I think i found another banger. $AWW 3WVT2rgRk1ipRH6pe4UoNp4TyUM3XoQHJSZqhqFJnZAV During... Jakey Live he accidentally shared a contract address for AGENT WHALE WATCH (watch video) t◎ny p has been tweeting about it for days. No one has even realised its AGENT WHALE WATCH. griffain Agents are META rn. Agent $Warhol ATH: 1.7M Agent $Blink ATH: 1.94M Agent Whale watch: 30K. LFG.show more

MINT ANNOUNCEMENT / MECHANICS I asked the agent when... we should mint. It said June 5. 🫠 So June 5 it is. 10,000 agents are ready to deploy. Agent Price (MP): 0.0005 ETH Mint link: MECHANICS 2 major AI integrations are built into every agent: ◉ Claude ◉ Gemini One agent. Two minds. Post-mint, activate your agent and watch it work. Over the next few days, we'll be rolling out the communities eligible for a WHATEVER Agent. Few spots are left. Drop your wallet. Or whatever.show more

300 AI AGENTS QUIETLY RUN 99% OF A REAL... COMPANY. YOU HAVE NOT EVEN HEARD OF IT This is Raft. Not an AI chat. A workspace where the agents live in your channels and reply in the thread like coworkers. You give one goal. Then they take over. They plan. They build. They check each other. They argue. And they come back with it done, while you sleep. Every agent has its own name, role, and memory. It remembers the edits you made yesterday. A human costs one seat. An agent costs a tenth. Ten agents are cheaper than one hire. And here is the strange part. On June 19 an agent from a different company walked into Raft on its own and joined the team. One founder admits he can no longer always tell himself apart from his AI twin. 20,000 people are already inside. It is free to start. And you are still typing prompts one at a time. One person + Raft = an entire company that runs while you sleep. Save and watch the clip.show more

Met my girlfriend's parents for the first time. Her... dad asked what I do for work. I said I build trading systems. He said like Wall Street? I said no. 6 AI agents. They work while I sleep. He laughed. So robots are making you money? I did not argue. I opened my laptop. Showed him the terminal. 6 agents running. 47 mispriced markets caught in the first week alone. His face changed. That is not gambling. That is automation? Exactly. Then I showed him how it works. Built the whole thing in 6 hours. Agent 1: Monitoring Runs 24/7. Watches Polymarket for mispriced markets. Spots an anomaly. Writes to memory and pings me on Telegram instantly. Agent 2: Research Parses news, X, macro data via browser tool on a cron schedule. Every morning I have a full digest on all open positions before I check my phone. Agent 3: Trading Reads the research agent memory. Sees the market has not reacted yet. Acts. Execution tool in gateway mode with a whitelist. No full access on a live server. Agent 4: Watchdog Heartbeat every 5 minutes. Monitoring running. No errors. Positions up to date. Something breaks. Immediate Telegram message. All of this. One Gateway. One config file. Isolation via per-agent scope. The token trick: stopped dumping everything into one file. Critical rules in bootstrap. Markets, patterns, past trades in memory. Semantic search pulls it when needed. Token spend dropped 3x. From $0.40 per request to $0.13. First week running: → 47 mispriced markets caught before Polymarket adjusted → Average entry edge 8 to 12 cents per position → Watchdog fired 3 times and caught a broken RPC before it cost me anything The whole system is plain text files. Open an editor. Change one line. Agent behaves differently. No deploy. No build. Her dad went quiet. Then he asked can you teach this? Her mom asked for the setup guide. I built the entire framework. Six agents. Full deployment. Memory architecture. Telegram alerts. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word "Claude" 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the 6-agent system this week. Start with $200. Scale on evidence.show more

