A V2EX user posed a distributed systems question: after sequentially writing keys 1 through 5 in ZooKeeper, can three clients simultaneously observe the sequences [1-5], [2-5], and [3-5]? Different AI assistants gave contradictory answers. The user’s own reasoning, based on ZooKeeper’s sequential consistency guarantees, argues it is impossible because seeing a later write implies having seen all earlier writes. The user then fed their reasoning back to the AIs, which then agreed, highlighting that LLMs can flip opinions and lack reliable reasoning on nuanced technical topics. The post is framed as an informal evaluation of AI judgment and intelligence.
MelandLabs has open-sourced OpenLoomi, an agent memory system that rethinks AI memory by mimicking coding-agent workflows. It introduces two-dimensional memory: spatial (associative linking with decay) and temporal (time-travel queries to retrieve exact past states). A three-tier forgetting engine ranks memories by recency, frequency, importance, and bookmarks to drop irrelevant data. On benchmarks, it reaches 96.3% on LoCoMo and 97.6% on LongMemEval-S500, but only 35% on CL-bench, highlighting that context-learning capability remains a hard open problem.
A V2EX user describes friends who universally distrust Chinese products: only use Apple iPhones, Tesla cars, and rely on foreign AI models like Claude and Gemini. Despite Chinese LLMs occupying positions 2-5 behind Claude on the arena coding leaderboard, these friends belittle domestic AI, pay for expensive and inconsistent overseas model relay services, and dismiss domestic car advertisements as false hype. The user questions whether such entrenched bias constitutes blind admiration of foreign things.
This is a tool for detecting whether audio clips are generated by AI. It currently offers free detection for up to three attempts per user. Logged-in users can enjoy ten free detections. Each detection can analyze up to 30 seconds of audio. The tool is available at voiceaichecker.com.