| ▲ | yellow_lead 3 days ago |
| You should periodically ask Claude to review random parts of code to pump your metrics. |
|
| ▲ | giancarlostoro 3 days ago | parent | next [-] |
| Has the net benefit that it points out things that are actually wrong and overlooked. |
| |
| ▲ | rasz 3 days ago | parent | next [-] | | But also points out tons of your deliberate design choices as bugs, and will recommend removing things it doesnt understand. | | |
| ▲ | rgbrgb 3 days ago | parent | next [-] | | just like any junior dev | | |
| ▲ | rozap 2 days ago | parent [-] | | consider rewriting in rust | | |
| ▲ | s1mplicissimus 2 days ago | parent [-] | | that's gonna be painful, as the borrow checker really trips up LLMs | | |
| ▲ | jmalicki 2 days ago | parent [-] | | I do a lot of LLM work in rust, I find the type system is a huge defense against errors and hallucinations vs JavaScript or even Typescript. |
|
|
| |
| ▲ | giancarlostoro 2 days ago | parent | prev [-] | | Great time to research if those choices are still valid or if there's a better way. In any regard, its just an overview, not a total rewrite from the AI's perspective. |
| |
| ▲ | strken 2 days ago | parent | prev [-] | | AI reviews have the benefit of making me feel like an idiot in one bullet point and then a genius in the next. |
|
|
| ▲ | lovich 3 days ago | parent | prev [-] |
| why periodically? Just set it up in an agentic workflow and have it work until your token limit is hit. If companies want to value something as dumb as LoC then they get what they incentivized |
