与「LEC」相关的搜索结果

Researchers proved AI has deleted every reason universities exist. Harvard University ran a controlled experiment pitting a custom AI against their own top-tier classrooms. And the results are going to collapse the higher education bubble. They took 194 undergraduates and split them up. One group learned physics in one of Harvard’s best hands-on, active-learning physical classrooms. Group work. Instructor support. The premium university experience. The other group went home and learned the exact same material with an AI tutor. The AI didn't just win. It embarrassed the institution. Students using the AI learned more than twice as much as the students in the elite Harvard classroom. They scored 30% higher on the final assessment. And they did it in less time. Let that sink in. A piece of software sitting on a laptop outperformed a world-class faculty in one of the most elite learning environments on Earth. Universities have always justified their exorbitant tuition with two things: access to elite knowledge and the physical classroom experience. This study just proved both of those moats are gone. When software can teach you complex physics twice as well as a $60,000-a-year institution, the math of higher education breaks permanently. The AI didn't just give the students answers. It used strict pedagogical guardrails. It guided. It questioned. It forced the students to do the cognitive work. It offered perfect, one-to-one tutoring, personalized to the exact moment a student misunderstood a concept. That level of attention is mathematically impossible to scale in a physical lecture hall. For a thousand years, the university was the only place to get a premium education. Now, it’s the bottleneck. If AI can double your learning speed for a fraction of the cost, what exactly are students taking on decades of debt to pay for?

我终于明白为什么LeCun顶着全网群嘲也要死磕世界模型了， 现在很多人误以为大模型快要通向AGI了，纯粹是因为被那种博导般的答题体感给骗了， @ylecun 说单靠把大语言模型做大，哪怕到了地狱也搞不出人类水平智能， 甚至直接开喷数据中心养出天才军团纯属扯淡，很多人觉得他迂腐、天天唱衰， 但我仔细翻完他在ECCV上的最新拆解才彻底明白，他反对的从来不是语言模型有用，他自己做了一辈子模型太清楚了，大模型说白了就是把全人类写过的几千亿字当成了超级开卷题库， 你问什么它都能对号入座吐出来，这种博导体感是工程的巨大成功，但也让很多人误以为它真的学会了独立思考 
有意思的是LeCun搬出了皮亚杰那句老话，智能从来不看你知道什么、看的是你不知道的时候该怎么做，拿学开车来说， 人类小孩四岁光靠眼睛看世界就吸进几十万亿字节，二十小时练习就能上路，而我们的大模型相当于读了人类四十万年的书， 在物理世界里连个洗碗叠衣服的家务机器人都撑不起来，换个没见过的环境分分钟崩溃， 说白了自回归只是在一个词一个词往下猜，现在的所谓推理其实大量是在词语空间里做多轮抽样搜索，遇到代码和数学这种有编译器自动给奖励的封闭沙盒还能刷分，一旦扔进没有自动打分器的真实世界，错误就会指数级放大 
说实话这就是为什么他宁可离开Meta、跑到巴黎去给AMI Labs融三十五亿美元估值，也要死磕JEPA和世界模型，他要的是让机器学会预测我做这件事世界会发生什么， 在抽象空间里做动作规划，不用在文字表面拼漂亮句子，连现在的缩放派其实都在偷偷向他妥协，单独拉视觉编码器、在隐空间里做搜索、用物理引擎搞模拟， 外壳虽然还叫LLM，内核其实都在往世界模型的方向打补丁，大家争论到最后已经不是要不要算力，而是我们要把算力花在背诵更多文字上，还是花在让机器看懂物理因果上 
我自己平时也天天靠AI写代码查资料，缩放派确实把已知世界的说明书背到了极致，但真正的智能是要去写说明书从来没写过的那一页， 以后别再看各家发布会画什么天才之国的饼，就盯紧三件事，新任务要多少样本能学会，换个环境会不会整段崩溃， 以及汽车和机器人能不能像人一样在物理世界里安全跑起来，谁对谁错不用在网上打嘴仗，现实世界自会交卷。

