Search: “claude”

we recently trimmed the deepagents harness base prompt by 65% (including tool info) it shows — deepagents is cheap! We ran DeepSeek V4 Flash through 4 more agent harnesses (Hermes Agent, Pi Agent, Pri

Mark Bergen / Bloomberg: Anthropic, Macquarie, and Singapore's GIC form Theseus Infrastructure to develop AI computing sites; Anthropic commits to cover consumer electricity price hikes — Anthropic PB

arXiv:2608.07004v1 Announce Type: new Abstract: Although remarkable capabilities have been demonstrated by Large Language Models (LLMs) across scientific domains, feedback controller design remains un

arXiv:2608.06811v1 Announce Type: cross Abstract: Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration

arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce measurably different behav

arXiv:2608.06526v1 Announce Type: new Abstract: Large language models can infer sensitive personal attributes, such as age, location, and occupation, from ordinary text, turning everyday writing into

Grok Imagine is focused on professional usefulness, fun for consumers and overall ease-of-use Grok 4.5 just ranked #1 on Design Arena for Daily Usage - measuring the average unique users actually inte

arXiv:2608.06778v1 Announce Type: cross Abstract: Mapping cyber threat intelligence (CTI) text to MITRE ATT&CK techniques is essential for structured threat analysis, yet manual annotation is costly a

Grok Build is quickly turning into an all-in-one creation environment It can now also generate images and videos with Grok Imagine directly inside your workflow You can create custom visuals for websi

Hey everyone, I constantly see high praise for M3 and M4 Macs for local LLM inference, even the base/16GB models. However, my experience has been quite different, and I'm trying to figure out if I hav

The future of FDE work seems closely related with all work around evals/posttraining/RL envs. FDEs are effectively responsible for the following: 1. Define the business problem. 2. Codify the business

Basically what the title says. For me, it would always crash and burn trying to use tensor split. Apparently, there's some bug where GPU memory gets corrupted with the default microbatch (512) or high

I've been tuning my new Radeon AI Pro R9700, and figured that this would be useful information for people who are trying to optimise their setups. I'm pretty happy with these results and looking forwa

arXiv:2603.14158v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are entering clinical workflows, yet evaluations rarely assess how clinician reasoning shapes model behavior duri

Codex is overoptimised for large models: it ranks 2nd out of 10 for GLM 5.2 but drops to 9th place for Gemma-4! Almost all the effort in this field goes into tuning the weights. We wanted to know how

arXiv:2608.05353v1 Announce Type: new Abstract: LLM judges are often asked to extract criteria and evidence before choosing between candidate answers. This workflow assumes that the intermediate recor

arXiv:2608.05817v1 Announce Type: new Abstract: Metaphor enables the understanding of abstract concepts through cross-domain mappings while conveying affective attitudes. In multimodal scenarios, visu

arXiv:2608.05263v1 Announce Type: new Abstract: Multi-agent orchestration frameworks are moving from demos to production, yet benchmarks typically report task accuracy without diagnosing why a pipelin

arXiv:2608.06167v1 Announce Type: new Abstract: We present a schema-based framework for extracting complex, structured information from unstructured text documents using generative AI, followed by aut

arXiv:2608.05628v1 Announce Type: new Abstract: Although agent skills equip LLMs with reusable procedural knowledge, manual maintenance suffers from high costs, unscalability, and misalignment. Real-w

turns out you can get indirect prompt injection to ~0 on unseen attacks if you stack enough layers (model training + input probes + a classifier checking intent). didn't expect that a year ago. auto m

arXiv:2606.21155v2 Announce Type: replace Abstract: Attorneys, judges, and pro se filers increasingly use AI to draft legal documents, yet these tools frequently fabricate citations. Despite predictio