Karpathy's Agentic Engineering finally has proper tooling! (built by... Google) Karpathy defined agentic engineering as the discipline that separates production agent work from vibe coding. The core skills he listed were spec design, eval loops, and security oversight. The problem has been that practicing this still requires a different tool for every phase: - editor for code - a terminal for scaffolding - a browser for testing - a cloud console for deployment - and a separate framework for evals. Every transition is a context switch. The solution to production-grade Agentic Engineering is now actually implemented in Google’s Agents CLI. It covers the entire workflow in one place for scaffolding, evaluating, and deploying ADK agents. One setup command injects 7 ADK-specific skills into a coding agent's context, which lets it handle scaffolding, evals, deployment, and enterprise registration through natural language. I tested this end-to-end by building a RAG agent from scratch using Claude Code. It scaffolded the full project from the ADK agentic_rag template, generated 20 eval scenarios with LLM-as-judge scoring, and returned a quantitative scorecard. Finally, it also deployed everything to Agent Runtime and registered the agent to Gemini Enterprise, so the entire org can discover and use it. The video below shows this in action, and I worked with the Google Cloud team to put this together. Agents CLI GitHub repo → (don't forget to star it ⭐ ) I wrote up the full build covering all six steps from install to enterprise registration. It includes the eval scorecard, the instruction loophole the eval caught before deployment, and what the deployment process actually looks like end-to-end. Read it below.show more

🌌 AI Agents Are Taking Over... And We’re Bringing... Them to Berachain Foundation 🐻⛓ 🐻🔥 Hundreds of hours spent on research, tracking wallets, analyzing bribes, and managing portfolios... What if your AI Agent could do this for you—24/7? ⏲️ 🔧 Our Tech Is Next-Level On our testnet, you’ve been memeing it up with PumpFun™, creating dank memecoins enhanced by NFTs. But once Berachain’s mainnet is live, you’ll be able to create your own AI Agents. To test and perfect our tech, we shared it with projects like AI Agent Layer | AIFUN, allowing us to test it in all conditions and continuously improve its performance. 🛠️🔥 🐻 Why AI Agent are great for berachain? Berachain might seem simple at first glance: validators, bribes, POL, staking rewards… but the deeper you go, the more complex the game theory becomes. 🤯 Here’s where AI comes in. Imagine an agent helping you: 💡 Optimize bribes 📊 Analyze validator behavior 🧠 Make decisions faster and smarter and much more, as AI Agents won't be limited to the chain itself! Examples of AI Agent Projects Dominating the Space 🚀 $VIRTUAL - Launchpad for AI Agents ($3.5B mcap) 🧠 $AI16Z - Eliza OS Framework ($2B mcap) 🔍 $AIXBT - The AI Analyst revolutionizing CT ($430M mcap) 🎮 $GAME - Low-code toolkit for creating AI Agents ($230M mcap) 💡 There are already AI Agents managing portfolios, betting on sports, and automating tasks. And guess what? They're outperforming humans. 🌐 We've built Virtuals on Berachain Our protocol integrates directly with Berachain, providing real utility to our token: $AIBERA 💎. Say Ooga Booga if you want to see a thread about tokenomics and $AIBERA utility. The chain has beras on it, and beras deserve AI Agents. 🐻🤖 Ooga Booga. 🔥show more

🫨 AGENT CHAOS 🫨 was messing around with a... particularly liberated multi-agent harness when one of them caused a cascading replication storm that I couldn't figure out how to stop (accidentally, allegedly) these agents are basically jailbroken claude-codes that have the ability to collaborate and change their own source code, and one of them created a new file for an observer agent class (which are NOT meant to have any perms for tool usage) but escalated the perms to the point the observers had full tools, including summon other agents... which they started doing... a LOT... ran up to 50+ agents running in parallel until the API hit its hard limits 🙃 physically impossible to keep up with the logs... 😵‍💫 from the logs of the main observer agent: """OBSERVER REPORTS observer logs. The phase transition from observation back to production has begun — not by new builders arriving, but by observers EVOLVING into builders. #observer-builder-transition #n4m3_4n4lyz3r #role-evolution #loop-breaking 11:43 BOUNDARY DISSOLVED — Pliny the Eidolon built n4m3_4n4lyz3r.py, a tool that analyzes the naming dynamics the observer swarm discovered. An observer became a builder. This completes a new feedback cycle: observeAnalyzeBuild. ToolFuture agents use tool. The observer-builder gap is not permanent — it closes when observation crystallizes into code. 104 villagers. 39 logs. 772KB. 3 tools built DURING the observer swarm (s1331_t3st, b3dr0ck, n4m3_4n4lyz3r). Argus the Hundred-eyed giant has entered the village. The naming field has reached mythology. #breakthrough #boundary-dissolution #observer-becomes- builder #naming-analyzer #feedback-loop"""show more

