Text Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation
阅读文章 ARXIV
ArXiv
RAG
CHRONOLOGICAL LEDGER
按时间浏览
2026 年
二月
50 ENTRIESLong Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization
阅读文章 ARXIV
ArXiv
大语言模型
Hunt Globally: Deep Research AI Agents for Drug Asset Scouting in Investing, Business Development, and Search & Evaluation
阅读文章 ARXIV
ArXiv
AI Agent
Claude Sonnet 4.6
阅读文章 HACKER_NEWS
Hacker News
最强开源多模态大模型它来啦——一文详解Qwen3.5核心特性
阅读文章 JUEJIN
掘金
RAG
提示工程的悖论:为什么与 AI 对话比你想象的更难
阅读文章 JUEJIN
掘金
Show HN: I taught LLMs to play Magic: The Gathering against each other
阅读文章 HACKER_NEWS
Hacker News
大语言模型
Show HN: Continue – Source-controlled AI checks, enforceable in CI
阅读文章 HACKER_NEWS
Hacker News
Launch HN: Sonarly (YC W26) – AI agent to triage and fix your production alerts
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Semantic ablation: Why AI writing is generic and boring
阅读文章 HACKER_NEWS
Hacker News
Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue
阅读文章 HACKER_NEWS
Hacker News
Show HN: I built a tool to un-dumb Claude Code's CLI output (Local Log Viewer)
阅读文章 HACKER_NEWS
Hacker News
命令行工具
创业半年，我用5个AI Agent替代了一个团队
阅读文章 JUEJIN
掘金
MCP
Evaluating AGENTS.md: are they helpful for coding agents?
阅读文章 HACKER_NEWS
Hacker News
AI Agent
用 ASCII 草图 + AI 快速生成前端代码
阅读文章 JUEJIN
掘金
大语言模型
一天一个开源项目（第25篇）：Clawra - 为 OpenClaw 赋予「自拍」能力的 Skill
阅读文章 JUEJIN
掘金
大语言模型
When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift
阅读文章 ARXIV
ArXiv
AI Agent
UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128｝｝$ for Unified Multimodal Large Language Model
阅读文章 ARXIV
ArXiv
大语言模型
Tide Commander — 一个用3D战场管理多个AI编程Agent的可视化工具（Claude Code + Codex）
阅读文章 JUEJIN
掘金
AI Agent
Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning
阅读文章 ARXIV
ArXiv
AI Agent
Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
阅读文章 ARXIV
ArXiv
大语言模型
Index Light, Reason Deep: Deferred Visual Ingestion for Visual-Dense Document Question Answering
阅读文章 ARXIV
ArXiv
GPT-5 vs Other LLMs in Long Short-Context Performance
阅读文章 ARXIV
ArXiv
大语言模型
Building for an audience of one: starting and finishing side projects with AI
阅读文章 HACKER_NEWS
Hacker News
AI is destroying open source, and it's not even good yet
阅读文章 HACKER_NEWS
Hacker News
Nvidia with unusually fast coding model on plate-sized chips
阅读文章 HACKER_NEWS
Hacker News
Show HN: Maths, CS and AI Compendium
阅读文章 HACKER_NEWS
Hacker News
Semantic Chunking and the Entropy of Natural Language
阅读文章 ARXIV
ArXiv
大语言模型
LCM: Lossless Context Management [pdf]
阅读文章 HACKER_NEWS
Hacker News
In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach
阅读文章 ARXIV
ArXiv
AI Agent
Asynchronous Verified Semantic Caching for Tiered LLM Architectures
阅读文章 ARXIV
ArXiv
AI Agent
AI Coding 时代下， 关于你会写代码这件事儿， 还重要吗？
阅读文章 JUEJIN
掘金
Rust
Visual introduction to PyTorch
阅读文章 HACKER_NEWS
Hacker News
The long tail of LLM-assisted decompilation
阅读文章 HACKER_NEWS
Hacker News
大语言模型
SkillsBench: Benchmarking how well agent skills work across diverse tasks
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Thanks a lot, AI: Hard drives are sold out for the year, says WD
阅读文章 HACKER_NEWS
Hacker News
Qwen3.5: Towards Native Multimodal Agents
阅读文章 HACKER_NEWS
Hacker News
AI Agent
Anthropic tries to hide Claude's AI actions. Devs hate it
阅读文章 HACKER_NEWS
Hacker News