搜索“Agent”

I / Cybersecurity English 中文 The NVIDIA AI Red Team shares how access controls, sandboxing, network egress restrictions, and secret management can reduce the risks of deploying AI agents at enterprise scale. AI-Generated Summary The NVIDIA AI Red Team assessed multiple AI agents over the past six months and identified four recurring failure modes: lack of access control, tools enabling arbitrary code execution, missing network egress controls, and secrets exposed in plaintext. Prompt-based guard

匹配字段正文

Inside Figma; Engineering; Security Our security team built an AI agent that triages alerts, conducts forensic investigations, queries our security data lake, writes code to fix issues—and remembers what it learns. Here's how we cut alert time-to-resolution by 71% and fundamentally changed how our on-call engineers work. Share How we secure Figma’s internal systems with agents Illustrations by Jimmy Simpson When it comes to protecting our internal platforms, the threats we defend against on Figm

匹配字段正文

Trail of Bits July 28, 2026 open-source , vulnerabilities , machine-learning Page content 1. Let Codex write the goal 2. Define the outcome, not the path 3. Assign one outcome per agent Where human judgment is needed Codex’s /goal feature amplifies bug hunting, but getting good results requires the right prompt, the right scope, and the right number of outcomes per run. For Patch the Planet , our joint initiative with OpenAI to find and fix bugs in open-source software, we pointed Codex at some

匹配字段正文

sounds to humans WER is a necessary metric for many use cases, especially those involving alphanumerics that are not words. But WER is rarely sufficient for enterprise-grade voice agents. 3. Contextual correctness is another challenge Many errors require semantic disambiguation to even define correctness: “read” (present vs past); “lead” (metal vs verb); “Polish” (nationality vs verb); “bass” (fish vs instrument); “live” (verb vs adjective); years like “2026” (twenty-twenty-six vs two thousand t

匹配字段正文

(pass@1 72.7% vs 68.5%) and solves more tasks four-for-four. Kimi K3 wins pass@2 and pass@4 and costs far less, so it is the stronger value pick for high-volume or retry-tolerant agent work. For most teams the best answer is to route between them. In our run, Kimi K3 cost \$4.65 per rollout versus \$8.37 for GPT-5.6 Sol, a little over half the price. Measured per solved task, Kimi K3 returned 14.7 solves per \$100 against Sol's 5.3, about 2.8x the work per dollar. Yes, if you can verify results

匹配字段正文

We removed over 80% of Claude Code's system prompt for more advanced models. How to apply the lessons we learned to your own context engineering in Claude Code and with your own agents. I’ve written previously about how to best prompt the newest generation of Claude 5 models and work with them iteratively to discover what you want to build. But when you send a message to Claude, the prompt is only a small part of the context it gets. Much of your context is assembled from your system prompt, Ski

匹配字段正文

(pass@1 69.9% vs 68.5%) and solves more tasks four-for-four. Kimi K3 wins pass@2 and pass@4 and costs far less, so it is the stronger value pick for high volume or retry-tolerant agent work. In our run, Kimi K3 cost \$4.65 per rollout versus \$13.41 for Claude Fable 5 at its xhigh setting, roughly a third of the price. Measured per solved task, Kimi K3 returned 14.7 solves per \$100 against Fable's 5.3, about 2.8x the work per dollar. Yes. Kimi K3 is an open-weight model from Moonshot AI, so on

匹配字段正文

ected token budget, its reward is instead set to -1. This gives the model a strong incentive to stay within the budget. (The exact reward setup is different for non-verifiable and agentic tasks, and Kimi also uses learned reward models and pairwise comparisons.) To have Kimi K3 support the three reasoning effort modes, the training looked as follows. First, the researchers start by training a max-effort version (“specialist”) with a relatively generous budget. They then lower the budget to train

匹配字段正文

w go profile something. 🤗 Thanks to Noe Flandre for their reviews on the early draft of the post! The blog post was polished using an LLM. This in no way means that we have let an agent run in the background and let it generate the blog. Some of us in the team are non-english speakers and think LLMs (which are mostly trained in the English Language) can rectify silly grammar mistakes or rephrase sentences that sound less intimidating and cleaner. Hope this helps with the idea of "why should I re

匹配字段正文

ext • 10B • Updated Mar 2 • 9.28M • 2.08k xtuner/llava-llama-3-8b-v1 1 Image-Text-to-Text • 8B • Updated Apr 28, 2024 • 34 • 120 Spaces mentioned in this article 1 Running on Zero Agents Featured 37 PRX Pixel 📷 37 Public test Space for pixel-space PRX t2i Collections mentioned in this article 1 Qwen3-VL 782 More from this author PRX Part 3 — Training a Text-to-Image Model in 24h! 69 March 3, 2026 Training Design for Text-to-Image Models: Lessons from Ablations 77 February 3, 2026 Community Thank

