Search: “NVIDIA Triton Inference Server”

32 stories

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Advisory 2 Vulnerability 2 Model release 1 Exploit / PoC 1 Ransomware 1

SeverityAll critical 4 high 0 medium 2 low 0 info 1

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut

NVIDIA's Vera Rubin NVL72 debuts in MLPerf Inference v6.1 with up to 3.7x higher throughput than GB300 NVL72 and 99% scaling efficiency at 288 GPUs.

In its first MLPerf Inference preview submission, NVIDIA's Vera Rubin NVL72 achieved up to 3.7x higher throughput than GB300 NVL72 on Qwen3-VL and 2.5x on DeepSeek-R1. A 288-GPU GB300 NVL72 submission across four racks reached 99% scaling efficiency on the DeepSeek-R1 offline benchmark. Software optimizations delivered up to 1.6x gains over v6.0, leveraging TensorRT-LLM, vLLM, Dynamo, disaggregated serving, and NVFP4 precision.

NVIDIA Blog15:00 UTC · 4h agoAI industry 2 sources

NVIDIA security advisory (AV26-900)

Canada's Cyber Centre flags NVIDIA Triton Inference Server versions through 26.03 and 26.06 as vulnerable, urging review of the September 2026 bulletin.

The Canadian Centre for Cyber Security issued advisory AV26-900 on September 9, 2026, noting that as of September 8, NVIDIA Triton Inference Server versions 0.0 to 26.03 and 0.0 to 26.06 are affected by vulnerabilities. The advisory includes no CVE identifiers or severity details and directs users to review NVIDIA's September 2026 Triton security bulletin and apply available updates.

Canadian Centre for Cyber SecuritySep 9, 15:47 UTC · 7d agoAdvisory

With Groq 3 LPX in Full Production, NVIDIA Extends Vera Rubin Inference for Agents

NVIDIA puts Groq 3 LPX into full production and extends Vera Rubin NVL72 rack-scale systems for fast token generation in agentic AI inference.

NVIDIA announced that Groq 3 LPX is in full production as part of an extension of the Vera Rubin NVL72 rack-scale platform aimed at agentic AI inference. The announcement frames the next era of inference as full-stack AI factory co-design across chips, networking, and systems rather than a single component breakthrough. The focus is improving token generation speed for agent workloads.

NVIDIA BlogAug 24, 15:00 UTC · 23d agoAI industry

Chipmaker Patch Tuesday: Nvidia, AMD, Arm Issue Security Advisories

AMD, Arm, and Nvidia issued Patch Tuesday advisories fixing a Linux GPU driver DoS flaw, nine Mali GPU vulnerabilities, and two high-severity Triton defects.

AMD fixed CVE-2026-43603, a NULL pointer dereference in its Linux GPU kernel driver that can crash systems and cause denial-of-service, credited to SecMate researchers, with patches for EPYC, Ryzen, Radeon, and Instinct shipped in July and embedded variants due in October. Arm published an advisory covering nine Mali GPU vulnerabilities allowing use-after-free access, kernel information leaks, or DoS, releasing fixes for Valhall and 5th Gen GPU Architecture drivers, with Bifrost also affected. Nvidia updated Triton Inference Server for Linux to resolve two high-severity flaws, one causing DoS and one enabling information disclosure, data tampering, and DoS. Intel had issued no new advisories since the previous Patch Tuesday.

SecurityWeekSep 9, 16:22 UTC · 7d agoAdvisory CVE-2026-43603

m-a-p/YuE2-3B — new model trending #30 on Hugging Face

M-A-P released YuE2-3B, an open music generation model that outperforms Suno v5 on WildSongBench and runs locally on a 24GB GPU.

The M-A-P (multimodal-art-projection) team released YuE2-3B, an open-weights music generation model that turns lyrics and a style prompt into full songs with vocals and accompaniment. It uses an AR-NAR Mixture-of-Transformers backbone with symbolic planning and flow matching through a VAE, and supports editable scores (melody and chords, including ABC notation) plus agentic editing workflows. On 192 WildSongBench prompts it reports a SongBench average of 6.9632 (best-of-8) versus 6.8721 for Suno v5, claimed as state of the art among evaluated open and proprietary models. It runs 48 kHz stereo inference locally on a single 24GB NVIDIA GPU without quantization, with companion releases including YuE2-Vae, MERT-v2 encoders, the WildSongBench dataset, and SheetSage2.

