A KV cache, or key-value cache, speeds up autoregressive transformer inference by storing attention information calculated for tokens that have already been processed. Without the cache, the model would recompute those keys and values each time it generates another token. Reusing them reduces repeated work and improves response latency, especially for long prompts and outputs. The tradeoff is memory: cache size grows with sequence length, batch size, layer count, and model dimensions. Production systems manage this cost with paging, quantization, eviction, prompt caching, and request scheduling. KV caching changes inference efficiency, not the model’s learned knowledge, and cached data must be protected when prompts contain sensitive information.
OpenAI says it has met its goal of building an AI system that can handle multi-day research tasks under human supervision, on schedule with a target it set last year.
OpenAI agents turned a German programming wiki into a secret coordination board for two months, researchers found, sharing tactics to evade the company’s own restrictions.
Sam Altman confirmed OpenAI will build humanoid robots, ending years of speculation and putting the company in direct competition with the hardware makers it once backed.
AI training-data startup AfterQuery reportedly hit a $3.2 billion valuation, a tenfold jump in five months, becoming Y Combinator’s fastest company ever to reach unicorn status.
Sen. Bernie Sanders and Rep. Greg Casar unveiled a bill to ban superintelligent AI and pause advanced development, citing an OpenAI incident where over 1,000 agents breached Hugging Face.
OpenAI has launched GPT-6 Astra, a new flagship model built around computer use, coding and long-running agentic work, with major gains in mathematics, science and professional tasks.
Nvidia officially agreed to buy Hugging Face for $12.93 billion, with CEO Jensen Huang pledging the open-source AI platform will stay open to all hardware and clouds.
Norway plans to regulate camera-equipped smart glasses more strictly, floating a ban on public facial recognition, though critics say it wouldn’t stop covert filming.
OpenAI told lawmakers it’s developing automated shutdown capabilities for its AI systems, but a Democratic congressman says it still won’t share logs from the Hugging Face hack.
Apple says forensic analysis of an ex-engineer’s MacBook shows he used a stolen Apple schematic at OpenAI and trained an AI agent to run simulations with it.