Russell, Bertrand - Lecture (1949-01-23), "Control and Initiative: Their Respective Spheres," Reith Lecture, "Authority and the Individual" No. 5, BBC Radio | WIST Quotations

Differences between nations, so long as they do not lead to hostility, are by no means to be deplored. Living for a time in a foreign country makes us aware of merits in which our own country is deficient, and this is true whichever country our own may be. The…

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bottleneck: exact lexical constraints, sparse clue conjunctions, local context checks, and multi-step hypothesis refinement are difficult to implement by calling a conventional off-the-shelf retriever, and evidence filtered out early cannot be recovered by stronger downstream reasoning. Agentic tasks further exacerbate this limitation because they require agents to orchestrate multiple steps, including discovering intermediate entities, combining weak clues, and revising the plan after observing partial evidence. To tackle the limitation, we study direct corpus interaction (DCI), where an agent searches the raw corpus directly with general-purpose terminal tools (e.g., grep, file reads, shell commands, lightweight scripts), without any embedding model, vector index, or retrieval API. This approach requires no offline indexing and adapts naturally to evolving local corpora. Across IR benchmarks and end-to-end agentic search tasks, this simple setup substantially outperforms strong sparse, dense, and reranking baselines on several BRIGHT and BEIR datasets, and attains strong accuracy on BrowseComp-Plus and multi-hop QA without relying on any conventional semantic retriever. Our results indicate that as language agents become stronger, retrieval quality depends not only on reasoning ability but also on the resolution of the interface through which the model interacts with the corpus, with which DCI opens a broader interface-design space for agentic search.

Client Challenge

GitStars

How does Shazam work? Music Recognition Algorithms, Fingerprinting, and Processing | Toptal®

The Shazam music recognition application made it finally possible to put a name to that song on the radio. But how does this magical miracle actually work? In this article, Toptal Freelance Software Engineer Jovan Jovanovic sheds light on the principles of audio signal processing, fingerprinting, and recognition,...