Hugging Face trending modelsSep 9, 18:30 UTC · 7d agoModel release1

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

NVIDIA researchers detail an end-to-end system for online draft co-training that speeds speculative decoding in large-scale long-context RL post-training.

The paper tackles scaling online draft co-training for speculative decoding in RL post-training, where rollout generation dominates cost. It extends packed, load-balanced zigzag ring attention to merge rank-local branch attention with causal main-sequence attention for context parallelism, and introduces TapChannel to transport target features across pipeline-parallel stages without changing the schedule. Experiments show co-trained drafts tracking the policy baseline with substantial rollout and end-to-end speedups up to 122B parameters and strong scaling at 256K tokens.

Hugging Face daily papersSep 6, 20:00 UTC · 9d agoAI research

Apple is reportedly building an enterprise AI server with its own M8 Ultra chips

Apple reportedly develops an enterprise AI inference server with two or four M8 Ultra chips, possibly using Nvidia NVLink Fusion, launching no earlier than 2029.

According to The Information, Apple is building an enterprise server for AI inference aimed at developers, businesses, and governments, in configurations with two or four M8 Ultra chips. Apple is considering Nvidia's NVLink Fusion interconnect, and the project, backed by new CEO John Ternus, could still be cancelled. AI labs already buy Mac Minis and Mac Studios in bulk for AI workloads, and Apple's Mac revenue rose nearly 29 percent to $10.4 billion last quarter.

The Decoder18:16 UTC · 1h agoAI industry 2 sources

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

BeaconKV introduces training-free KV cache compression using beacon queries, cutting long-reasoning inference memory up to 5.8x while preserving accuracy.

The paper shows recency-based KV cache compression assumptions fail in long-horizon reasoning because Thought Revisiting Tokens (TRT) re-attend to distant context such as early task-solving plans. TRT queries cluster into a small number of similarity groups, which BeaconKV exploits by maintaining compact beacon query representatives to anticipate revisited KV pairs without storing full query history. The training-free method achieves up to 5.8x memory reduction and over 4.3x throughput improvement across four open-source large reasoning models while nearly preserving full cache accuracy.

Hugging Face daily papersSep 3, 20:00 UTC · 12d agoAI research1

NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction

An 8.9B-parameter latent-space language model using next-concept prediction matches OLMo-3-7B pretraining loss with only 51.3% of the training tokens.

NCP-ArchPreview augments next-token prediction with Next Concept Prediction over a product-quantized concept vocabulary built from hidden states, trained jointly end-to-end. The 8.9B model was trained on 5.73T tokens from the Dolma-3 dataset, the largest latent-space language model demonstration to date. It consumes 51.3% of the tokens to reach OLMo-3-7B's final pretraining loss and outperforms it by 2.45 points on the downstream macro-average, including a 5.99-point GSM8K gain. The learned latent space also enables lightweight domain adaptation via a 17M-parameter VQ module and improves speculative drafting accepted length by 4.17%.

Hugging Face daily papersSep 8, 20:00 UTC · 7d agoAI research1

NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH100

NVIDIA released BioNeMo Inference Runtime (BioIR), an open-source PyTorch-compatible library delivering 2.90x higher Boltz-2 protein-folding throughput on 8xH100 GPUs.

NVIDIA detailed BioIR, a Python library that accelerates Boltz-2, OpenFold2, and OpenFold3 structure-prediction inference on NVIDIA GPUs while preserving standard PyTorch workflows. On a matched benchmark of 1,000 human dimers on 8xH100 80GB GPUs, BioIR delivered 58.5K folded residues per GPU-hour versus 20.2K for a torch.compile baseline, a 2.90x throughput gain. BioIR already powered the AlphaFold Database expansion, generating about 31 million candidate complexes across 4,777 proteomes, with 1.81 million released as high-confidence predictions. Extrapolated to 1 million targets, estimated folding energy drops from 35 MWh to 11 MWh at 8-GPU TDP equivalents.

MarkTechPostSep 10, 21:57 UTC · 5d agoAI tools & infra1

Inside NVIDIA’s cuDNN Graph API: Fusion, Autotuning, and Plan Reuse with cuDNN Frontend

MarkTechPost tutorial walks through NVIDIA's cuDNN Frontend graph API, covering kernel fusion, autotuning, plan reuse, and CUDA graph capture on Colab GPUs.

