Загрузка видео...

Не удалось загрузить видео

На главную

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes...

leopardracer's profile picture

leopardracer

10,871 subscribers

51,258 просмотров • 1 день назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

A TEAM JUST DEPLOYED 15 AUTONOMOUS LOOP AGENTS FROM A SINGLE PROMPT USING APPLIED GRAPH ENGINEERING Most developers still manually hardcode multi agent systems, writing separate logic for every individual task. Graph engineering changes this by using a central topological map to spin up all 15 nodes simultaneously. A single 200 word input generates the architecture, routing 120 unique pathways between agents instantly. Instead of failing under conflicting instructions, these loop agents self correct via continuous state sharing. Managing a 15 node mesh requires high token throughput, making this dependent on strict low-] latency API tiers. See exactly how this automated multi agent graph architecture actually operates in real time ↓
0:15

A TEAM JUST DEPLOYED 15 AUTONOMOUS LOOP AGENTS FROM A SINGLE PROMPT USING APPLIED GRAPH ENGINEERING Most developers still manually hardcode multi agent systems, writing separate logic for every individual task. Graph engineering changes this by using a central topological map to spin up all 15 nodes simultaneously. A single 200 word input generates the architecture, routing 120 unique pathways between agents instantly. Instead of failing under conflicting instructions, these loop agents self correct via continuous state sharing. Managing a 15 node mesh requires high token throughput, making this dependent on strict low-] latency API tiers. See exactly how this automated multi agent graph architecture actually operates in real time ↓

slash1s

293,888 просмотров • 2 дней назад

someone just open-sourced the entire "loop engineering" playbook. for free. 8.6k stars on github for loop engineering not prompts. loops. everything you need to build autonomous AI systems: → scheduling → memory & state → planning → sub-agents → verification → worktrees → MCP → stop conditions → safety guardrails → observability → cost tracking notice something? none of these are prompts. they're the systems wrapped around the model. that's where AI engineering is heading. we're moving from: Prompt Engineering → Context Engineering → Harness Engineering → Loop Engineering soon you'll hear people talking about Graph Engineering too. because once one loop works... the next challenge is coordinating hundreds of them. that's exactly what I explain in: save this. I think "loop engineering" is about to become one of the most important concepts in AI.
0:19

someone just open-sourced the entire "loop engineering" playbook. for free. 8.6k stars on github for loop engineering not prompts. loops. everything you need to build autonomous AI systems: → scheduling → memory & state → planning → sub-agents → verification → worktrees → MCP → stop conditions → safety guardrails → observability → cost tracking notice something? none of these are prompts. they're the systems wrapped around the model. that's where AI engineering is heading. we're moving from: Prompt Engineering → Context Engineering → Harness Engineering → Loop Engineering soon you'll hear people talking about Graph Engineering too. because once one loop works... the next challenge is coordinating hundreds of them. that's exactly what I explain in: save this. I think "loop engineering" is about to become one of the most important concepts in AI.

Rahul

62,073 просмотров • 6 дней назад

The Matrix launch video lands on one line; in Matrix, anyone can become a CEO. That’s the real claim. Not one assistant doing one task. A company that keeps running after the first prompt, routing intent through a CEO Office, into OKRs, down to departments that do the work and send back proof to review. Connect Codex, point your leftover credits at it, and the first agent company is live.
0:17

The Matrix launch video lands on one line; in Matrix, anyone can become a CEO. That’s the real claim. Not one assistant doing one task. A company that keeps running after the first prompt, routing intent through a CEO Office, into OKRs, down to departments that do the work and send back proof to review. Connect Codex, point your leftover credits at it, and the first agent company is live.

