CodiumAI, debuted TestGPT, and raised $11M, interactive unit-testing (codium.ai) 1 points by itamarcode 3y ago ↗ HN
[–] itamarcode 3y ago ↗ Does an AI-empowered code level testing tool really require its own domain specific model? [–] verdverm 3y ago ↗ For now, but not for long? It may always be the case that a fine-tuned model will outperform, but at some point the general will be good enough.I'd prefer a single assistant that works everywhere, rather than having to learn the nuances of a model per service
[–] verdverm 3y ago ↗ For now, but not for long? It may always be the case that a fine-tuned model will outperform, but at some point the general will be good enough.I'd prefer a single assistant that works everywhere, rather than having to learn the nuances of a model per service
2 comments
[ 2.2 ms ] story [ 12.6 ms ] threadI'd prefer a single assistant that works everywhere, rather than having to learn the nuances of a model per service