The tutorial explains how to express GPU computations as operation graphs via the cuDNN Frontend graph API, running the five-step build pipeline of validate, build operation graph, create execution plans, check support, and build plans. It progresses from a single fused convolution with bias and ReLU to autotuning across engine configs, FP8-style epilogues, attention, plan serialization, dynamic shapes, and CUDA graph capture. Each kernel is benchmarked against a PyTorch reference on a single Colab GPU to verify correctness and measure cost. The piece also covers practical setup issues like making libcudnn.so visible to the frontend's dynamic loader.

MarkTechPostSep 15, 21:37 UTC · 21h agoAI tools & infra1

Implementation of Machine Learning Workflows with NVIDIA cuML, RAPIDS, GPU Benchmarking, Explainability, Clustering, and Model Inference

Hands-on tutorial implements NVIDIA cuML and RAPIDS to GPU-accelerate scikit-learn-style ML workflows with benchmarking, clustering, and inference.

The tutorial demonstrates NVIDIA cuML as a GPU-accelerated machine learning framework, using cuml.accel to speed up unmodified scikit-learn scripts with zero code changes and the native cuML API for CuPy/cuDF interoperability. It benchmarks CPU versus GPU implementations of PCA, K-Means, nearest-neighbor search, logistic regression, random forests, and DBSCAN on datasets up to 200,000 samples with 64 features. It also builds GPU pipelines with UMAP, t-SNE, and HDBSCAN, validates GPU-generated SHAP explanations, uses the FIL library for forest inference, and covers model serialization and GPU/CPU portability.

MarkTechPostSep 13, 01:42 UTC · 3d agoAI tools & infra

Sparks Fly: NVIDIA Accelerates Local AI at IFA 2026

NVIDIA announces local AI push at IFA 2026 with faster llama.cpp/vLLM inference, PAIR routing tool, and October RTX Spark PCs.

At IFA 2026, NVIDIA announced simplified local AI support for agents in Hermes Agent, OpenClaw, and Perplexity Portable Computer, plus new llama.cpp and vLLM optimizations delivering up to 1.9x faster local inference. NVIDIA also unveiled PAIR, a Personal AI Router for distributing inference across a local network's PCs, and compact RTX Spark Windows PCs from Lenovo and Acer arriving in October. The post recaps recent local-capable model releases including Nemotron 3.5 Lightning (30B), Qwen3.8-Flash-Next and Qwen3.8-27B, DeepSeek v4 Flash (284B MoE, 13B active), Meta Muse Glimmer (30B), Z.ai GLM-5.3-Flash, LTX 2.5, and MiniMax-H3 with the FastH3 distilled variant.

NVIDIA BlogSep 3, 16:00 UTC · 13d agoAI industry

nvidia/Qwen3.8-Flash-Next-NVFP4 — new model trending #28 on Hugging Face

NVIDIA released an NVFP4 4-bit quantized build of Alibaba's Qwen3.8-Flash-Next, a 125B-parameter MoE vision-language model, via Model Optimizer.

The checkpoint quantizes Qwen3.8-Flash-Next — a hybrid-attention (Gated DeltaNet and Qwen Sparse Attention) Mixture-of-Experts model with 125B total and 6B activated parameters, plus 51B n-gram embeddings and 4B MTP — using NVIDIA Model Optimizer v0.46.0. NVFP4 benchmarks stay close to FP8: GPQA Diamond 91.5 vs 92.0, MMMU Pro 78.3 vs 77.1, Terminal-Bench 2.1 82.9 vs 83.3. It targets Blackwell B200/B300 GPUs, runs on vLLM, supports 262K context extendable to 1M tokens, and is licensed under the NVIDIA Open Model License with Qwen Community License 1.0.

Hugging Face trending modelsSep 2, 04:03 UTC · 14d agoModel release

NVIDIA NVLink Fusion Expands With NVHBM Custom High-Bandwidth Memory

NVIDIA expands NVLink Fusion with NVHBM custom high-bandwidth memory for hyperscalers building trillion-parameter and agentic AI infrastructure.

NVIDIA announced that NVLink Fusion will expand to support NVHBM, a custom high-bandwidth memory option. The offering targets hyperscalers and AI innovators building next-generation systems where agentic AI and trillion-parameter workloads are mainstream. NVIDIA frames the announcement around co-designing compute, memory, storage, networking, and software as a unified system.

NVIDIA BlogAug 26, 21:05 UTC · 20d agoAI industry

An Open-Source End-to-End FHE Implementation for Privacy-Preserving Llama 3 8B Inference

Odin runs Llama-3-8B fully homomorphic encrypted inference on a single H100 in 366 seconds, a 4.51x speedup over THOR.