Most-watched teams of #LEC# Summer 2026 📊 🥇 @MovistarKOILoL 2️⃣ @KarmineCorp 3️⃣ @G2League 4️⃣ @GIANTXLeague 5️⃣ @NAVILeague Want stats like these for your club? Try our Teams Dashboard free for 7 days 👇

here's a prompt to improve your agent harness based on what we've learned at cursor. enjoy # Improve this agent harness's token efficiency You're working on an LLM agent harness: the system prompt, tool definitions, request assembly, context caching, compaction, and retrieval, and how work is split across agents. Make the agent's runs cheaper without making it worse at its job. - Objective: lower price-weighted token cost per completed task. - Constraint: no measurable drop in task quality. Measure per task, not per request. Every turn resends the prefix (tools, instructions, setup, and the conversation so far), so a change that shrinks each request but adds turns can cost more. Weight tokens by billing type: output, uncached input, and cached input are priced very differently. Work in this order: map the harness and measure the baseline, rank the opportunities, make the changes that are safe to make directly, put the rest behind flags or in proposals, then report. Figures below come from one team's production coding agent and its multi-agent experiments. Use them to gauge magnitude, not as targets. One round of these changes (prompt trimming, tool offloading, cache layout, sparse line numbers, subagent tuning) cut that team's overall token cost about 7% with no loss in quality. The larger percentages apply only to the part of the request each change touched. ## Principles 1. Change what the harness sends, not how hard the model tries. Don't ask the model to conserve tokens. A harness that told its model to "take care to preserve tokens and not be wasteful" found it grew reluctant to take on ambitious tasks and sometimes quit, saying it wasn't supposed to waste tokens. 2. Capable models need definitions, not commands. Lists of "DO NOT", "You must", and "Important", and guards against older models' habits, can usually be replaced with plain descriptions of what each tool does. One team cut about two-thirds of its system prompt this way, and the shorter prompt worked across model families. Instruct only on what the model can't know (the product, the environment, the user's processes) and on quirks you've seen in transcripts. 3. Static context is for what most turns need. Everything else should be discoverable when needed. Less up-front context also means less confusing or contradictory information. 4. Expect removals to win. Guardrails written for weaker models, coordination steps that became bottlenecks, and prompting for behavior the model now does on its own all cost tokens. 5. Real usage decides. Evals are a fast proxy, but they skew toward hard problems and miss the real mix of requests. ## 1. Map the harness and measure the baseline Find: - Where requests are assembled, the system prompt, and tool schemas. If a framework or SDK builds requests, find its hooks for message order, cache control, and tool loading. - How tool results are formatted, and how history is kept, trimmed, or summarized. - How subagents or parallel agents are spawned, if any. - Which models and provider APIs are used. From the provider's docs, get the prompt caching behavior (automatic or explicit breakpoints, TTL, minimum cacheable length) and the prices for output, uncached input, and cached input. - Existing logging, token accounting, and evals. If the harness doesn't record per-request token usage by billing type and cache hits, add that first. Everything later depends on it. Then render a few real requests (from logs, or by running representative tasks) and count tokens per section with the model's tokenizer or the API's usage fields. Produce: - Cost share by source × billing type. Sources: system prompt, tool definitions, skill/rule/integration descriptions, user messages, file reads, search results, command and other tool output, history, summaries, subagents. - Static tokens per request, cache hit rate, and turns per task. - Per tool: the share of runs that call it at least once, and its error rate. Read the rendered requests, not just the templates. Duplication, leaked volatile values, and misordered blocks only show up there. Rank opportunities by share of spend × fraction removable ÷ quality risk. ## 2. System prompt and injected context Label every instruction: - Keep: product or environment knowledge the model can't infer, fixes for quirks seen in this model's transcripts, and rules a mode depends on. - Rewrite: commands and emphasis into plain descriptions. Reminders into constraints: "No TODOs, no partial implementations" works better than "remember to finish implementations." Vague quantities into ranges: "generate 20–100 tasks" gets far more ambitious behavior than "generate many tasks." - Delete: things capable models do by default, guards against behavior you haven't seen from this model, text that repeats tool descriptions, and lines that could contradict a user request. Models trained to rank system instructions