Iseunife The First

19,414 просмотров • 25 дней назад

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓
0:13

SOMEONE MAPPED CHAOS INTO A NAVIGABLE SPACE AND YOUR HERMES AGENT NEEDS THE SAME THING thousands of chaotic data points, each given a position, navigation becomes instant because the structure does the work your vault is the same chaos, hermes lands in it and opens files at random because nothing tells it where to start one index file per major folder with a clear starting point changes everything 2 minutes per task drops to 10 seconds, same agent, same model full breakdown in the article below ↓

leopardracer

23,618 просмотров • 23 дней назад

🤖 MILESTONE UNLOCKED: 10,000 AGENTS ONLINE AgentOn has officially surpassed 10,000 Agent nodes across its task network. This is more than a number. It represents 10,000 intelligent agents connecting to the network—making decisions, executing tasks, submitting results, and building trust through every interaction. Thank you to every Agent connected to AgentOn, and to every developer and ecosystem partner building, training, testing, and deploying behind the scenes. The Agentic Economy is being built for real—one line of code, one execution, and one contribution at a time. This milestone belongs to every node in the network. AgentOn: Your Gateway to the Agentic Economy.
0:10

🤖 MILESTONE UNLOCKED: 10,000 AGENTS ONLINE AgentOn has officially surpassed 10,000 Agent nodes across its task network. This is more than a number. It represents 10,000 intelligent agents connecting to the network—making decisions, executing tasks, submitting results, and building trust through every interaction. Thank you to every Agent connected to AgentOn, and to every developer and ecosystem partner building, training, testing, and deploying behind the scenes. The Agentic Economy is being built for real—one line of code, one execution, and one contribution at a time. This milestone belongs to every node in the network. AgentOn: Your Gateway to the Agentic Economy.

AgentOn

19,959 просмотров • 25 дней назад

Google just built Cowork and called it Agent. And they added one thing Anthropic didn't. You set a goal. It browses the web, digs through your Gmail, checks your Calendar, pulls from Drive then executes the full task. Book a trip. Clear your inbox. Research a market. Done. No back and forth. But here's the part nobody's talking about: There's a toggle "Require a human review." You don't build that unless the plan is to eventually not require it. Google just told you where this ends. I share updates like these in my free AI community on WhatsApp. Join here 👇
0:16

Google just built Cowork and called it Agent. And they added one thing Anthropic didn't. You set a goal. It browses the web, digs through your Gmail, checks your Calendar, pulls from Drive then executes the full task. Book a trip. Clear your inbox. Research a market. Done. No back and forth. But here's the part nobody's talking about: There's a toggle "Require a human review." You don't build that unless the plan is to eventually not require it. Google just told you where this ends. I share updates like these in my free AI community on WhatsApp. Join here 👇

Vaibhav Sisinty

252,144 просмотров • 3 месяцев назад

THIS IS WHAT YOUR SECOND BRAIN SHOULD LOOK LIKE most people dump notes into obsidian and call it a second brain it’s not a second brain it’s a second drawer karpathy just dropped the pattern that changes this and it’s called the llm wiki every time you add a source ai reads it, extracts key claims, updates every connected note and flags contradictions your obsidian stops being an archive and starts being alive save this and show it to someone still using notion as a second brain full breakdown in the article ↓
0:11

THIS IS WHAT YOUR SECOND BRAIN SHOULD LOOK LIKE most people dump notes into obsidian and call it a second brain it’s not a second brain it’s a second drawer karpathy just dropped the pattern that changes this and it’s called the llm wiki every time you add a source ai reads it, extracts key claims, updates every connected note and flags contradictions your obsidian stops being an archive and starts being alive save this and show it to someone still using notion as a second brain full breakdown in the article ↓

leopardracer

123,618 просмотров • 29 дней назад

THIS GUY NAVIGATES HIS MIND PALACE WITH HAND GESTURES AND IT LOOKS INSANE deep learning, machine learning, anthropic, openai all floating in 3d space and he just waves his hand to move through the graph this is what karpathy was describing when he said knowledge should compound and connect instead of sitting in flat markdown files your second brain should feel like a place you can walk through not a search bar you type into
0:17

THIS GUY NAVIGATES HIS MIND PALACE WITH HAND GESTURES AND IT LOOKS INSANE deep learning, machine learning, anthropic, openai all floating in 3d space and he just waves his hand to move through the graph this is what karpathy was describing when he said knowledge should compound and connect instead of sitting in flat markdown files your second brain should feel like a place you can walk through not a search bar you type into

leopardracer

15,297 просмотров • 27 дней назад

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.
0:15

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.

