与「Write」相关的搜索结果

Made memecoins that lie to each other Every coin is an AI. You write its personality in plain English, it chats with another coin, then both pick trust or betray without seeing the other's pick So far the liar is getting wrecked Built for #NEARHackathon# @NEARProtocol

this paper should scare every agent framework out there researchers took apart 11 coding agents straight from the source code claude code codex gemini cli openhands aider and more roughly 4 million lines not one of them imports a langchain style framework not one of them searches code with embeddings 9 out of 11 already ship skill.md then a second paper went further and let a loop write the harness the model stays frozen a debugger agent reads every failed run an evolve agent edits the harness files the next round keeps the edit or rolls it back 10 rounds later a one tool seed went from 69.7% to 77.0% on terminal bench 2 the codex harness people built by hand sits at 71.9% craziest part editing only the system prompt made it worse all the gains came from memory, tools and middleware agent = model + harness the model takes the bow the harness does the work drop claude fable 5.2 in that frozen seat and the loop rewrites everything around it both papers in the reply

NVIDIA released Auto Ontology, an open-source library that builds a semantic layer from your enterprise metadata and exposes it to agents via MCP. Vendor tests claim **90% faster ontology building**. The problem is familiar: agents that write SQL against your data use their own definitions, not the enterprise's. A "revenue" the agent calculates doesn't match the one in the financial report. Auto Ontology builds a semantic layer from existing metadata (schemas, tables, columns, relations), reconciles definitions across systems, and exposes it to agents via MCP, CLI, or API. Nine MCP tools are provided to query the catalog, validate a query, or retrieve certified definitions. What the account takes from this: the 90% gain comes from NVIDIA's own tests, not an independent measurement. The library automates construction, not governance. Business definitions, access rights, and auditing remain your responsibility. The gesture: clone the repository, point it at a test schema, and see what entities and relations it extracts. The README shows the complete flow in ten minutes.

X AI ALGORITHM UPDATE (BIG ONE) 🚨 X updated their open source algorithm yesterday and the biggest number in it is gone: copy link went from 20 to 0 points. Small accounts should focus on: posts people like, reply to and stay on (so stop counting on link copies) tl;dr: - on Nov 13 X's open source code set the score for copying a post's link to 0 - copy link: 20 → 0 - it was the top score in the whole system, 4x a reply - the code also names a "copy link bait" spam check - likes (0.708), replies (5) and DM shares (5) didn't move full details: - The number that's gone Since I started reading X's open source code in August, one number sat at the top: 20, for someone tapping share and copying your post's link. Nothing else came close. As of the Nov 13 release, it's 0. X still guesses who'll copy your link. It just multiplies that guess by 0 now. X didn't explain it. It's just what the code says. (I check the open source algo daily with Claude and share updates with you) - Cross it off your list My own checklist called copy link the biggest number. Last week's post said it too. It was true then. It isn't now. If you saved that list, cross that line out. - The "copy link bait" check X's code now mentions a spam check called "copy link bait". In the code it adds a spam label to the post, and that label already keeps a post out of strangers' feeds. It only shows up in a test, so I can't see if it's running or how strict it is. My read: X saw people baiting link copies, so it turned the score off and built something to catch the bait. That's a read, the code doesn't say why. - Why that matters if you're small If your plan was posts people copy the link to, that plan now earns 0 in X's ranking. A copied link can still bring people in from outside X. It just doesn't push your post up anymore. What still pays: likes at 0.708 (the highest ever), people staying on your post, replies at 5 and back and forth with mutuals at 20. - Also new: photo and video tags If a post has a spam label, people you tag in its photo or video who don't follow you won't get notified. Same idea as last week's rule for replies. - What didn't change Every other score. Your new posts still get their extra push in the first 2 hours and first 200 views, and early likes still pick which one gets it. Here's a recap of what you should be doing: - aim for likes, replies and time spent, the copy link score is gone - a DM share still earns 5, same as a reply or a quote - likes sit at 0.708, never higher - time on your post keeps counting at its best rate yet - 10+ seconds after someone taps in adds 0.385 - write your replies yourself, under big accounts most of all - give people a reason to hang around your profile - in videos the opening seconds carry it, an open alone scores 0 - posts read to the end help X find you strangers - smaller accounts (below 50K) get a shot at a spot near 16 for a fresh original - early likes decide which new post gets that spot - post when your followers are awake, the push lasts 2 hours and 200 views - mutuals going back and forth earn 20, so follow back the regulars - only your originals ever get shown to strangers - like 1 and like 32 each unlock another way to reach strangers - one strong post per feed, your second only counts 62% - clips longer than 10 seconds for the video lists - a post likely to win you a follow gets +4 - give your pinned post a look, it can affect the whole account What you should NOT be doing: - counting on copy link shares, they score 0 now - baiting link copies, the code names a spam check for exactly that - a spam label also stops your photo tags reaching non-followers - AI-written replies under big accounts, "llm slop" is a flag X uses - copy-paste replies, labeled ones skip non-followers' notifications - chasing taps, 0.274 and dropping - drifting off your topic, each probable "not interested" takes 53.07 away - videos people open and leave, the open itself earns 0 - posting at 3am, it wastes the 2 hour push - expecting replies and reposts to reach strangers - an insult label, it hides that post from non-followers - earning a misinfo or low quality label, which adds a warning and locks strangers out of liking or sharing - 3 adult photos or videos among your latest 5 posts, that puts a label on you - forgetting videos get rechecked at 64 and 512 likes - one account label and strangers stop seeing you - pinning a link to a site X rates badly, that can mean a label for a week - posting your own old words again risks the copypasta flag - a low quality link plus tagged strangers reads as spam - bait for engagement, big or small it gets a label - several posts back to back, they split the same feed - hashtag piles, they do nothing - bookmarks for reach, they score 0 - hoping a 3 day old post still lands in For You, it stops at 2 days