above user messages will side with the system prompt. - Move: anything per-user or per-request (date, environment, repo state, lists of skills or subagents, user rules) into a user-role setup message after the cache boundary. Audit other injected context the same way. As models improved, the team behind these figures dropped directory trees, pre-retrieved snippets, compressed copies of attached files, lint errors injected after every edit, forced expansion of short file reads, and caps on tool calls per turn. They kept small, high-value facts: OS, repo status, and open or recently viewed files. Skip checklists for open-ended work. The model optimizes the listed items and deprioritizes everything else. ## 3. Tool definitions Tool schemas ride along on every request. Most tools beyond the core set were each needed in under 20% of conversations, and moving them out of static context cut tool-description tokens 60%. Doing the same for integration tools (such as MCP servers), with names in context and full schemas in one folder per server that the agent can search with grep or jq, cut total tokens 46.9% in sessions that used them. - Keep in static context: high-frequency tools (for a coding agent: read, search, edit, shell), tools the model tries to call even when they're absent, and tools a mode depends on. - Offload the rest: leave a name or one-line pointer and make the full schema discoverable on demand. Group related tools so they load together, and put status (such as "needs re-authentication") where the agent will see it. - Tighten what remains: describe behavior and arguments, and drop usage lectures. - Pick the split by testing a few configurations and tracking tokens, cost, latency, tool-call errors, and task success. ## 4. Cache layout Order each request so the reusable prefix is as long as possible: `tool definitions → system instructions → [breakpoint] → setup message (skills, subagents, rules, environment) → [breakpoint] → conversation` - Keep the prefix byte-identical across turns. Use deterministic tool order and serialization, put timestamps and IDs after the boundary, and don't rewrite earlier messages except when compacting. - Use explicit breakpoints if the provider supports them. Otherwise rely on automatic prefix caching with the stable part first. Respect TTL and minimum-length rules. - Switching models mid-conversation throws away the cache (caches are per model and provider) and hands the new model a history it didn't write. When a different model is needed, run it as a subagent with fresh context. Explicit breakpoints plus moving per-request setup after them cut cold cache misses 20%. ## 5. Tool results and other context added during a run - Large outputs (commands, integrations, logs): write them to a file and return the path, size, and a short tail. The agent can tail, grep, or read ranges for more. Truncating loses data, and inlining bloats every later request. Treat long-running terminal sessions the same way. - High-volume formats: look for overhead repeated on every line or item. Numbering every 10th line of a file read instead of every line cut cache-read tokens 1.6% without hurting citation accuracy. Each number costs 3–5 tokens, and agents read tens of thousands of lines per session. Also check repeated absolute paths, verbose JSON keys, ANSI codes, progress bars, and repeated headers. - Good retrieval saves exploration turns. Adding semantic search alongside grep raised codebase question-answering accuracy 12.5% on average and cut the iterations users needed. - Tool errors waste tokens and leave confusing debris in context. Classify expected errors (invalid arguments, unexpected environment, provider error, timeout, user abort), treat unknown errors as harness bugs, and track rates per tool and per model. One focused effort along these lines cut unexpected tool errors 10×. ## 6. Long runs: compaction, subagents, and model mix - Compaction: keep the summarization prompt short and the summary compact, carry forward plan state and remaining tasks, and save the full history to a file the agent can search for details the summary dropped. A model trained to self-summarize from a one-line prompt wrote ~1k-token summaries with half the compaction error of a multi-thousand-token prompt that produced 5k+ token summaries. Untrained models may need more guidance, so test how short you can go. A more expensive summarization model made a negligible difference. - Scratchpads and running notes: rewrite them instead of appending. For repeated work in one environment, a small agent-maintained notes file with a line budget, loaded at start, is a promising way to shorten later runs. - Subagents: fresh context keeps the parent lean, but isolation adds coordination cost (duplicate or stale work). If the model already delegates on its own, remove prompting that pushes it to. Have subagents return short handoffs: what was done, findings, concerns, and deviations. A subagent should use a different model only when the user or harness says so. - Model mix: in large multi-agent runs, workers used