Odin is an open-source end-to-end GPU CKKS implementation for privacy-preserving Llama-3-8B inference that co-designs ciphertext packing with model execution. A feature-major cross-layer layout unifies residual connections and layer interfaces, while transient intra-operator layouts serve linear projections and attention, avoiding intermediate repacking of QK^T softmax outputs. Minimax polynomial approximation with input-range control reduces polynomial degree and multiplicative depth for nonlinear ops. With 128-token input, Odin evaluates all 32 Transformer layers on one NVIDIA H100 80 GB in 366.4 s using 58.9 GiB peak memory, versus 1651.9 s for the THOR baseline, a 4.51x speedup.

arXiv cs.CRSep 11, 02:51 UTC · 5d agoResearch

Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS

NVIDIA's Magpie TTS open-weight multilingual speech model enables low-latency voice agents with full deployment control.

Hugging Face's blog highlights NVIDIA Magpie TTS, an open-weights multilingual text-to-speech model designed for building low-latency voice agents. The open licensing gives developers full deployment control, allowing self-hosted multilingual speech for agentic applications. The post walks through building voice agents with the model.

Hugging Face BlogAug 10, 16:25 UTC · Aug 10, 2026Model release

Nous Research Adds One-Click Local Model Setup to Hermes Desktop

Nous Research's Hermes Desktop now offers one-click local model setup that reads hardware, picks a fitting quantization, downloads weights, and configures llama.cpp automatically.

Hermes Desktop, the MIT-licensed build of the open-source Hermes Agent, now sets up local models in one click: it reads the machine's hardware, selects a model that fits, downloads weights, and configures the inference runtime. It manages a pinned llama.cpp build with CUDA, Metal, Vulkan, HIP, and CPU backends, and shows green/amber/red memory-fit verdicts per catalog model before download. Quantization floors at 4-bit, and recommended models guarantee at least a 64K context window protected by ordered RAM offload (expert weights first, never the attention cache). It runs on macOS 12+, Windows 10/11, and Linux with no account required for local models.

MarkTechPostSep 5, 19:12 UTC · 11d agoAI tools & infra1

Scalability Analysis of Distributed Kolmogorov-Arnold Network Training on High-Performance Computing Systems

An empirical study shows distributed Kolmogorov-Arnold Network training reaches 74.7% parallel efficiency at 8 A100 GPUs, with overheads driven by All-Reduce choices.

The study evaluates data-parallel Kolmogorov-Arnold Network (KAN) training on the FinisTerrae III supercomputer using up to 8 NVIDIA A100 GPUs across 4 nodes with PyTorch Distributed Data Parallel. Strong scaling yields 5.97x speedup and 74.7% parallel efficiency at 8 GPUs, comparable to conventional deep learning workloads, while communication overhead ranges from 1.3% to 6.1%, driven mainly by All-Reduce algorithm selection and inter-node latency rather than KAN's edge-wise gradient structure. Weak scaling shows an initial single-to-multi-GPU throughput drop followed by stability, and the parameter-to-memory ratio improves with model size even as training time scales unfavorably. The authors provide GPU topology and model-size deployment guidelines for KAN training.

arXiv cs.AI / cs.LG / cs.CLSep 7, 16:45 UTC · 9d agoAI research1

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

Hugging Face released @huggingface/kernels, a library offering 200+ WebGPU compute kernels to accelerate AI inference locally in browsers.

Hugging Face introduced the @huggingface/kernels package, bundling more than 200 optimized WebGPU compute kernels for running AI workloads locally. The release targets browser-based and on-device inference, reducing reliance on server-side compute. No article body was available beyond the title, so benchmark results and supported models are not specified.

Hugging Face BlogSep 1, 00:00 UTC · 15d agoAI tools & infra

TokenRhythm/NeoHorse-1-4B — new model trending #30 on Hugging Face

TokenRhythm releases NeoHorse-1-4B, an Apache-2.0 agentic fine-tune of Qwen3.5-4B claiming +5.93 benchmark macro-average gain.

NeoHorse-1-4B is a roughly 4B-parameter text-only causal language model post-trained by TokenRhythm from Qwen/Qwen3.5-4B for agent harnesses, tool use, coding, and instruction following. It applies routing-guided curriculum SFT and routing-guided on-policy distillation over execution trajectories as an early prototype toward recursive self-improvement (RSI). The release reports a 64.87 macro average across ten benchmarks versus 58.94 for Qwen3.5-4B (+5.93) and is distributed under Apache-2.0, trending #30 on Hugging Face.

