TGTGInsighttelegram intelligenceLIVE / telegram public index
← GitHub Trends

TGINSIGHT SIMILAR POSTS

Find similar content

Source channel @githubtrending · Post #15349 · Dec 20

#python#ai#bug_detection#code_audit#code_quality#code_review#developer_tools#devsecops#google_gemini#llm#react#sast#security_scanner#supabase#typescript#vite#vulnerability_scanner#xai **DeepAudit** is an AI-powered code audit tool using multi-agent collaboration to deeply scan projects for vulnerabilities like SQL injection, XSS, and path traversal. Import code from GitHub/GitLab or paste snippets; agents plan, analyze with RAG knowledge, and verify issues via secure Docker sandbox PoCs, generating PDF reports with fix suggestions. Deploy easily with one Docker command, supports local Ollama models for privacy, and cuts traditional tools' high false positives. **You benefit** by automating secure audits like a pro hacker—saving time, reducing errors, ensuring real exploits are caught, and speeding safe releases without manual hassle. https://github.com/lintsinghua/DeepAudit

Results

2 similar posts found

Search: #phi

当前筛选 #phi清除筛选
科技&趣闻&杂记

@kejiqu · Post #3318 · 05/01/2025, 08:14 AM

微软发布 Phi-4 系列小语言 AI 推理模型,AIME 2025 跑分超满血版 Deepseek R1 微软发布了Phi-4-reasoning系列推理模型,该系列包括Phi-4-reasoning、Phi-4-reasoning-plus和Phi-4-mini-reasoning三款模型。Phi-4-reasoning模型拥有140亿参数,通过监督微调Phi-4并结合OpenAI o3-mini的高质量推理演示数据训练而成,专为复杂推理任务设计。Phi-4-reasoning-plus版本通过强化学习提升性能。Phi-4-mini-reasoning是一款基于Transformer的紧凑型语言模型,专为计算资源有限的环境设计。该系列模型在数学推理和代理型应用中表现出色,在多项数学基准测试中,性能超越OpenThinker-7B等模型,部分测试接近OpenAI o1-mini水平。IT之家 | Microsoft 🏷#Phi#reasoning#模型#推理 📢频道👥群组📝投稿

耕读频道

@iGengdu · Post #440 · 08/03/2024, 12:17 PM

#AI#Github Models #微软#免费体验#Llama 3.1 #Mistral Large 2 #Phi-3 #GPT-4o #GPT-4o mini 分享我的一篇博文:微软Github发布Github Models,为用户免费提供AI大模型体验场所 更多AI资源,请访问智汇AI网(SumeAI):https://www.sumeai.com 📢频道✈️ 群聊 (耕读) 📬投稿