recall

This article presents a head-to-head comparison of a new deterministic memory tool that achieves perfect recall with zero LLM calls during retrieval against four other tools.

An article demonstrating how to build a loop that automatically tunes RAG system configurations to achieve a target recall, including full code and evaluation methods.

Waymo issued a recall for 3,871 robotaxis after incidents where vehicles entered freeway construction zones at highway speed; a software fix is under development and freeway operations are suspended until it is deployed.

A commentator highlights OBLIQ-Bench (recall@k) and StudyBench (expertise) as two of the few reliable long-context benchmarks.

Midas achieves 0.56 recall@k on BEAM 100K and 0.51 on BEAM 500K with zero LLM calls and zero cost, demonstrating efficient long-term memory for agents.

This paper studies a deployed LLM-as-judge system for evaluating multi-turn conversational agents and finds it catches far fewer defects than human review, revealing a structured blind-spot taxonomy and routing failures.

This paper identifies a blind spot in reference-free faithfulness metrics: they only measure precision (whether claims are supported) but not recall (coverage of relevant facts). The authors introduce a complete-oracle evaluation using Formula 1 telemetry and weather data, showing that high-precision models often have poor coverage, and propose a combined metric.

Tesla is recalling 14,575 Model Y vehicles because a weight certification sticker may be missing due to an automated vision-scanning tool error, requiring physical inspection instead of a software update.

Waymo pauses its robotaxi service in Atlanta after a vehicle drove into a flooded street and got stuck, following a similar pause in San Antonio. The company's software recall last week was insufficient to prevent the incident, highlighting ongoing challenges with autonomous vehicles in adverse weather.

Waymo is voluntarily recalling about 3,800 robotaxis in the U.S. to fix a software glitch that allowed them to drive into flooded roads, following incidents in Austin and San Antonio.

Tesla is recalling its cheaper RWD Cybertruck Long Range over faulty brake rotors that could cause wheels to fall off, affecting all 173 units sold; the company will replace the parts free of charge.

Chronicle is a voice-based personal memex tool that helps you remember everything by recording and organizing your spoken thoughts.