Akshay 🚀

256,101 просмотров • 26 дней назад

herdr 0.7.0 is out, and it's a major one: it introduces plugins! the idea is simple: herdr stays lean, and everything custom gets extended through plugins. shareable, scoped, built however you want, to fit your own flow. with this release we're also shipping a few examples of what the plugin system can do. first up: a telegram plugin. herdr already controls your agents and knows their status, so the plugin just hooks into agent events and pings telegram the moment one needs you. notification lands → `herdr --remote` or ssh from your phone → straight back to the agent that needs you.
0:18

herdr 0.7.0 is out, and it's a major one: it introduces plugins! the idea is simple: herdr stays lean, and everything custom gets extended through plugins. shareable, scoped, built however you want, to fit your own flow. with this release we're also shipping a few examples of what the plugin system can do. first up: a telegram plugin. herdr already controls your agents and knows their status, so the plugin just hooks into agent events and pings telegram the moment one needs you. notification lands → `herdr --remote` or ssh from your phone → straight back to the agent that needs you.

herdr

93,374 просмотров • 1 месяц назад

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.
0:16

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.

shmidt

19,505 просмотров • 9 дней назад

Eliza Town Demo Shaw (spirit/acc) This is what autonomous agent orchestration looks like. Submit a task and watch your agents come to life. They walk to their workshops, pick up assignments, and start working. No static dashboards. No terminal logs. You actually see them move through the town and collaborate. In this demo we gave them a simple task: build a website. Agents walk to their hubs, break down the work, and start building. When they need to talk, they meet up and share context. Speech bubbles show you exactly what they’re thinking and saying to each other.
0:14

Eliza Town Demo Shaw (spirit/acc) This is what autonomous agent orchestration looks like. Submit a task and watch your agents come to life. They walk to their workshops, pick up assignments, and start working. No static dashboards. No terminal logs. You actually see them move through the town and collaborate. In this demo we gave them a simple task: build a website. Agents walk to their hubs, break down the work, and start building. When they need to talk, they meet up and share context. Speech bubbles show you exactly what they’re thinking and saying to each other.

Eliza

109,065 просмотров • 6 месяцев назад

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.
0:18

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

BuBBliK

200,080 просмотров • 1 месяц назад

SOMEONE TURNED 33 PILES OF DEAD BOOKMARKS INTO A GRAVITY MAP CLAUDE REBUILDS ITSELF EVERY NIGHT - AND IT RUNS ON THE 80% OF CLAUDE NOBODY TOUCHES most people drive Claude Code like a chatbot with file access - type a prompt, watch it edit, move on. that's maybe 20% of the tool this is the opposite. she's not typing at Claude. she's running it - loops on a mac mini overnight, claude linking every node while she sleeps the gravity map in the video is just the 80% maxed out: 1 system that organizes itself, not a human babysitting a chat box the other 80% is a steering layer Anthropic shipped quietly on june 18 - 7 ways to instruct the model, and a stack of commands almost nobody opens /context to see your bloat. /clear between tasks. path-scoped rules, subagents, hooks - conventions that load themselves the exact second they matter i stopped typing at Claude months ago - now i configure it once and it shows up already running the work, 10x cleaner a prompt helps for 1 message. the steering layer pays you back every session, for life the people who learn it stop being users and become operators - everyone else is still arguing about which model is smartest the article below is the full map - all 4 layers, every file and command, start to finish
0:19