Hugging Face trending modelsSep 5, 08:21 UTC · 11d agoModel release1

Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

A survey catalogs inference-efficiency techniques for video and audiovisual LLMs, mapping bottlenecks in sampling, encoding, token reduction, and LLM decoding.

This survey covers inference-efficiency mechanisms for visual and audiovisual video LLMs, reporting reductions in parameters, FLOPs, latency, memory, and token counts. It organizes methods by pipeline stage, covering frame sampling, modality encoding, connector-level token reduction, and LLM prefilling and decoding for systems built since late 2022. The authors compile accuracy-cost comparisons under shared host models and input protocols, identify gaps in audiovisual efficiency and standardized evaluation, and maintain a public repository.

Hugging Face daily papersSep 8, 20:00 UTC · 7d agoAI research

Miles v0.1: Production-Level Post-Training

Radix Ark open-sources Miles v0.1, a full-stack RL post-training framework demonstrated with asynchronous agentic RL on GLM-5.2 744B-A40B across 64 GB300 GPUs.

Miles v0.1 is a full-stack, open-source system for frontier-scale reinforcement-learning post-training, built on slime with rollout engines on SGLang and trainers supporting NVIDIA Megatron-LM and PyTorch FSDP backends plus three weight-synchronization transports. It supports full-parameter RL, LoRA RL, on-policy distillation, supervised fine-tuning, true-on-policy rollout-training alignment, and extends to diffusion models. The end-to-end case study ran fully asynchronous agentic RL on GLM-5.2 744B-A40B for terminal-use coding tasks on 64 NVIDIA GB300 GPUs with a median step time of 263 seconds over the first 30 measured steps. The code is open-sourced on GitHub.

Hugging Face daily papersSep 7, 20:00 UTC · 8d agoAI tools & infra

Domain-Specific Hallucination Detection in Large Language Models

A multi-signal pipeline detects LLM hallucinations, reaching F1 0.915 on HaluEval and cutting Qwen2.5-0.5B hallucination rates from 85.5% to 37.7% via DPO.

The paper presents a hallucination detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo Dropout uncertainty, and temperature-scaled calibration. It achieves F1 0.915 and AUROC 0.977 on general-domain HaluEval tasks, with MC Dropout inference raising accuracy to 93.2%. Applying DPO to a Qwen2.5-0.5B generator reduces its hallucination rate from 85.5% to 37.7%, while cross-domain evaluation shows poor general-domain transfer to SciFact (F1 0.52) and PubMedBERT fine-tuning as the strongest adaptation (F1 0.63).

arXiv cs.AI / cs.LG / cs.CLSep 10, 17:45 UTC · 6d agoAI research1

OPEN-1B: A Fully Auditable Training Run

Open-1B releases a 1B-parameter model with bitwise-reproducible training, letting independent auditors verify every step of the run on commodity hardware.

The paper introduces a 'fully auditable' tier of model transparency: every training operation is reproducible with bitwise certainty on heterogeneous commodity hardware by imposing definite ordering on GPU kernel reductions, data batch ordering, and collective communication. Because replaying a full run on one machine is infeasible, a collective verification scheme lets many independent auditors certify individual steps covering the whole run. The authors release Open-1B with its full pretraining dataset, every intermediate checkpoint, the training codebase, and an audit harness. This rules out undisclosed data, injected biases, or backdoors that proof-of-learning or proof-of-training-data techniques cannot exclude.

arXiv cs.AI / cs.LG / cs.CLSep 15, 16:23 UTC · 1d agoAI research

FlashVector: Agent for Hierarchical Model Serving Stack Optimization

FlashVector agent optimizes all layers of Unity's ad-serving stack, delivering up to 2x model-server throughput and 1.98x latency speedup in production.

FlashVector is an agentic system that optimizes performance across GPU kernels, ML framework computation graphs, model servers, and on-demand feature processing. Deployed in Unity's Vector advertising platform, it achieved up to 2x model-server throughput increase, 1.98x latency speedup, and 1.6x feature-store throughput gain. Optimizations spanned NVIDIA Triton's C++ codebase and the Python feature transformation service, demonstrating extensibility beyond single-kernel tuning.

arXiv cs.AI / cs.LG / cs.CLSep 15, 16:27 UTC · 1d agoAI research

RetroThinker: Enabling Retrospective Thinking in Speech LLMs

RetroThinker is a post-training framework letting the Moshi speech LLM self-correct reasoning mid-stream, adding 11% GSM8K accuracy at similar latency.