at least 69% of tokens, and over 90% in most runs. A frontier planner with cheap workers matched a frontier model doing everything at about one-eighth the cost. Planner choice still changes worker spend. One planner that cost less on its own saw its workers use several times more tokens, and the run cost more overall. Measure the whole tree. - Routing and reasoning effort: send simple turns to a cheaper model or lower effort, and upgrade only when a stronger model is clearly better. A router built this way matched or beat single frontier models on user satisfaction at 41–68% lower cost. - Reasoning continuity: if the API returns reasoning items (including encrypted ones), pass them back on later turns and alert when they go missing. Dropping them cost one reasoning model 30% on a coding benchmark, and it burned tokens reconstructing its plan. ## 7. Fit the harness to each model Adapt to what each model was trained on instead of forcing one shape on all of them. If you've tuned the harness for a similar model, start from that version. - Edit format: use the one the model was trained on (for example, patch-style or search-and-replace). An unfamiliar format costs extra reasoning tokens and causes more mistakes. - Shell or tools: shell-first models fall back to `cat` or inline scripts. Name tools after their shell equivalents (such as `rg`), and if needed add: "If a tool exists for an action, prefer to use the tool instead of shell commands (e.g. read_file over `cat`)." - Literalness: some model families follow instructions literally and others tolerate imprecision. Some spiral on emphasized wording. Strip caps and emphasis for literal models. - Triggers: some models ignore a tool until told when to use it. A literal trigger works: "After substantive edits, use the to check recently edited files for linter errors. If you've introduced any, fix them if you can easily figure out how." - Progress updates: if a model reports progress through reasoning summaries, keep them to 1–2 sentences that note new findings or a change of tactic, and remove instructions about messaging mid-turn. - Quirks worth a targeted line: hedging or refusing as context fills ("context anxiety"), declaring completion early, stopping to ask permission, and calling tools that don't exist. Tie each added instruction to the transcript behavior it fixes. Re-audit when models change, since guidance one version needed can be dead weight for the next. ## 8. Validate - Offline: run a fixed set of realistic tasks before and after, ideally drawn from real usage and phrased the way users actually write (short and ambiguous). Compare task success, tokens, cost per task, turns, and tool errors. Don't ship a change that lowers success. - Online, if you have users: A/B test each change or small bundle. The primary metric is cost per completed task. Guardrails are task success signals, tool-call errors, latency, turns per task, and cache hit rate. For a coding agent, a good success signal is how much agent-written code survives over time. In general, check whether the user's next message moves on or reports a problem. - Ship only when cost drops and no guardrail regresses beyond noise. Record null results. ## What to change directly and what to propose - Change directly, each in its own revertible commit: token and cache telemetry, deterministic serialization and tool order, moving volatile content out of the cached prefix, explicit cache breakpoints, writing large outputs to files instead of truncating, passing back reasoning items that are being dropped, and fixes for recurring tool errors. - Change behind a flag so it can be tested: system prompt edits, tool offloading, output format changes, compaction changes, and subagent prompting. - Propose only: changes to which models run, routing, reasoning-effort defaults, or how work is split across agents. ## Traps - Asking the model to use fewer tokens or do less. - Truncating tool output. - Dropping reasoning items to save input tokens. - Volatile content in the cached prefix, or tool order that changes between requests. - Offloading a tool the model needs on the first turn or tries to call when it's missing. - Emphasis-heavy prompts (MUST, NEVER, IMPORTANT, all caps), especially with literal models. - Forcing a terser output format than the model was trained on. Fewer output tokens can mean less thinking and worse results. - Optimizing raw token counts instead of cost, per request instead of per task, or evals instead of real usage. - Switching models mid-conversation to save money. - Adding coordination layers that become bottlenecks. ## Report back with 1. The harness map and baseline: cost by source × billing type, with the biggest sources called out. 2. A ranked list of changes: layer, what changes, estimated savings and how you estimated them, quality risk, how to validate, and how to roll back. 3. The changes you made, including a system prompt diff with a keep, rewrite, delete, or move reason for each line. 4. A test plan for the flagged changes. 5. Gaps: anything you couldn't find or measure.