The tweet is a question from user Simon Willison (posted on 6 Aug 2026) asking which OpenAI API model corresponds to the ChatGPT “GPT‑5.6 Instant” version. No answer or clarification is included in th

arXiv:2608.05004v1 Announce Type: new Abstract: Mental health professionals have raised concerns about risks of psychological harm from interaction with large language models (LLMs), including 'delusi

arXiv:2608.04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why. We introduce canary tools: diagnostic probe tools planted in an agent's Mo

arXiv:2608.04032v1 Announce Type: cross Abstract: Modern chip design relies on electronic design automation (EDA) tools that generate large, heterogeneous artifacts, including source files, scripts, l

One of the things the pelican benchmark is still useful for is visually representing (to a tiny extent) the improvements in a single model family Here's Meta AI's Spark (8th April), Spark 1.1 (9th Jul

arXiv:2505.19840v3 Announce Type: replace-cross Abstract: Deep Neural Networks (DNNs) have achieved widespread success yet remain prone to adversarial attacks. Typically, such attacks either involve f

arXiv:2608.04015v1 Announce Type: new Abstract: With the increase in digitized resources of Classical Latin texts and modern breakthroughs of Large Language Models (LLMs), I contribute to ancient lang

We made an MCP for your phone. Your laptop is just half of your life, and the other half is in your phone. Now your agent gets the mobile screen too. No connectors, no complex setup, it has access to

arXiv:2608.03166v1 Announce Type: new Abstract: Role-Playing Language Agents (RPLAs) are increasingly deployed in high-stakes applications such as healthcare assistance, customer support, and educatio

arXiv:2608.03416v1 Announce Type: new Abstract: Large language models (LLMs) are now regularly asked to forecast real-world events, but comparisons are often difficult because models receive different

arXiv:2608.02643v1 Announce Type: cross Abstract: Computer-use agents (CUAs) operate real desktop and web interfaces through screenshots, mouse and keyboard actions, and stateful UI feedback, yet thei

arXiv:2608.02830v1 Announce Type: cross Abstract: Many-shot in-context learning (ICL) lets vision-language models (VLMs) adapt from image--label demonstrations without weight updates, and is widely as

arXiv:2608.02639v1 Announce Type: cross Abstract: Production prompts rarely carry a single instruction. One system message may require valid JSON, a word limit, three citations, and a fixed tone at th

arXiv:2608.03428v1 Announce Type: cross Abstract: Image based dietary assessment offers a scalable alternative to self reported food diaries, yet fine-grained food recognition remains challenging due

Prime Agent is an open-source coding and research agent for general and long-running work. A self-improving RLM harness for coding and long-running autonomous tasks. Designed to be both token-efficien

arXiv:2608.02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is f

SITUATION DETECTED: Prime Intellect is releasing Prime Agent, a self-improving harness for coding and long-running autonomous tasks. The team reports 95.5% on ARC-AGI-3, above the human baseline, and

Third-party cyber evaluations involving OpenAI models And another one. I had to create a accidental-cyberattacks tag to keep track of them all! This post from OpenAI covers both the UK AI Safety Insti

Threat detection company Vectra AI Inc. today launched Vectra AI Pro, a product built to give the artificial intelligence agents now working inside security operations centers a more reliable read on

arXiv:2608.02878v1 Announce Type: new Abstract: Large language models have shown promise for automated Verilog RTL generation, yet state-of-the-art multi-agent systems plateau at ~95% accuracy on stan

The video is one real run, not a mock-up: grapharc go 'why did checkout latency spike at 09:14 UTC?' --model ollama/qwen3:8b A local 8B model proposes the graph → triage fanning out into four parallel

arXiv:2606.15673v2 Announce Type: replace Abstract: Web agents act through long interaction sequences, yet existing benchmarks evaluate only terminal success, discarding all process information and of

ui: CWD for agent (#26518) server : extend file_glob_search for UI pickers ui : add per-conversation working directory with picker ui : add path navigation and search scope to cwd picker Treat path-li

arXiv:2608.01792v1 Announce Type: cross Abstract: Intelligent document processing (IDP) with vision-language models (VLMs) hinges on confidence scores trustworthy enough to route extractions between a