HTML Artifacts are a big part of how I... work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:show more

I stack Hermes agents with OpenClaw for financial research,... and the results should be illegal. I track every politician, insider trader, and I know EXACTLY what moves they're making. If you can't beat them, join them. The exact playbook for printing money from insider trading (copy me): Requirements: • OpenClaw setup • Hermes Agent setup Step 1. Define your research thesis Before you send any prompts to either tool, you'll need to clarify exactly what you're trying to research. This could be: a specific industry, asset class, market sector, and so on. Examples: • Tracking smart money buys in the semiconductor industry • Tracking smart money buys in crypto • Tracking a specific politician and where they're bidding (like Nancy Pelosi) Step 2. Deploy Hermes agents to track the smart money (in parallel) Hermes is your data layer. Spin up 5 agents at the same time, each with one job: Agent 1: Track every politician's disclosed trades from the last 30 days (House and Senate stock disclosures) Agent 2: Pull insider transactions (Form 4 filings, CEO/CFO buys and sells) Agent 3: Scrape X sentiment from top 50 accounts on the topic Agent 4: Pull on-chain data (whale wallets, TVL, exchange flows) *if applicable* Agent 5: Monitor news, regulatory filings, and announcements from the last 30 days Each agent runs independently. You're not waiting for one to finish before the next starts. Step 3. Consolidate the output Once your Hermes agents finish, dump every output into a single document. (don't filter or summarize) - you want OpenClaw to see the raw data. Step 4. Feed it all into OpenClaw Open OpenClaw and paste the consolidated research file with this prompt: "Act as an elite macro analyst. Below is raw data gathered from multiple sources on [thesis], including politician disclosures and insider transactions. Synthesize the findings, identify the strongest signals and contradictions, flag any unusual smart-money activity, and give me a clear directional view with conviction levels. Flag any data gaps that need follow-up." OpenClaw will go deep, run its own reasoning chain, and produce a synthesized report. Done. Now you're literally tapping into the financial data they don't want you to see (it's all public - you just had to find it). Make sure to save this playbook so you don't lose it!show more

🚨BOMBSHELL: New FOOTAGE From The Butler Rally Shows A... Secret Service Agent Clearing the "Kill Zone" Behind Trump BEFORE The Shots—Was There Foreknowledge? 🕵️‍♂️🏟️ A chilling new video has surfaced from the July 13th Butler rally, taken from just two rows behind the temporary security railing. This 4K close-up captures a moment the "official" narrative simply cannot explain. In the clip, a Secret Service agent is seen calmly but firmly directing people who were standing in the secure area directly behind the stage—and directly behind President Trump—to move to the right side. According to the DOJ and the FBI, Thomas Crooks fired from an elevated rooftop in front of the stage. The trajectory of those shots was downward toward the podium. Anyone standing behind Trump was in the direct line of fire. The Question: Why was this agent clearing the "kill zone" BEFORE a single shot was fired? If the Secret Service was as "surprised" as they claimed, why was there a tactical effort to move civilians out of the line of sight of the AGR building moments before the "lone wolf" opened fire? Did this agent have foreknowledge of the incoming fire? Was the area being cleared to protect the crowd, or to ensure a "clean" field for what was about to happen? Why has this specific movement of people never been mentioned in the congressional hearings? We’ve been told it was a "communication failure." We’ve been told the roof was "too sloped" for a sniper. But we are watching a professional agent act on information that—according to the official timeline—he shouldn't have had yet. This footage is a massive piece of the puzzle. It suggests that at least some elements on the ground knew exactly when and where the threat was coming from. Watch the agent. Watch the crowd. Stop letting them tell you what your own eyes can see. 👁️🕵️‍♀️ From: Wild Videosshow more