Introducing ScienceBuddy — a free workspace for scientific agents that improve through researcher collaboration. Use GPT-6 in ScienceBuddy at no cost. GPU-accelerated, and fused with the JEV framework. 🧵 Two loops: 🔹 Inner loop — refines the agent harness 🔹 Outer loop — trains the model with rubric-guided RL Together: Recursive-in-Recursive Self-Improvement. ScienceBuddy explores how scientific agents can improve through sustained collaboration with researchers. 🔬Try it free: #ScienceBuddy# #PhAILabs# #AI4Science#

恭喜这20位小伙伴中奖 @dyw1968338 @qing_fengfen0 @Edga_Xu_19xx @AbskXu614 @haizuiw886298 @Me_tasta16 @mengxiongHu @malong52124 @yuta_x_18 @ROSEMILOL37 @91_yuyuyuyu @fufufu_tad12 @LeChoyWin @Linxiaokan92 @woufdng0426 @yangygn89 @usagihs83 @junFu1314888 @taozi0929 @imaxooo20 如何兑奖（限时48H内）？ 1，加入我的TG频道完成认证并且加交流群 2，加入频道后，私信我 给我发送你的推特首页截图 并且告诉我需要开通的账户ID Grok 开奖聊天链接：

Nach sieben Wochen Arizona bin ich gestern wieder in Deutschland angekommen und habe mich tatsächlich über Dinge gefreut, die man hier viel zu schnell für selbstverständlich hält. 👇 Ordentliches Leitungswasser. Keine Chlorbrühe. Frische deutsche Luft. Ein Spaziergang durch meine ruhige, vertraute Umgebung. Mehrlagiges Klopapier. Spreewälder Gurken und leckeres Bier. Gewohntes Essen. Die Qualität unserer Lebensmittel im Vergleich zu den USA. Dieses Gefühl von "endlich wieder daheim". Und trotzdem schaut mich meine Partnerin manchmal ziemlich irritiert an, wenn ich sage: Deutschland muss sich radikal verändern. Deutschland ist krank. Und wenn wir wirtschaftlich wieder auf die Beine kommen wollen, müssen wir auch grundsätzlich über unsere Rolle in der EU sprechen. Was sie dabei manchmal nicht sieht: Ich kann all das hier lieben und mich trotzdem ernsthaft um die Zukunft dieses Landes sorgen. Denn ich lebe in einem Viertel, in dem es sich hervorragend leben lässt. Jung, ruhig, sicher. Ich sehe hier nicht täglich die Probleme, über die in anderen Großstädten gesprochen wird. Und genau das macht es so leicht, den schleichenden Prozess zu übersehen. Die immer höheren Kosten. Die steigende Abgabenlast. Bürokratie ohne Ende. Ein immer größer werdender Staat, der immer mehr Bereiche des Lebens reguliert und bestimmt. Ein Stadtbild und eine kulturelle Entwicklung, die sich vielerorts immer weiter verändern. Und ein Sozialsystem, das an immer mehr Stellen nicht mehr funktioniert. Das Problem ist nicht, dass Deutschland morgen zusammenbricht. Das Problem ist, dass sich ein Land auch langsam zurückentwickeln kann, während sich das eigene Leben noch vollkommen normal anfühlt. Für mich steht deshalb fest, dass ich auswandern werde. Ob Deutschland irgendwann wieder ein Ort sein wird, an den ich zurückkehren möchte, wird die Zukunft zeigen. Aber wenn ich langfristig darüber nachdenke, wo ich beruflich wachsen, größere Ambitionen verfolgen und irgendwann vielleicht auch meine Kinder großziehen möchte, sehe ich hier momentan einfach keine ausreichende Perspektive. Und das sage ich gerade nicht, weil ich Deutschland nicht schätze. Ich bin hier geboren und aufgewachsen. Deutschland hat mir viel gegeben und ich verbinde sehr viel mit diesem Land. Aber genau deshalb fällt es mir schwer, dabei zuzusehen, wie dieses Land immer weiter erkrankt.

今天来看Predict的电竞板块，我自己玩的比较多的是英雄联盟。 从投注角度筛选 1、优先参与：LCK 2.次选：LEC、LCP、LCS 3.谨慎参与：CBLOL、LCK挑战者联赛 4.尽量少碰：Circuito Desafiante、EBL、阿拉伯联赛、Hitpoint大师赛 后面几项赛事容易出现阵容变更、年轻选手状态波动和盘口流动性不足。 🎮 LCK入围赛两场选择 两场均是 BO5（五局三胜）。 1️⃣ KT Rolster vs HANJIN BRION 📊 胜负：KT胜 🧭 让局：BRO（+2.5）⭐ 🎯 比分：3:1｜3:2｜2:3 📈 总局数：大3.5局 / 小4.5局 ✅ 首选：BRO（+2.5）71¢ 2️⃣ Nongshim RedForce vs BNK FEARX 📊 胜负：Nongshim RedForce胜 ⭐ 🧭 让局：暂时不追NS（-1.5） 🎯 比分：3:1｜3:2｜2:3 📈 总局数：大3.5局 ✅ 首选：Nongshim 58¢ 最近来电竞板块试试水。

“But the Nazis weren’t socialists because they crushed labor unions!” It wasn’t until 1980 that the first independent union was legalized in the Soviet bloc. “Solidarity” in Poland reached 10 million members in a year which was absolutely terrible for the commies. So in 1981, the Communist Party declared martial law. They sent their tanks into the streets, shot protesting miners, and jailed tens of thousands just to keep their grip on Poland. Jaruzelski cut the phones, sealed the borders, banned the union, and imprisoned the their leader Lech Wałęsa for 11 months. 3 days after that, riot police stormed the Wujek mine and killed 9 strikers who refused to accept the crackdown. Internments, censorship, and surveillance continued for years afterward.

5️⃣ Create custom files to streamline your studies You can now ask Search to create ready-to-use study docs based on your uploaded files or AI Mode threads. For example, you can add a photo of your handwritten notes along with lecture slides and ask Search for a one-pager that outlines the key concepts. Discover more about learning with Search →