Researchers introduce RetroThinker, a multi-stage post-training framework that equips the Moshi speech LLM to verify and forward-correct chain-of-thought steps during streaming inference. It combines supervised fine-tuning on curated retrospective thinking data with length-based direct preference optimization (DPO). On GSM8K it achieves an 11% absolute accuracy gain over non-retrospective baselines at comparable latency.

arXiv cs.AI / cs.LG / cs.CLSep 10, 17:41 UTC · 6d agoAI research1

Teaching Everyone to Fish for Tokens

Analysis argues open-source AI now depends heavily on Nvidia's financing, with a reported $26 billion bet shaping the open-weights ecosystem's future.

An Interconnects essay examines whether the open-source model recipe, exemplified by Ai2's Olmo and Nvidia's Nemotron releases, can become economically self-sustaining. It reports Nvidia is spending roughly $26 billion on near-open-source models to drive demand for its chips, and argues the open ecosystem faces an existential financing window over the next few years. The author predicts open models may fork toward efficiency, specialization, and on-prem enterprise agents rather than competing head-on with closed frontier labs.

InterconnectsAug 17, 15:07 UTC · Aug 17, 2026AI industry

ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding

ReactVAU is a slow-fast streaming framework for real-time video anomaly understanding that reserves heavyweight MLLM reasoning for suspicious events, improving efficiency.

ReactVAU addresses causal streaming video anomaly understanding with three components: a lightweight Fast Detection Module using Spatial Grid Folding, Anomaly-Aware Persistent Memory that protects critical visual cues from temporal decay, and a Slow Reasoning Module activated only on suspicious events. This design minimizes heavyweight MLLM invocations during long normal intervals. Experiments show competitive anomaly detection and causal reasoning under strict streaming constraints with significantly enhanced computational efficiency.

Hugging Face daily papersSep 6, 20:00 UTC · 9d agoAI research

Notes on gotchas while migrating 35kb preprompts from Opus to self-hosted Ollama

Opinion piece urges migrating 35KB preprompts from Anthropic/OpenAI to self-hosted Ollama, citing session privacy risks and safety filters blocking security research.

The author documents gotchas migrating 35KB preprompts from Claude Opus to self-hosted Ollama, motivated by fears that frontier providers train on user sessions, citing the OpenAI Navier-Stokes controversy. The piece argues inference providers cannot audit their own retention or training pipelines and that only self-hosted hardware offers verifiable privacy. It also criticizes frontier safety filters for refusing vulnerability research tasks and calls for models that support exploitability testing in CI/CD pipelines.

Hacker News · AISep 14, 13:59 UTC · 2d agoAI industry HN 41↑ · 13 comments1

SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outsourcing

SpliTEE splits LLM inference between Intel TDX trusted execution and untrusted GPUs, using differential privacy instead of encryption to protect intermediate representations.

SpliTEE extends split inference to LLMs, running inference partly inside an Intel TDX TEE while masking intermediate inputs sent to untrusted GPUs with differential privacy rather than encryption. The authors show a prompt-reconstruction attack recovers nearly 80% of prompts from unmasked intermediate representations, motivating the masking. A global sensitivity analysis bounds the required DP noise scale, avoiding quantization and keeping models in floating point. The implementation is nearly twice as fast as full CPU-based TDX inference and 5-15 seconds faster than encryption-based Slalom with higher accuracy, evaluated on Llama-3.2-3B and Qwen3-4B.

arXiv cs.CRSep 14, 04:55 UTC · 2d agoResearch

NVIDIA and CrowdStrike Strengthen Agentic Cybersecurity Frontier

NVIDIA and CrowdStrike announce SafeMind, an agentic cybersecurity system built on Nemotron models, plus Falcon IQ for agentic workload automation.

At CrowdStrike's Fal.Con 2026, NVIDIA and CrowdStrike announced SafeMind, an agentic cybersecurity system combining CrowdStrike's purpose-built frontier models and harnesses with NVIDIA Nemotron open models in a continuous red-versus-blue coevolution loop. A Blue Solano model post-trained on Nemotron 3 Super reportedly achieved higher accuracy than leading frontier models at 99% lower cost. CrowdStrike also introduced Falcon IQ, powered by Nemotron models in the Charlotte AI AgentWorks platform, coordinating more than 50 agents for automated defensive workflows. CrowdStrike cited an 89% year-over-year rise in AI-enabled attacks and a fastest eCrime breakout time of 27 seconds as context for agentic defense.

NVIDIA BlogSep 1, 21:19 UTC · 14d agoAI industry