlers in parent elements. In this screenshot Ryan moved the input's change handler to the form tag. Since Remix X uses plain 'ol events this works"
X Link @housecor 2025-10-12T22:53Z 142.7K followers, 17K engagements

"AI is making me faster. But picking an AI-assisted coding workflow is harder than ever. Here's XX key decisions: X. Editor AI focused (Cursor Windsurf) or "vanilla" IDE X. CLI or Extension - Copilot Claude Code Codex CLIs or use extension to embed in my editor X. Model GPT-5-Codex Sonnet Opus etc Think low med or high X. Instructions Agents .md and alternatives nesting .prompt files custom subagents X. Approvals Read only auto (workspace only) prompt full access X. Testing Write first or last Run after each change or manual Use MCP or not X. Validation Linting formatting static analysis"
X Link @housecor 2025-10-15T19:05Z 142.8K followers, 12.7K engagements