If we transfer this to modern "agentic" software engineering, it's similar to saying every stage needs its own agent and the context of the previous one shouldn't leak into the next one. which works better yes and one can optimize each step separately too.
If we transfer this to modern "agentic" software engineering, it's similar to saying every stage needs its own agent and the context of the previous one shouldn't leak into the next one. which works better yes and one can optimize each step separately too.
Interesting. Didnt think of it like that. The caveat is that the model was done with humans.. not AI.
AI/Humans... we are all one big family now 🤪
Sure …. NuneGPT