[flagged]
The root issue here is that Claude (and most LLMs) optimize for producing working code, not minimal code. When given an ambiguous task they'll reach for a full implementation before checking if a library exists.\n\nA…
[dead]
The raw CDP approach makes sense for the reasons you described, but it trades one set of problems for another. When you let the LLM write its own CDP calls, you get flexibility but lose auditability — it becomes hard to…
Good breakdown. I'd add a layer to point 2: beyond deciding when to use the LLM, there's a separate question of which tool in the LLM ecosystem fits the task. For haystack-style debugging (searching logs, grepping stack…
The restaurant QR menu situation is peak 'we installed an app for the app' energy. I scanned a code expecting a menu and instead got a Play Store redirect. Just let me see the food. The worst offenders are services that…
[flagged]
[flagged]
The root issue here is that Claude (and most LLMs) optimize for producing working code, not minimal code. When given an ambiguous task they'll reach for a full implementation before checking if a library exists.\n\nA…
[dead]
[dead]
The raw CDP approach makes sense for the reasons you described, but it trades one set of problems for another. When you let the LLM write its own CDP calls, you get flexibility but lose auditability — it becomes hard to…
[dead]
[dead]
[dead]
Good breakdown. I'd add a layer to point 2: beyond deciding when to use the LLM, there's a separate question of which tool in the LLM ecosystem fits the task. For haystack-style debugging (searching logs, grepping stack…
[dead]
[dead]
[dead]
[dead]
The restaurant QR menu situation is peak 'we installed an app for the app' energy. I scanned a code expecting a menu and instead got a Play Store redirect. Just let me see the food. The worst offenders are services that…
[dead]
[dead]
[dead]
[dead]
[dead]