5 articles tagged “LLMs”.
Hornet held the retriever, model and corpus fixed and swapped the harness from one tool call per turn to one Python program per turn. Recall went up 65%, tokens down 51%. Strip the new vocabulary and the win isn't Python - it's that retrieval was finally allowed to fan out.
Open Perplexity, run a query, look at the Sources panel. The architecture is recognisable: retrieve, rerank, summarise, cite. The system has moved; the engineering hasn’t. A bridge piece between the observational posts and the next phase of this series.
SID AI’s SID-1 is the first retrieval model trained end-to-end with RL. Some observations through a search-and-IR lens: the middle of the retrieval pipeline collapses into one trained model, the NDCG reward gets deliberately bent toward recall, and the agentic-retrieval loop becomes a subagent you hand to a larger system.
Laurie Voss says applied-AI iteration has moved off the model and into "the harness". He’s right - and once you strip the new vocabulary, the harness is mostly a retrieval system.
Agentic search looks like a clean break from classical IR. Look closer and the architectural instincts are the ones backend engineers have used for decades - the components are new, the rules are not.
