Search: “claude”

A new release of our Agent Skills and Docs eval library, Cultivar is available! Now, use @typesafeai's Jev model to evaluate how well your agents use docs and Skill against specified tasks in Modal sa

cuda : fix CUB argsort corruption caused by in-place keys (#28389) argsort_f32_i32_cuda_cub called the one-shot DeviceRadixSort::SortPairs API with d_keys_in == d_keys_out (temp_keys, temp_keys). CUB'

I think AI automated labs should be banned from anything viral or pathogen related. They will do gain of function research otherwise. Anyone agree with me? BREAKING: Anthropic has quietly set up a 'we

Meet Inco Splash, open-source inference engine, built around the model and around Apple silicon. Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents. Req

arXiv:2609.19722v1 Announce Type: cross Abstract: Large language models are being integrated into malware triage workflows as reasoning components that summarize static evidence and produce analyst-fa

vulkan: raise the hoisted row-id limit for mul_mat_id from 256 to 1024 experts (#28501) vulkan: raise the hoisted row-id limit for mul_mat_id to 512 experts The expert-count shader (count_experts.comp

Build your own harness, folks. This is absolute banger paper from NVIDIA on self-evolving agent harnesses. (bookmark it) They introduce SoL-Pi which cuts token traffic by nearly half. And it matches i

arXiv:2609.19244v1 Announce Type: new Abstract: Conversational LLM agents increasingly rely on Web search, yet the end-to-end lifecycle of agentic search remains poorly understood. We present the firs

arXiv:2609.19892v1 Announce Type: cross Abstract: As agent systems become more widely used, multiple agent sessions increasingly run alongside pre-existing user tasks in the same environment, sharing

arXiv:2609.20005v1 Announce Type: new Abstract: People increasingly turn to AI chatbots for news and explanations of world events. But do they receive the same political answers when they ask in diffe

arXiv:2609.20218v1 Announce Type: cross Abstract: Large language models can label a tabular row from a plain-English description with no training - a capability now shipping in mainstream spreadsheet

arXiv:2609.19587v1 Announce Type: cross Abstract: To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before i

arXiv:2609.20519v1 Announce Type: new Abstract: As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into lon

arXiv:2609.19155v1 Announce Type: new Abstract: In Human-LLM dialogue, follow-up user utterances may implicitly conflict with earlier intents, leading the LLM to misinterpret user needs and generate i

arXiv:2609.19530v1 Announce Type: new Abstract: Hiring is bilateral: employers assess fit, while candidates present and defend evidence of their qualifications. Yet resume screening, the first gate, i

🔥: “While AI comes with danger, we should be sceptical of any narrative that conveys inevitability around its trajectory. AI systems do not build their own data centres. They do not manufacture their

arXiv:2509.21891v3 Announce Type: replace-cross Abstract: Fine-tuning large language models for code editing has typically relied on mining commits and pull requests. The working hypothesis has been t

arXiv:2609.18052v1 Announce Type: cross Abstract: This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specifica

Narrative intelligence company PeakMetrics Inc. today launched a monitoring service that measures how brands are portrayed across five prominent generative artificial intelligence platforms and identi

arXiv:2603.06084v2 Announce Type: replace Abstract: Large language models have been widely used for robotic task planning, often taking advantage of representations such as Behavior Trees (BTs). Visio

arXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre

arXiv:2609.18805v1 Announce Type: cross Abstract: Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web development, however, agents ma

I spent the first week of September building a personal assistant over Gemma 4 in Ollama on a 16 GB M1 Pro: Node backend, React web UI, Expo phone client, two-model routing, cross-session memory, RAG

Not sure if here’s the right place to ask this but whats ur usecase to use AI in video editing ? I dont believe its up to par. Not looking for FULL VIDEO EDITS, but i got a feeling many use it it smal

Another question asked 1 thousand time, but I can't find actual threads. Sorry in case of mistake. Due to interstellar price of hardware like high-end GPU (more than 5k euros for a 5090 and similar pr

arXiv:2609.19006v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Large Reasoning Models (LRMs) are typically evaluated on challenging benchmarks through dataset accuracy alone, provi

I find another new model at HF: https://huggingface.co/XingChen-AGI/Xing4.0-29B-A4B 'Xing4.0-29B-A4B is a next-generation large language model in the Xing series (formerly TeleChat), developed by Chin

arXiv:2609.16793v1 Announce Type: cross Abstract: People increasingly reason with large language models (LLMs), yet complementary capabilities do not guarantee outperforming both components. In a betw

model : add support for HrmTextForCausalLM (DFM Mimir 1B) (#27625) model : add support for HrmTextForCausalLM (DFM Mimir 1B) HRM-Text runs two transformer stacks (low, high) in an alternating cycle ov

hexagon: accept the zeroed rope probe in supports_op (#28995) llama probes weight placement with a rope where all params are 0, so rejecting n_dims == 0 or freq_base == 0 puts rope_freqs on the CPU. T

Banger report from Salesforce. Pretty interesting to see more of these custom enterprise models. Salesforce trained the enterprise agent model from the same files it uses to configure agents. Koa star

Welcome to the first Cloud CISO Perspectives for September 2026. Today, Sandra Joyce shares the latest details on Google’s visibility into how attackers are using AI, and how we’re using AI to stop th

Agentic AI workflows using NVIDIA Omniverse libraries automate preparation of Blender scenes for robotics simulation by adding semantic labels, sensor definitions, physics properties and validating th

Interesting safety paper from Microsoft. They find that a weaker, unaligned model can split a harmful task into harmless-looking subquestions, ask an aligned frontier model each one in a separate sess

Nice work from Adobe. It's standard practice to store a fixed reference answer for every eval case. When the underlying data changes daily, that stored answer goes stale. Adobe researchers write each

arXiv:2609.15998v1 Announce Type: new Abstract: Every large language model (LLM) has behavioral traits and moral preferences that comprise its character. Whether by design or as an emergent property o

arXiv:2609.14796v1 Announce Type: new Abstract: The threat that AI persuasion poses to human control has been acknowledged in the literature, but not yet systematically studied. Now that persuasion at

opencl: choose the MoE expert matmul by batch size for speculative decoding/MTP (#27637) opencl: gate the prebuilt q4_0 MoE GEMM on routing count opencl: stop writing zeros into the padded MoE activat

arXiv:2609.15849v1 Announce Type: cross Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM pers

arXiv:2609.15706v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to extract structured fields from business documents, yet most evaluations report accuracy on clean

Good Start Labs experiments show that AI training with gameplay can lead to transferable skills: a version trained on a railroad simulation outperformed peers in financial research. Inspired by Twitch

arXiv:2609.15383v1 Announce Type: cross Abstract: Language model safety is typically evaluated one interaction at a time. We show that a weaker, unaligned model can split a harmful task into benign-lo

arXiv:2609.14839v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into automated code optimization introduces a critical reliability risk we term the Efficiency Halluci

arXiv:2609.15422v1 Announce Type: new Abstract: AI agents are provisioned the same as employee-owned hosts in many enterprise settings with a static credential set fixed at deployment which includes a

arXiv:2609.15134v1 Announce Type: new Abstract: Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through ru

arXiv:2609.13637v1 Announce Type: new Abstract: Persistent agents need evaluations that distinguish identity facts they can recall from those they express and enact. We introduce PAI-Bench, a provider