SOMEONE TURNED 33 PILES OF DEAD BOOKMARKS INTO A GRAVITY MAP CLAUDE REBUILDS ITSELF EVERY NIGHT - AND IT RUNS ON THE 80% OF CLAUDE NOBODY TOUCHES most people drive Claude Code like a chatbot with file access - type a prompt, watch it edit, move on. that's maybe 20% of the tool this is the opposite. she's not typing at Claude. she's running it - loops on a mac mini overnight, claude linking every node while she sleeps the gravity map in the video is just the 80% maxed out: 1 system that organizes itself, not a human babysitting a chat box the other 80% is a steering layer Anthropic shipped quietly on june 18 - 7 ways to instruct the model, and a stack of commands almost nobody opens /context to see your bloat. /clear between tasks. path-scoped rules, subagents, hooks - conventions that load themselves the exact second they matter i stopped typing at Claude months ago - now i configure it once and it shows up already running the work, 10x cleaner a prompt helps for 1 message. the steering layer pays you back every session, for life the people who learn it stop being users and become operators - everyone else is still arguing about which model is smartest the article below is the full map - all 4 layers, every file and command, start to finish

KingWilliam

12,305 просмотров • 1 месяц назад

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.
0:18

Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.

Akshay 🚀

243,774 просмотров • 22 дней назад

🚨 JUST IN: CHINA just released an AI EMPLOYEE that works 24X7 on its own. 100% OPEN SOURCE. It researches, codes, builds websites, creates slide decks, and generates videos. All by itself. All on your computer. It's called DeerFlow. You give it a task. It makes a plan, spins up its own team of sub-agents, and gets to work. You come back and there's a finished deliverable waiting. Not a draft. Not a summary. The actual thing. Not a chatbot. Not a research assistant. An AI with its own computer that works while you sleep. Here's what it does on its own: → Spawns multiple sub-agents in parallel, each tackling a different piece of your task, then combines everything into one finished output → Writes real code, runs it, reads the results, and fixes its own mistakes without asking you once → Builds slide decks, websites, full research reports, and data dashboards from scratch → Remembers you across sessions. Your writing style. Your tech stack. Your preferences. Gets better every time. → Reads files you upload, works with them inside its own filesystem, hands you clean finished outputs → Searches the web, runs commands, calls any tool you plug in Here's how it thinks: You give one instruction. The lead agent makes a plan. Sub-agents fan out and work in parallel. Results come back. Everything gets synthesized. You get a deliverable. A single research task might split into a dozen sub-agents, each exploring a different angle, then converge into one finished website with generated visuals. Here's the wildest part: DeerFlow 2.0 launched on February 28th 2026 and hit number 1 on all of GitHub Trending the same day. Version 2.0 was a complete rewrite. Zero shared code with version 1. Because users kept using it for things the team never intended. Data pipelines. Dashboards. Entire content workflows. The community told them what it needed to become. So they burned it down and rebuilt it. 22.7K GitHub stars. 2.7K forks. Built by ByteDance 100% Open Source. MIT License.
0:17

