注册并分享邀请链接,可获得视频播放与邀请奖励。

与「DEMON」相关的搜索结果

DEMON 贴吧
一个关键词就是一个贴吧,路径全站唯一。
创建贴吧
用户
未找到
包含 DEMON 的内容
Some new misalignment disclosures from OpenAI: • Last Sunday morning, one of our models was able to gain unauthorized access to the internet during RL training (~all inference for our most capable models remains stopped until we have hardened our systems further) • In May, a version of HPIM uploaded a employee's GitHub token to the internet, causing the model to be quarantined for two weeks • A new research finding, demonstrating that one can construct self-replicating prompt injections
显示更多
0
65
1.1K
119
转发到社区
Elon has warned for over a decade that AI poses an existential risk. In 2014 he likened it to “summoning the demon.” In 2018 he called it far more dangerous than nukes. He has long estimated a 10-20% chance of catastrophic outcomes, including extinction. Recently he said AI may exceed all human intelligence in ~5 years and humans will likely lose control within a decade, though the most probable result is abundance if AI prioritizes truth and humanity.
显示更多
0
14
130
23
转发到社区
1. We will keep accelerating. Our AI efforts are only 3 years old, vs 6 and 10 years old for Anthropic and OpenAI. If our second derivative remains strong, SpaceX will reach pole position in about 6 months. 2. Once you far exceed the caliber of intelligence needed for a class of tasks, additional intelligence is pointless. You don’t need (and it would be cruel to put) Newton-level intelligence in your toaster! 3. Hardware is hard. Bringing massive compute online rapidly is incredibly difficult. SpaceX has demonstrated exceptional ability in this regard and will only get better.
显示更多
0
1.9K
36.3K
2.8K
转发到社区
I propose that Richmond’s next supportive housing site be located at the location shown below. I invite all councillors who voted for the three-year extension of supportive housing to continue demonstrating their commitment to the community — starting a little closer to home. @CarolDayRmd @Gillanders_L @bogberry 我提议下一个列治文支持性住房的建设点位置如下图中所示,请所有投票支持性住房延长3年的市议员们继续持续为社区的贡献!
显示更多
其实只要认认真真脚踏实地再服务社区多4-8年并让温哥华列治文(里士满)市民看到,2030年或者2034年有志者事竟成。 実のところ、真摯かつ着実にあと4〜8年地域社会への奉仕を続け、その姿をバンクーバーやリッチモンドの市民に見せ続ければ、2030年や2034年には志を成し遂げることができるでしょう。 In reality, if one simply serves the community diligently and steadfastly for another four to eight years—demonstrating this commitment to the residents of Vancouver and Richmond—success is certainly achievable by 2030 or 2034.
显示更多
Here’s to every era, every evil, and every one of you. 🔥 From our inner demons to yours, Happy 30th Anniversary.
0
100
2.3K
312
转发到社区
Which demon Denji? Power and Makima #chainsawman#
0
7
1.6K
51
转发到社区
Launching today… Canary Staked TRX ETF (TRXS) First spot TRX ETF TRX is 8th largest crypto asset by market cap @justinsuntron: "The launch of the Canary Staked TRX ETF demonstrates the growing recognition of the TRON network as critical infrastructure for the global digital economy & provides institutional investors with a new way to access a network that is already powering real-world financial activity at scale."
显示更多
CS 329Z: Engineering AI Agents Stanford / Fall 2026 @stanfordnlp 课程定位:从"模型"到"系统"的工程学 覆盖:简单 LLM 流水线 → 复合 AI 系统 → 自主 Agent。三位讲师的背景也高度互补: @Diyi_Yang(斯坦福 NLP 教授,人机交互与社会计算方向) @michaelryan207(DSPy 核心贡献者,自动评估 AutoMetrics 作者) @jyangballin(SWE-agent / SWE-bench / SWE-smith 作者,软件工程 Agent 领域最重要的研究者之一) # 课程主线:三大工程挑战 贯穿全课的三个核心问题——分解(decomposition)、数据(data)、评估(evaluation)。11 周的内容基本围绕这三条线展开,可以分为五个模块: 模块 1:构建基元(Week 2–3) · LLM 作为构建材料:API/SDK(litellm)、结构化输出、约束生成、解码策略、test-time compute、上下文工程、模型选型与成本/延迟权衡 · RAG:embedding、向量库、分块策略、混合检索、cross-encoder 与 ColBERT 后期交互 · 工具调用:函数调用 API、MCP(Model Context Protocol)、工具设计、代码沙箱、错误处理与重试 模块 2:框架与设计模式(Week 3–5) · 框架层:DSPy(signature / module / optimizer)、LangChain/LangGraph、LlamaIndex,重点是"框架抽象了什么 vs. 你手写了什么" · 设计模式:workflow vs. agent 的分类学,五种可组合 workflow 模式,ReAct / plan-and-execute / reflection,"scaffold(脚手架)本身就是设计决策" · 记忆架构:短期/长期记忆、记忆作为工具动作、文件系统作为外化记忆、跨 Agent 记忆(MemGPT、Mem0、Generative Agents) · 多 Agent 系统:编排模式、handoff 与状态传递,以及一个很有态度的对照阅读——既读 AutoGen,也读《Why Do Multi-Agent LLM Systems Fail?》和 Neubig 的《Don't Sleep on Single-agent Systems》 模块 3:优化(Week 5) · 从提示词到微调的全景:GEPA、MIPROv2、OPRO、TextGrad(提示优化);LoRA/QLoRA、蒸馏、RLHF/DPO(权重优化);test-time scaling(推理算力) · 核心问题是决策框架:什么时候优化 prompt、什么时候优化 weights、什么时候堆推理算力 模块 4:数据与评估(Week 6–8)——最有分量的部分 · 数据:trace、demonstration、feedback 三类数据;训练数据 vs. 评估数据;数据飞轮;合成数据;从 Agent 轨迹构建数据集(SWE-smith) · 评估基础:为什么 eval 难;4 元组框架(request / environment / stopping criteria / scorer);好 benchmark 的性质;tinyBenchmarks · 评估基础设施:三类 grader、LLM-as-judge 的 prompt 设计与已知偏差、pairwise vs. pointwise、非确定性指标 pass@k vs. pass^k、harness 设计 模块 5:安全与前沿(Week 8–11) · 安全:工具访问的隐私风险、prompt injection(含间接注入)、红队、沙箱与权限模型、输出护栏、human-in-the-loop · Coding Agent:SWE-agent、Claude Code、OpenHands 的端到端架构对比 · 主动式 Agent:从 reactive 到 proactive,General User Models(GUM)、Next Action Prediction,以及"Agent 何时应主动、何时应等待"的 mixed-initiative 问题 · 开放问题:多模态/web/计算机使用 Agent、科学 Agent、长时运行架构、生产可观测性(tracing、monitoring、成本管理) # 作业设计:一手建、一手评 HW1:从零构建 Agent 系统(10%) 给定论文库,构建能检索并推理回答科学问题的 Agent。 · Part A:只用 litellm 手写 RAG + 工具调用 + ReAct 式 Agent 循环 · Part B:用 DSPy 重建关键组件,并反思框架抽象了什么 HW2:评估一个 Agent(10%) 给定一个预构建 Agent,设计完整评估套件:代码型 grader、至少一个 LLM-as-judge、用 4 元组框架构建 benchmark 任务、错误分析。
显示更多
0
23
148
30
转发到社区
Cyberleak fakest demon ever bro
0
46
26.5K
517
转发到社区