관심도 점수
100
- 검색 slug
- openai-codex
- 실제 연결
- Hacker News, GitHub, arXiv
- 키워드
- the, and, with, codex, openai, for, that, this
- 마지막 수집
- 2026-11-21T07:34:06.976Z
출처별 탭
Remark on Kobayashi's conjecture: a volume Schwarz lemma
This remark offers an expository reconstruction of OpenAI's proof of Kobayashi's ampleness conjecture for compact Kähler manifolds, together with new results. We extract a volume Schwarz lemma for extremal discs and derive a pointwise volume comparison: the volume form of a Kähler metric with $\mathrm{Ric}(ω)\ge-ω$ is bounded below by an intrinsic volume form built from the Kähler--Einstein metrics of pseudoconvex domains containing the Kobayashi--Royden indicatrix. As a consequence, if a compact Kähler manifold $...
Polylogarithmic Approximation for Packing Convex Polyhedra
We study translational packing of convex polyhedra in three dimensions. Given $n$ convex polyhedra in $\mathbb{R}^3$, we seek a placement with pairwise disjoint interiors that minimizes the volume of an axis-parallel bounding box. Constant-factor approximation algorithms are known when rotations are allowed, but no approximation guarantee was previously known for arbitrary convex polyhedra with fixed orientations. A central difficulty is that, unlike in the plane, the total volume and the coordinate extents of the...
Frontier models need only one text to unmask its human or AI author
Given a single text and a simple zero-shot prompt (no web access, tools, candidate lists, or writing samples), frontier models can answer "who wrote this?" at three increasingly specific levels: (1) whether an AI or human wrote it, (2) if an AI, which lab, and (3) if a human, often exactly who. The latest models (Claude Fable 5.2, GPT-6.1 Sol, Gemini 4 Carbon) match trained detectors like Pangram while also explaining their predictions in natural language, and Opus 5.5 names the correct lab for 98% of texts genera...
Hardening JavaScript Programs against LLM-Based Vulnerability Detection
JavaScript programs are often distributed as source code, so attackers can analyze them for vulnerabilities. LLM-based vulnerability detection agents now make this analysis much easier. To mitigate this emerging threat, we present AntiAgent, a defense that lets developers harden their programs against such detection agents. AntiAgent transforms a program before release to impede an agent's analysis. To find effective transformations, AntiAgent evolves a corpus of programs with known vulnerabilities and traces how...
AutoRAGBench: A Benchmark for LLM Agents Automating RAG System Development
Retrieval-augmented generation (RAG) is a well-established paradigm for augmenting large language models (LLMs) with information retrieved from external corpora. However, developing effective RAG systems requires substantial engineering effort and iterative experimentation, as effective design choices vary across tasks and domains. With rapid advances in LLM agent capabilities, we ask how well these agents can autonomously build RAG systems and how effectively they can improve them through iteration. In this paper...
ToolPulse: Side-Channel Eavesdropping on Tool-Using LLM Agents
Large language models (LLMs) are increasingly deployed as agents that translate user requests into sequences of local tool invocations. While prior cache-based side-channel attacks target the locally deployed models, they typically require the adversary to share model-related components or hardware resources with the victim's inference process. These assumptions do not apply to the predominant agentic settings, in which commercial LLMs execute on vendor-controlled infrastructure. We show that agentic execution exp...
ChainAgent: Automated Chainable Vulnerability Discovery in PHP Web Applications
High-impact attacks on PHP web applications often chain limited-capability vulnerabilities with other flaws or intended behaviors. Discovering these chains requires identifying flaws and the dependencies enabling capability composition. Existing vulnerability discovery techniques analyze flaws in isolation, while attack planning assumes known components. This separation makes it difficult to discover previously unknown components whose security relevance becomes apparent only through their potential roles in an ex...
DVBench: End-to-End Benchmark for Real-World UVM Design Verification Agents
Design verification (DV) remains a major bottleneck in hardware development, with large-scale verification using the Universal Verification Methodology (UVM) being highly labor-intensive. Recent advances in large language models (LLMs) and agentic systems offer new opportunities for DV automation. However, existing benchmarks primarily construct mutually decoupled subtasks, which deviates from the real-world workflow. In this paper, we present DVBench, the first end-to-end benchmark for Real-World UVM design verif...
On Hilbert's tenth problem over a quadratic field
In 2026, OpenAI proved that Hilbert's Tenth Problem over the field $\mathbb Q$ of rational numbers has a negative solution. In this paper we study Hilbert's Tenth Problem over the quadratic field $K=\mathbb Q(\sqrt2)$. We prove that there is no algorithm to decide for any polynomial equation $P(x_1,\ldots,x_{48})=0$ with integer coefficients whether it has solutions with $x_1,\ldots,x_{48}\in K$. We also show the existence of a polynomial $f(x_0,x_1,\ldots,x_{25})$ with integer coefficients such that $a\in K$ is a...
Counting $6$-Cliques in $O(n^{5.97})$ time and $O(\log n)$ space
We present an algorithm that, given read-only access to the adjacency matrix of an $n$-vertex graph $G$, computes the number of $6$-cliques in $G$ using $O(n^{5.97})$ time and $O(\log n)$ space. We achieve this by exploiting a decomposition of an equality indicator function underlying, among others, the refutations of the Exponential Time Hypothesis by OpenAI and Anthropic, and of the $k$-Clique Conjecture by Vassilevska Williams and Zamir [arXiv, 2026]. Via known reductions, this implies an $O(1.994^n)$ time and...
openai/codex-plugin-cc
Use Codex from Claude Code to review code or delegate tasks.
cheaper-inference/OmniRoute
Never stop coding. Free MIT AI gateway: one endpoint, 375 providers (150+ free), 1,400+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 900+ contributors
decolua/9router
Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.
Wei-Shaw/sub2api
Sub2API 一站式开源中转服务,让 Claude、Openai 、Gemini、Grok订阅统一接入,支持拼车共享,更高效分摊成本,原生工具无缝使用。
code-yeongyu/oh-my-openagent
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
NousResearch/hermes-agent
The agent that grows with you
router-for-me/CLIProxyAPI
Wrap Antigravity, ChatGPT Codex, Claude Code, Grok Build, Muse Code, Devin as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini Series, GPT Series, Grok Series, Claude model through API
asgeirtj/system_prompts_leaks
Leaked system prompts of ChatGPT, Claude, Gemini and more. The hidden system prompt of every popular chatbot, in full, every version since May 2025. Also Anthropic Claude Code, OpenAI Codex, Google Antigravity, xAI Grok, Meta Muse, Moonshot Kimi, Alibaba Qwen, Z.ai GLM ZCode, MiniMax, Cursor, Perplexity, DeepSeek and 30+ others. Updated daily.
openai/codex
Lightweight coding agent that runs in your terminal
zhayujie/CowAgent
Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.