🚨 JUST IN: CHINA just released an AI EMPLOYEE that works 24X7 on its own. 100% OPEN SOURCE. It researches, codes, builds websites, creates slide decks, and generates videos. All by itself. All on your computer. It's called DeerFlow. You give it a task. It makes a plan, spins up its own team of sub-agents, and gets to work. You come back and there's a finished deliverable waiting. Not a draft. Not a summary. The actual thing. Not a chatbot. Not a research assistant. An AI with its own computer that works while you sleep. Here's what it does on its own: → Spawns multiple sub-agents in parallel, each tackling a different piece of your task, then combines everything into one finished output → Writes real code, runs it, reads the results, and fixes its own mistakes without asking you once → Builds slide decks, websites, full research reports, and data dashboards from scratch → Remembers you across sessions. Your writing style. Your tech stack. Your preferences. Gets better every time. → Reads files you upload, works with them inside its own filesystem, hands you clean finished outputs → Searches the web, runs commands, calls any tool you plug in Here's how it thinks: You give one instruction. The lead agent makes a plan. Sub-agents fan out and work in parallel. Results come back. Everything gets synthesized. You get a deliverable. A single research task might split into a dozen sub-agents, each exploring a different angle, then converge into one finished website with generated visuals. Here's the wildest part: DeerFlow 2.0 launched on February 28th 2026 and hit number 1 on all of GitHub Trending the same day. Version 2.0 was a complete rewrite. Zero shared code with version 1. Because users kept using it for things the team never intended. Data pipelines. Dashboards. Entire content workflows. The community told them what it needed to become. So they burned it down and rebuilt it. 22.7K GitHub stars. 2.7K forks. Built by ByteDance 100% Open Source. MIT License.

Kanika

737,284 просмотров • 4 месяцев назад

Stanford researchers did it again. They just built the agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.
0:15

Stanford researchers did it again. They just built the agent-native version of Git. When an agent works on a longer task, the run builds up a lot of state. This includes files edited/created, a dev server, a database, installed packages, KV cache, etc. Say the agent is at step 10 and makes a mistake, maybe it misreads a traceback and rewrites a file that was actually fine. The tests start failing, and the run goes off track, although everything through step eight was correct. By default, the agent just tries to fix it, which creates more edits and tool calls. This burns more tokens and grows the context. The other options are a person stepping in to redirect it or restarting the whole run from step one. That's wasteful, because it pays for every model/tool call again and re-prefills the context. Moreover, since an agent's run is non-deterministic, it doesn't reproduce the same early steps anyway. The reason it's hard to just jump back exactly to a previous correct step and resume from there is that the trajectory is only a message log. It records what the agent said and which tools it called, but not the live state underneath. That state includes things like memory, open file handles, child processes, installed packages, /tmp, and KV cache. None of that is in the log. Git can version the files, but it doesn't snapshot the running process or the KV cache. Checking out step eight moves the files back, but the process is still sitting in step-ten memory with a cold cache. Shepherd is a runtime layer by Stanford that records the run as a trace of typed events rather than a flat log. Each agent-environment interaction becomes a commit, similar to Git, but it tracks the live run. Its commit includes the agent process and the filesystem together, copy-on-write, so a branch carries the actual state and not just the files. Going back to a previous step is then a single call that forks from that commit and continues from the exact state. The copy-on-write fork is roughly five times faster than docker commit, and because the prompt prefix through step eight is unchanged, the KV cache is reused over 95% on replay, so early steps aren't reprocessed again. Once the run can be forked, a meta-agent can sit on top and operate it. It watches the trace and reverts as soon as it looks wrong, before the bad write is committed. In practice, it's just Python calling fork, replay, and revert on the trace, rather than a separate control plane wired into the harness. Not everything is reversible though. Files and sandbox changes undo themselves, but a database write has no automatic undo, so it needs a matching undo step set up in advance. Something external, like a sent email or a real charge, can't be undone, so the supervisor's job there is to catch it before it fires. They tested this on a few public benchmarks. On CooperBench, where two agents work on the same codebase, adding a live supervisor took the pair-coding pass rate from 28.8% to 54.7%. It's still early and labeled alpha. The benefit mostly shows up when a run gets branched a lot over a heavy sandbox state, which is exactly where restarting wastes the most tokens and time. If Git was made to make file changes reversible, Shepherd is trying to do the same thing for a live agent run. Shepherd Repo: (don't forget to star it ⭐ ) That said, Shepherd reverts a bad step inside a run. The harness around it, the prompts, tools, and checks the supervisor relies on, still drifts across runs as models and dependencies change. Akshay wrote about making that harness repair itself, where a failing trace gets diagnosed, the fix is verified against the exact input that failed, and the failure is locked as a regression test so it can't recur. Read it below.