匹配字段正文

was real, but reaching it required a caller to set up a state that was extraordinarily unlikely in real-world conditions, so the model logged it as unreachable and moved on. This agent kept going without human intervention and found several higher-impact issues. That discipline is the whole game. The value of the zlib harness came from automation plus a strict definition of what counted as a reportable finding . Without strong validity rules baked into the goal and a model truly capable of eval

匹配字段正文

Contents 1. TL;DR; 2. Why SGLang Is a Good Fit for Agent-Assisted Development; 3. From Prompt Engineering to SKILL: Protocols and Examples; 3.1 Current Skill Stack; 3.2 Recent Optimization and Workflow Examples; 4. Profiling, Review, and Loop Engineering; 4.1 Humanize/RLCR: Adding External Review to the Loop; 4.2 SGLang SOTA Performance Loop (Loop Engineering); 4.3 Codex Goal: A Lower-Cost Loop Implementation; 5. KDA-Based CUDA Kernel Optimization for SGLang Systems; 6. Practice Rules; 7. Acknow

匹配字段正文

are subsidized, by one audience estimate a factor of ten to forty. Angelos’s hope is that optimization, not subsidy, eventually closes that gap. The largest models, he said, have to be subsidized to make economic sense, but he expects smaller, Sonnet-class models to become good enough for nearly all everyday use, at margins that actually work. He already sees the shape of it in agent systems: route each request to the smallest model that can handle it, and reserve the expensive one for planning.

匹配字段正文

Many people reached out to me in the past asking about my local agent stack as well as how I set up my local agent stack. So, I thought it might be useful to put together a little tutorial on how to set up a local (coding) agent using open-source tools and open-weight LLMs. This article is a tutorial on setting up a production-ready coding agent with a fully local stack. We will use a locally served LLM together with a local coding harness that can read files, make edits, run commands, and verif

匹配字段正文

sponse comes back in under two seconds. It now runs in 20 countries, handles around 25,000 calls a month, and resolves a customer’s problem roughly eight times faster than a human agent. AIR, the latest layer, followed in Q2 2025 and pulls in transactional data: it can break down your spending, propose hotels inside a budget computed from your own history, or explain why a stock is moving. Across the arc from the old chatbot to today, the share of cases resolved without a human climbed from 17%

匹配字段正文

oom. That machine restores a saved browser VM, starts Chromium inside it, waits until Chromium is ready to be controlled, and returns a connection URL. That URL is what the user's agent connects to. Browser Use controls Chromium over a WebSocket using the Chrome DevTools Protocol, or CDP. CDP is the remote-control API for Chrome: click this button, type this text, read this page, take this screenshot. Three things made this take longer: restoring the VM's memory, launching Chromium, and keeping

匹配字段正文

about why we built the feature and how we use it ourselves today. Like a lot of people who build software, I felt the ground shift at the start of 2026. The models got better, the agents got better with them, and almost overnight the amount of code moving through my team went up. Between January and March our total issues created and PRs merged both climbed by 50%. That was exciting, and it was also a problem. With that much code moving, I felt the pull to “looks good!” my way through reviews ju

匹配字段正文

ng a high score, it bested the next-highest model, GPT 5.5, by 12 points. The result came at an exorbitant price: $580.87 in API cost for 100 tasks. BU Bench tests whether browser agents can complete real web tasks. It requires agents to handle multi-step navigation, search, information extraction, form filling, dynamic UI interactions, iframes, PDFs, downloaded files, and synthesis across live websites. Its tasks, code, and model scores are available here. Below is Claude Fable 5 compared to ot

匹配字段正文

type of skills are worth making? How do you structure a skill? When do you share them with others? WHAT ARE SKILLS? Skills are folders of instructions, scripts, and resources that agents can discover and use to do things more accurately and efficiently. This blog post assumes familiarity with skills basics; if you’re new, start with our Introduction to agent skills course on Skilljar. A common misconception we hear about skills is that they are “just markdown files.” They’re actually folders tha

匹配字段正文

fic patterns. The lesson was to keep profiling beyond the model. GPU time, queue depth, and model execution all looked normal; the latency spike lived in the Python runtime. Voice agents usually run as a cascade: ASR produces a transcript, an LLM generates the response, and TTS produces audio. ASR is the first stage in that path, so its latency and jitter set the earliest bound on user-visible response time. The optimizations above target different parts of that path. TensorRT multi-profile engi

匹配字段正文