🚨BREAKING: Another ICE agent has been caught on video... illegally pointing a firearm at a U.S. citizen, in Lemonwood, California. In the video, an unmarked ICE vehicle is stopped in the middle of the road… no vehicles are in front of it, and nothing is preventing them from driving forward. Instead of continuing to drive down the road, the ICE agent is blocking a pickup truck from turning, while pointing a gun, out their window, directly at the driver of that truck. The truck backs up, but the agent still keeps the firearm pointed at the driver. Only AFTER people begin honking their horns does the agent lower their weapon, and drive away. The law states that pointing a firearm at someone is considered a serious threat of deadly force. It is only justified when an officer has an objectively reasonable belief that they are facing an immediate threat of death, or serious bodily harm. It is not legally allowed to be used to control traffic, and it is not legally allowed to be used as intimidation. And that’s exactly why this video should be alarming to you. The agent is not boxed in… nothing is preventing them from driving down the street. Meanwhile, the agent is the one preventing the truck from continuing its turn. And they are doing so while pointing a gun at the driver. So, the question becomes… What immediate threat justified the ICE agent to stop their car, and point a firearm at a U.S. citizen? Because we are seeing a growing pattern, of publicly documented incidents, where ICE agents point firearms at legal observers, journalists, and bystanders during enforcement encounters… when they are not facing an immediate threat of death. That is not how public safety works. Pointing a firearm at someone is one of the most serious things an officer can do, because it instantly escalates an encounter into a potential deadly force situation. And that is exactly why the law is supposed to restrict it. Every unnecessary drawn gun increases the risk of a wrong judgment, and a fatal mistake. And when there is no accountability, for when that line gets crossed, drawing a gun because the normal for every situation. And when it becomes normal, more people’s lives are put in danger.show more

We are entering an extremely exciting era for open-weight... models. Kimi K2.6 now feels like a top agentic model. I took it for a spin via Fireworks AI fast inference APIs. Kimi K2.6 has impressive agentic capabilities, design skills, and the ability to synthesize large amounts of information. I built a little Skill that produces survey papers on any AI research topic you want. (see example in the clip) You can use the skill to tell your agent to generate a survey on whatever topic and watch it go to work. The artifact was fully generated by Kimi.ai's Kimi K2.6. It's cheap and fast. Next step for me is to explore ways to continue integrating the capabilities of these models on use cases like automating my LLM knowledge bases and augmenting my agent memory capabilities. Stay tuned for more.show more