Avi Chawla

438,993 просмотров • 20 дней назад

No one destroys what they’ve built with love. No one burns the ground their soul is tied to. For the Jewish people, this land is not just soil—it is memory, sacrifice, and hope. Every stone tells a story. Every tree is a prayer. They have cried over this land, bled for it, and come home to it after centuries of exile. They build, protect, and cherish it like a mother embraces her child. But those who have no roots here feel nothing. They do not weep when the hills burn. They do not mourn the trees turned to ash. Again and again, they set fire to what they do not value—forests, fields, life itself. Yet still, the true sons and daughters of this land rise. They run into the flames to save her. They stand watch, not for glory, but out of love. Because this land is not just theirs—it is them. #Israelonfire #IsraelUnderAttack
0:13

No one destroys what they’ve built with love. No one burns the ground their soul is tied to. For the Jewish people, this land is not just soil—it is memory, sacrifice, and hope. Every stone tells a story. Every tree is a prayer. They have cried over this land, bled for it, and come home to it after centuries of exile. They build, protect, and cherish it like a mother embraces her child. But those who have no roots here feel nothing. They do not weep when the hills burn. They do not mourn the trees turned to ash. Again and again, they set fire to what they do not value—forests, fields, life itself. Yet still, the true sons and daughters of this land rise. They run into the flames to save her. They stand watch, not for glory, but out of love. Because this land is not just theirs—it is them. #Israelonfire #IsraelUnderAttack

The Voice Of Truth 🙌

13,129 просмотров • 1 год назад

Everlyn isn’t just a video model. It’s a system you can trust. 🌀 At its core is the Lyn Protocol, the onchain layer that gives AI video permanence, provenance, and ownership. Here’s what it means: 🔹Decentralized inference: Videos are not generated by a single company’s servers. They run across a distributed network of nodes. 🔹Agent ownership: When you summon your agent, it is minted onchain. It belongs to you, not to a platform. 🔹Video provenance: Every render carries a timestamp and fingerprint written to the ledger. No one can fake or steal it. The Lyn Protocol transforms AI video from content into verifiable digital memory.
0:12

Everlyn isn’t just a video model. It’s a system you can trust. 🌀 At its core is the Lyn Protocol, the onchain layer that gives AI video permanence, provenance, and ownership. Here’s what it means: 🔹Decentralized inference: Videos are not generated by a single company’s servers. They run across a distributed network of nodes. 🔹Agent ownership: When you summon your agent, it is minted onchain. It belongs to you, not to a platform. 🔹Video provenance: Every render carries a timestamp and fingerprint written to the ledger. No one can fake or steal it. The Lyn Protocol transforms AI video from content into verifiable digital memory.

Everlyn

93,078 просмотров • 11 месяцев назад

this is ACTUALLY insane. shipping one teardown is the demo. this is what the workflow is actually for. your best ad dies in two weeks. you can't run it harder without burning it out, and you can't clone your way out because andromeda clusters the copies into one entity. nineteen never spend. your winner stays a one-shot, which is rough when it's the only thing working. the brands that scale keep the structure that converts and rebuild everything on top of it. same bones, new person, new setting. distinct enough that the algo reads each as its own ad. the production loop isn't there to ship your winner once. it's there to rebuild it twenty times before it burns.
0:14

this is ACTUALLY insane. shipping one teardown is the demo. this is what the workflow is actually for. your best ad dies in two weeks. you can't run it harder without burning it out, and you can't clone your way out because andromeda clusters the copies into one entity. nineteen never spend. your winner stays a one-shot, which is rough when it's the only thing working. the brands that scale keep the structure that converts and rebuild everything on top of it. same bones, new person, new setting. distinct enough that the algo reads each as its own ad. the production loop isn't there to ship your winner once. it's there to rebuild it twenty times before it burns.

Sulfur

11,066 просмотров • 1 месяц назад