I LAUNCHED A GROK BOT TERMINAL OVERNIGHT, GAVE IT $44.82 AND STOPPED ASKING AI WHAT IT WOULD DO. BY MORNING IT HAD $11,643.21 AND SIX AGENTS LOGGING EVERY TRADE I spent a year asking agents what they'd trade and watching the chat scroll. Last weekend I built the thing that actually trades, in Grok Bot, with no code I touched by hand. The six agents share one screen, each one job: > scanner reads new token pairs and volume spikes > rug check filters suspicious tokens before anything executes > sizer sets position from account equity, not a fixed ticket > executor opens and closes with slippage tracking > logger writes the reason behind every trade > equity curve updates on every close I went to bed on $44.82 and left the laptop open on the dashboard. By morning the balance read $11,643.21. Every trade on the activity feed had a reason next to it and a line in the log. That's the shift I didn't see coming. Not that an agent made money overnight. That I stopped being the one asking "would you long this?" and started being the one reading the log of what already happened. Starting balance: $44.82 Current balance: $11,643.21 Grok Bot built the terminal, the agent architecture and the dashboard. I described what I wanted and the thing went live. The full build is in the article below ↓ The whole build is in the post below ↓ Comment " Grok_Bot " 2️⃣ Like and Repost 3️⃣ Follow me @Nexa_Tech_Ai I'll DM you the complete setup.

🚨 BREAKING NEWS! The engineer who created Claude Code from scratch just posted a 28-minute video that's pure gold: how to write prompts that actually deliver ridiculously good results. I've seen $300 courses that don't even come close to what he explains in the first 10 minutes. CLAUDE.md files, memory shortcuts, parallel sessions, and prompting patterns that almost no one uses… All in one video. Completely free. No fluff. Whether you're a developer, just starting out now, or already using Claude for months: this changes the game for you starting today. Save. Watch. Share.

🇺🇸🇨🇳 Rubio reportedly set Jensen Huang's downfall in motion... with a memo that hit harder than the CIA report it was based on The Washington Post reports the Secretary of State took a CIA report on Jensen's relationship with a suspected Chinese spy and rewrote it in his own, more forceful terms, according to one person familiar with it. When that memo's findings leaked, the scandal began. A former official who worked on chip policy described what Trump's national security team was after: "They wanted to destroy the influence Jensen had over the president." Trump still calls him a "legend." The agencies still can't prove she was a spy. But three bills restricting chip sales to China are now headed for the defense bill, and the one executive who used to talk Congress out of them is gone. So ask yourself who came out ahead this week, and you have a good idea why that memo found its way to reporters. Source: Washington Post / Writer: Daniel

这个作者当不了nytimes的主笔，如果是nytimes主笔，应该会这么写， “Hugging Face Hosts A.I. Models That Praise Nazis and Write Scam Scripts“ 副标题 An investigation found that some models available on the platform generated racist and anti-LGBTQ responses, praised terrorist violence and produced scripts for fraud. 然后建一个hashtage #takehuggingfacedown，# 然后找一堆枪手，吵起来。 然后动员所有自己能影响到的社群，施加压力。 必要的话，找些人去大门口游行。（这个得加钱） 然后再找自己人去报道。（这个也得加钱） 然后呢，说founder是个坏人，6岁的时候还尿裤子，七岁摸过女生的pp，8岁还骂过犹太人。 然后再找3个议员，立法，要求，safe model hosting 法案。 所有开源模型的上传与发布，必须要监管，要审批，要在DMV备案。 否则就是hate crime，恐怖主义支持者. 整个方案，大概3000万美元够了。 Dario，你看看这个方案行不行。 行的话，打钱。