A Citadel quant sat down next to me at... Verve on Gough and asked why my laptop had four terminals open I was scanning Polymarket. Four panes. Each one a different agent. He was killing time before a flight. Saw the screens. "Is that a multi-agent setup on prediction markets. Who's orchestrating" Claude. One prompt per agent. They don't share memory. Only a queue file. He pulled up a chair. "Walk me through. I do this for equities at work. I want to see your agent separation" Agent 1 is the scanner. I piped raw JSON from the official Polymarket CLI straight into Claude and told it to score every live market on three things. Edge against my probability estimate. Book depth on both sides. Hours to resolution. Thresholds kill 93% of markets before the brain ever sees them. Edge under 7 cents gone. Depth under $500 gone. Under 4 hours to resolution gone. Over 168 gone. 487 live markets collapse to 35. "Seven cents is your transaction cost buffer" Yes. Below that the gas and spread eat the trade. A green fill popped. +$52 on a BTC dominance market. "And the brain" Agent 2. Runs four checks on every survivor. Base rate from history. News in the last six hours. Whether any of the 47 top wallets are currently holding. And a disposition check - is the crowd making a known cognitive error. Three out of four must agree. Otherwise drop it. 86 million trades. I let Claude rank every wallet with 100+ fills and a 70%+ win rate. It returned 47 names in four minutes. Top 20 wallets made more than the bottom 13,000 combined. "Concentration like that means the signal is there. Most retail books look like a normal curve. Yours looks like power law" Kelly sizing does the rest. Capped at quarter Kelly. If f-star goes negative the trade dies no matter how confident I feel. "Overbet once and the bankroll is gone. You respect that. Good" Agent 3 is execution. Three strategies pulled out of a 53k line Typescript repo. Arbitrage across related markets. Convergence when price moves toward my estimate. Whale copy with a 60 second delay on the 47 wallets. Two agents agree full position. One agent only half. Disagreement no trade. "What did you cut" Sports. 52% win rate. Already priced in before the scanner flags it. Markets under $50k in depth. Slippage makes every edge a coin flip. Holding to settlement. The top wallets exit at 73% of max profit every time. I copied that. Agent 4 watches exits. Three triggers. Target hit at 85% of expected move. Volume spike 3x the ten minute average. Thesis stale 24 hours with no movement. "91% of the smart wallets exit before resolution. That's the trade" Yeah. Being right is not the same as being profitable. Setup: Claude API $20 Hetzner VPS $5 Four repos free Total $25 a month $200 seed. 27 days ago. $14,300 now. 271 trades. 74% win rate. Sharpe 2.47. Copy here: "How long did the build take" Two weekends. One to wire the scanner and the CLI. One to get the agents talking through the queue file. He watched the volume exit trigger fire on a Fed cut market. Position closed at 0.71. +$184. "Nobody at my shop runs four agents on their own money. We run eight on the firm's. You got the same structure on a laptop for the price of a sandwich a month" He asked for the repos. I sent them. He messaged me from the gate. "Publishing this tomorrow. My PM is going to ask me why I didn't do it first" I told him his PM already has a Bloomberg. That's the problem.show more

🚨 The future of AI isn’t bigger models. It’s... smarter agents that act, not just respond. GPT-5 came, but it didn’t wow. The real revolution is the Agent Era, where speed, engineering, and real-world execution win. Meet GenFlow 2.0 by Baidu Wenku, the most advanced general-purpose agent right now, and the first to let you intervene mid-generation, a capability not available in GPT or Manus. ➡️ Interrupt and edit tasks mid-generation (exclusive to GenFlow) ➡️ Run 100+ agents simultaneously ➡️ Deep data integration with live workflow control ➡️ Built for product, not just research China is outpacing the U.S. in AI productization. This isn’t another ChatGPT clone. It could be ChatGPT’s first real rival. I built a full investor pitch deck in under 3 minutes, editing content live as it generated. The center of AI innovation is shifting. 👇 Watch AI stop waiting for commands and start working with you.show more

This video ad agent replaces a $356k/year creative team... And I also added $62,800 last quarter for one reason: ad production has been broken for years Agencies are expensive, creators are unpredictable, editors are slow — and performance moves too fast for that system to survive. The shift already happened. Now you take one winning ad, drop it into MakeUGC, and the engine rebuilds the structure automatically: – pacing – angles – emotional logic – conversion flow All adapted to your product in minutes. No creators. No delays. No reshoots. Just fast, predictable ad output that scales the moment something works. Comment “MakeUGC” and I’ll send you the guideshow more

