Saved toolsSubmit a tool
FOXAI SEARCH

Search FoxAI

News stories 847

Idle, then spiking: Why AI agents are breaking Kubernetes resource planning

AI agents are changing the economics of cloud infrastructure, and autonomous orchestration is becoming the way platform teams keep up. Agentic workloads sit idle and then spike without warning. That pattern leaves static resource settings either wasteful or likely to fail. Container orchestration for AI is fast becoming the backbone of production AI, and agents […] The post Idle, then spiking: Why AI agents are breaking Kubernetes resource planning appeared first on SiliconANGLE.

SiliconANGLE AI

Introducing Vercel X

Vercel is launching Vercel X, a six-week accelerator in San Francisco for AI founders at the idea and pre-seed stages. The program offers no equity take, access to over $9 million in credits from partners like AWS, Anthropic, and OpenAI, technical mentorship, founder community events, investor access, and funding opportunities. Applications are open until November 29, 2026, with the cohort running from January 19 to March 2, 2027. Eligible applicants must be Vercel customers, not have raised institutional seed funding or participated in traditional VC accelerators, and commit to full-time in-person attendance in San Francisco.

Vercel

KV-LTM: Persistent Per-Session KV Caches as Long-Term Memory for Personal Assistants

arXiv:2611.21998v1 Announce Type: new Abstract: Personal assistants accumulate months of conversations, but today's long-term memory stacks put derivation or selection between a question and its evidence. In a system-level comparison on LongMemEval, two commercial assistants scored well below the same model reading the history offline [1], consistent with, but not isolating, content loss between write and read. We propose KV-LTM: a memory tier storing each session's raw text plus its KV cache under a fixed reader model, answering by restoring cached sessions and appending the question. KV-LTM is complementary to, not a replacement for, retrieval and indexing. Text is the memory of record; the cache is a recompute-free prefill accelerator, degrading gracefully to text. We specify the design: storage record, budget-derived retention, append-only read path, and bounded aggregation. We size it analytically: across pinned BF16 full-attention (GQA) and latent-cached MLA configurations, per-token state spans approximately 31K-328K bytes (the pinned KDA+MLA hybrid differs: approximately 8.1K bytes/token plus a fixed per-session recurrent term), giving approximately 0.34-3.6 TB per user-year at a declared 30K-token/day scenario, against approximately 49 MB of raw text; per-query cost is modelled as regime-conditional transfer, attention, decode, aggregation, and compute. We define an evaluation protocol needing no persistent-cache implementation for logical QA evaluation: per-session prefill emulates valid cache reuse under the same model/input-state contract and ideal arithmetic, with named arms, controlled baselines, and a preregistered reader-model gate; a separate minimal real-cache replay tests numerical equivalence and measures the cost axis, with outcomes not assumed. KV-LTM trades storage for avoided re-prefill compute and write-time fidelity, within a declared retention budget.

arXiv cs.AI