AI agents spend most of their time idle, waiting on a human prompt, a tool result or a model response. Kubernetes wasn’t built for that. Running one Pod per...
Article URL: https://evanxmerz.com/post/ai-usage-generates-a-fragile-codebase/ Comments URL: https://news.ycombinator.com/item?id=50438318 Points: 47 # Comments: 28
Introducing ClickHouse Observability: fully managed observability with the speed and scale of ClickHouse. Just send telemetry; we'll handle the rest. Plus, build the observability experience you've always wanted with a simple prompt in Observability Apps.
For several years, the conversation about enterprise artificial intelligence has focused on capability: which model is smartest and which GPU is fastest. That made sense when technology was the constraint. It isn’t anymore. AI can now do far more than most organizations will allow, and the gap is trust. That’s the core finding of “Permission […] The post Cisco research: Trust, not technology, is now the speed limit on enterprise AI appeared first on SiliconANGLE.
ClickHouse Managed Postgres, our NVMe-backed Postgres service natively connected to ClickHouse, is generally available, and we're acquiring Xata to add instant branching, cloning and scale-to-zero for developers and AI agents.
arXiv:2611.09953v1 Announce Type: new Abstract: Handwritten character recognition systems can achieve high accuracy while retaining concentrated errors among visually similar classes. Motivated by residual letter confusions in earlier geometry-based recognition work, we investigate whether these errors can be addressed through the training objective. We introduce Confusion-Adaptive Margin Learning (CAML), which constructs a sparse weighted confusion graph from a discovery partition held out from pilot training and applies pair-specific cosine-separation constraints during final training. CAML adds no classifier, routing rule, or inference-time parameters. We evaluate CAML on EMNIST Letters against a strictly matched cross-entropy CNN baseline, using the same architecture, final training data, deterministic augmentation, optimizer, and checkpoint selection. Eight confusion pairs are targeted: I/L, G/Q, U/V, R/V, D/O, C/E, I/J, and H/N. On the official clean test set, accuracy changes from 95.6346% to 95.6731%, and macro-F1 from 0.956326 to 0.956724. Mean accuracy across ten predefined corrupted conditions increases from approximately 95.3812% to 95.4303%; symmetric errors within targeted pairs decrease from 614 to 605 (1.47%). The global differences are small and not statistically reliable. CAML fixes 124 baseline errors but introduces 116 new errors on clean data (exact McNemar p=0.6515), and no corruption-specific difference remains significant after Holm correction. Thus, CAML does not establish global superiority, but shows that a leakage-controlled, pair-specific margin objective can alter targeted error structure with limited overall benefit for an already strong classifier.
arXiv:2611.09938v1 Announce Type: new Abstract: LLMs can now draft complete multi-episode dramas, and LLM judges are increasingly used to evaluate them. Assessing the reliability of these judges is difficult because drama quality encompasses specification-backed errors, reproducible preferences, and legitimate disagreement among human raters. Most existing evaluations reduce these cases to a single score from one judge call and leave tie calibration, call-to-call variation, and the vote margin underlying the human reference unreported. We introduce DramaGrow, a regime-aware benchmark and audit protocol for AI-generated Chinese five-episode drama. The benchmark assigns verifiable constraint violations, four-of-five preferences, and within-panel disagreements to separate denominators and evidence rules. It contains 800 episodes, 120 byte-preserving interventions, and 1,155 blinded five-rater records, including a frozen extension with 114 supermajority pairs and 21 disagreement pairs. On the frozen sets of 114 preference pairs and 35 constraint interventions, the repeated absolute-score rubrics yield overlapping performance, with mean accuracies of 53.8-55.8% and three-call agreement of 29.8-32.5%, and their accuracy falls from 71.6-71.9% to 34.8-37.1% as the tie band widens. DirectPair-GLM reaches 85.1% preference accuracy, 89.5% constraint F1, and 81.9% Detect+Locate on the same items, and exact subpanel enumeration identifies four-of-five as the smallest stable human vote margin. Evaluation protocol, tie calibration, judge-call variation, and panel margin therefore affect performance as much as rubric design. We will release the specification packages, scripts, interventions, anonymized human votes and rationales, frozen judge runs, and analysis code.
DuckDB is fast among other reasons because it stores data by column, so a query reads only the columns it names. This post covers DuckDB features that take advantage of that design choice: querying files in place, column-level SQL, aggregation shortcuts, window functions, ASOF joins, and writing well-organized Parquet.
General, often expert, and sometimes jagged
arXiv:2611.10832v1 Announce Type: new Abstract: AI agents and reinforcement-learning (RL) trainers run thousands of short, isolated GPU jobs: tool calls, verifiers, and rollouts. A job often finishes in seconds, but starting a GPU pod for it takes 20-35 s even when the container image is already on the node, and minutes when it is not. A warm pod removes the wait only if it can serve the next job, and keeping pods warm must neither waste GPUs nor leak state between callers. Firepool, the sandbox and execution broker behind agentic and RL workloads at LinkedIn, meets both requirements. It makes pods interchangeable by building them from a shared base image per hardware profile and binding each job's code, extra dependencies, and cluster topology when the job starts. It keeps them warm cheaply and safely by reusing a pod only for the caller that used it last, staging zero-VRAM standby pods in fractional GPU shares alongside active pods, and capping the GPUs that warm pools may hold via queue-driven budgets. Over a sampled peak period in production, Firepool serves 94.7% of 3,206 pod requests from warm or standby capacity. In paired benchmarks with fixed-duration jobs on production H200 nodes, agent and RL loops finish 13x and 10.8x faster than with a fresh pod per job; against a fresh reuse tag per job, warm reuse cuts p90 start latency from 59.1 s to 3.5 s. When a job cannot reuse the previous pod, standby promotion shortens the handover wait from 51 s to 0.94 s. In local and simulated runs, a keep-alive matched to the loop's pauses keeps the latency benefit while holding about half the capacity of an always-on pool.