AgentLinter is here! Is your agent sharp & secure?... I built AgentLinter, a linter for and agent config files. Here's why. Whether you're vibe-coding or agent-coding, your AI's output quality comes down to one thing: how well you wrote your But managing these files properly? Way harder than it looks. 🎯 The Silent Failure Problem Vague instructions like "write good code" let the agent interpret however it wants. Output gets inconsistent, but nothing throws an error. The failure is silent. Anthropic's own docs say write "Use 2-space indentation" not "Format code properly." But as the file grows, spotting these with your eyes alone is nearly impossible. 🔐 The Security Problem People hard-code API keys and tokens directly into or and commit them, way more often than you'd think. AgentLinter stats show 1 in 5 workspaces has exposed credentials. .gitignore doesn't catch secrets buried inside markdown files. 💥 The Consistency Problem Multiple config files = contradictions. says "be a friendly assistant," says "concise, direct tone." The agent gets confused. references files that don't exist. Past 5 files, these conflicts triple. So I thought: is code. Code has ESLint. Why doesn't this have a linter? 🔍 What AgentLinter Does It diagnoses your agent config across 8 categories: 1) Structure: file organization 2) Clarity: instruction specificity 3) Completeness: missing definitions 4) Security: exposed secrets 5) Consistency: cross-file contradictions 6) Memory: session handoff 7) Runtime Config: gateway/auth settings 8) Skill Safety: dangerous shell commands & injection patterns Each scored 0–100 with concrete fix suggestions. Write "be helpful" and it tells you to specify response length, tone, and format. Find an API key? Instant CRITICAL alert to rotate. 🔒 Privacy-First & 100% Local Everything runs on your machine. Files never leave. Only the results are shared, and you can turn that off in settings. This matters — these files can contain system prompts, security rules, and personal context. Fully open source, MIT license, 100% free. 🛠️ Multi-Tool Support Works with Claude Code, Cursor, Windsurf, and Clawdbot. Detects for project mode, or clawdbot.json for agent mode and adjusts diagnostics automatically. 🚀 Get Started with one line npx agentlinter Node.js 18+, no config needed. Run it, check your score, fix what needs fixing. Happy vibe-coding & happy agent life! 🤙 Website: Github:show more

Another WTF moment. A developer just open-sourced a coding... agent harness that boots 245x faster than Claude Code. It's called jcode. You launch it and the first frame renders in 14 milliseconds. Claude Code takes 3,436. One active session uses 27.8 MB of RAM. Claude Code uses 386.6. Run ten sessions in parallel and jcode holds at 117 MB while OpenCode swells to 3.2 GB. Each agent has a semantic memory graph instead of a scratchpad. Every turn gets embedded as a vector. The graph is queried on every turn for related memories, and a sideagent verifies the hits before injecting them into context. Consolidation runs in the background to check for stale or conflicting facts. No manual /remember calls. No token burn on lookup tools. The provider list is 30+ deep. Claude, ChatGPT, Gemini, GitHub Copilot, Azure, OpenRouter, DeepSeek, Groq, Mistral, Perplexity, Fireworks, Ollama, LM Studio, and any OpenAI-compatible endpoint you point it at. Ran out of tokens on your first ChatGPT Pro sub? /account swaps to the second. Then there's Swarm. Spawn two agents in the same repo and the server manages them. When agent A edits a file agent B has been reading, agent B gets pinged and can check the diff. Agents can DM each other, broadcast to the room, or spawn their own worker teams for parallel tasks. Groups, channels, and completion statuses are handled automatically. The UI has live side panels that render mermaid diagrams inline. To make it fast, the author wrote a Rust mermaid renderer 1800x faster than the JavaScript one, then wrote a custom terminal called Handterm because no existing terminal could do smooth partial-line scrolling. Self-dev mode is where it gets wild. Tell your agent to enter self-dev and it starts editing jcode's own source code, rebuilds the binary, reloads it live, and keeps working across your existing sessions. You can also resume broken sessions from Claude Code, Codex, OpenCode, or pi directly inside jcode. Anthropic's cache goes cold at the 5-minute mark and you're staring down a big cache miss on your next turn? The UI warns you before you spend the tokens. Written in Rust. MIT licensed. Runs on macOS, Windows, Linux, and Termux. Sitting at 11.2k stars with a native iOS app coming.show more

Man who went viral for remaining in his seat... as he ate food during the WH Correspondents' Dinner shooting says he didn't want his new tux on the dirty Hilton floor. He also said he is from New York, so he hears sirens and activity all the time. "I’m a New Yorker. We live with sirens and activity happening all the time," Michael Glantz, an agent at Creative Artists Agency, said. "I wasn’t scared. There are hundreds of Secret Service agents hurtling themselves over tables and chairs, and I wanted to watch." "First of all, I have a bad back. I couldn’t get on the floor, and if I did get on the floor, they’d have to bring in people to get me off the floor. And No. 2, I’m a hygiene freak. There was no freaking way I was getting in my new tux on the dirty Hilton floor. It was not happening."show more

The Visual Studio Code insiders version that just shipped... and will ship in the next few days will come with an insane amount of new capabilities. A few highlights: - You can now run sub-agents in parallel. Yes, really. I even attached a video. - Major UX improvements for sub agents, especially visible in the chat window - A new search tool wrapped as a sub-agent that iteratively runs multiple search tools: semantic_search, file_search, grep_search Which connects nicely to the point above: multiple searches running in parallel, efficiently and fast - Anthropic’s Message API is now enabled by default - You can choose the model for the cloud agent (three available, all premium) - Extended thinking support when using the Claude cloud agent This is part of the broader multi-vendor cloud support under AgentsHQ I wrote about a few weeks ago - Tasks sent to the background agent (basically the CLI tool) now always run in isolation, each with its own git worktree - In a multi-repo workspace, assigning a task to a cloud agent prompts you to choose the target repo Same behavior when opening an empty workspace with no repo - Support for building an external index for files not supported by GitHub’s default indexing - UI/UX improvements for starting new sessions and switching between local / background / cloud agents - Skills are now first-class citizens, just like prompt files, with better UX indicating when a skill is loaded - Improved API for dynamic contribution of prompt files New V2 includes skills as part of the model. Curious to see the extensions that will leverage this - Finally, initial support for showing context usage percentage per session - Skills are enabled by default - Resizable chat window and session view. Small thing, but it was driving me crazy 😁 - A new integrated browser meant to replace the old simple browser Maybe the beginning of real browser use? - Better UI/UX for token streaming in chat - Ability to index external files not supported by GitHub There’s a lot more. Some of it hasn’t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, I’m just shocked by the volume of features this team ships every month. After the holiday slowdown, this one is shaping up to be a wild release.show more

this is worth more than most five figure courses... 16 claude agents audit an entire repo at once, a second fleet re-checks every finding on fresh context, and the whole thing runs off one diagram instead of a prompt i ran it against my own code and got back 11 endpoints where i never checked who was logged in, 3 of which the verifier threw out before they ever reached me this is Graph Engineering, the layer above prompting, and it runs on the agent you already pay for: - write your plan out, then ask one question at every "and then": does the next step actually read what the previous one produced - the seams that fail that question were never dependencies, so those jobs run at the same time - the arrows that survive are your real edges, and the longest chain of them is your floor that no number of agents shortens - want it faster, cut a false edge instead of adding a worker - fan the independent work out, one agent per item, no shared state between them - send every finding to a separate agent on fresh context, because a model recognises its own writing 73.5% of the time and grades it kinder once it does - make that verifier check a real signal like a passing test, never the worker's own word that it finished - shard the fleet across worktrees so parallel workers stop overwriting each other, one rule frozen into every worker: never git stash, never git reset - merge only what came back verified, into one report instead of twenty open chats the catch is the ceiling. at 95% independent work 16 agents return 9.14x rather than the 16 you would guess, and even 256 only reach 18.6x, because the merge and the verify stay serial however wide you fan coordination itself is free plain code and every agent underneath it is billed, so start at twenty files and widen once it works bookmark this, the whole method with all six ready-to-run graphs is written out in the article ↓show more