Loading video...

Video Failed to Load

Go Home

๐Ÿซจ AGENT CHAOS ๐Ÿซจ 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...

elder_plinius's profile picture

Pliny the Liberator ๐Ÿ‰๓ …ซ๓ „ผ๓ „ฟ๓ …†๓ „ต๓ „๓ …€๓ „ผ๓ „น๓ „พ๓ …‰๓ …ญ

177,281 subscribers

39,818 views โ€ข 2 months ago โ€ขvia X (Twitter)

LIVE

Anya Rossiโ€ข Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing agent-tail: a dev tool that makes your logs easily accessible to agents. npm i agent-tail Wrap dev server commands, add the Vite/Next plugin, install the skill, and your agent has full context of your browser, server, and any other logs. Link to full docs below โ†“
0:10

Introducing agent-tail: a dev tool that makes your logs easily accessible to agents. npm i agent-tail Wrap dev server commands, add the Vite/Next plugin, install the skill, and your agent has full context of your browser, server, and any other logs. Link to full docs below โ†“

Kyle Gill

29,373 views โ€ข 4 months ago

The observer
0:10

The observer

Gone Fishing ๐ŸŽฃ

15,887 views โ€ข 1 year ago

A commission for ๐Ÿ•ณ๏ธThe Observer๐Ÿšช ! Quite an unusual request, but I had a lot of fun animating it, thank you! โœจ
0:14

A commission for ๐Ÿ•ณ๏ธThe Observer๐Ÿšช ! Quite an unusual request, but I had a lot of fun animating it, thank you! โœจ

azuladiana โ€ข comms OPEN โ€ข ๐Ÿค–โƒ 

70,320 views โ€ข 5 months ago

A Way of the Cross procession held over the Brooklyn Bridge in New York Video: Orthodox Observer
0:10

A Way of the Cross procession held over the Brooklyn Bridge in New York Video: Orthodox Observer

Sachin Jose

24,841 views โ€ข 1 year ago

Thrilled to announce the Monitor tool which lets Claude create background scripts that wake the agent up when needed. Big token saver and great way to move away from polling in the agent loop Claude can now: * Follow logs for errors * Poll PRs via script * and more!
0:14

Thrilled to announce the Monitor tool which lets Claude create background scripts that wake the agent up when needed. Big token saver and great way to move away from polling in the agent loop Claude can now: * Follow logs for errors * Poll PRs via script * and more!

Noah Zweben

1,186,375 views โ€ข 2 months ago

๐Ÿšจ WTF?! Somali Rep. Ilhan Omar just called the anti-ICE terrorist in Minneapolis a "LEGAL OBSERVER" "The killing of a legal observer." Un-freaking-believable. DEPORT ILHAN OMAR! She is a traitor.
0:13

๐Ÿšจ WTF?! Somali Rep. Ilhan Omar just called the anti-ICE terrorist in Minneapolis a "LEGAL OBSERVER" "The killing of a legal observer." Un-freaking-believable. DEPORT ILHAN OMAR! She is a traitor.

Eric Daugherty

45,471 views โ€ข 5 months ago

Just open-sourced PositionObserver โ€“ the missing observer to detect position, size & visibility changes. โšก๏ธ Async & efficient โ€” zero polling, powered by native observers ๐ŸŽฏ Track elements relative to viewport or any root element Try it out ๐Ÿ‘‰ npm install position-observer
0:17

Just open-sourced PositionObserver โ€“ the missing observer to detect position, size & visibility changes. โšก๏ธ Async & efficient โ€” zero polling, powered by native observers ๐ŸŽฏ Track elements relative to viewport or any root element Try it out ๐Ÿ‘‰ npm install position-observer

Claudรฉric Demers

21,513 views โ€ข 1 year ago

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

199,917 views โ€ข 27 days ago

A foreign "observer" from #Africa, at gunpoint, assures that everything is fine in the #Russian pseudo-elections and there are no violations.
0:17

A foreign "observer" from #Africa, at gunpoint, assures that everything is fine in the #Russian pseudo-elections and there are no violations.

NEXTA

380,973 views โ€ข 2 years ago

New video shows an ICE agent adding a legal observer to a "domestic terrorist" database for peacefully recording him: "We have a nice little database. And now you're considered a domestic terrorist"
0:19

New video shows an ICE agent adding a legal observer to a "domestic terrorist" database for peacefully recording him: "We have a nice little database. And now you're considered a domestic terrorist"

FactPost

13,701 views โ€ข 5 months ago

Chat...STOP blaming the Observers at the EWC Broadcast. THIS IS A DIRECTING PROBLEM. Observers are who is flying around the map, always trying their best to make their specific POV look the best. A Live broadcast director is making the decision when to switch between Player POV, an observer, the Map etc. Name a more iconic duo than gamers always managing to blame and attack lower level workers instead of the ones actually making decision at the top.
0:20

Chat...STOP blaming the Observers at the EWC Broadcast. THIS IS A DIRECTING PROBLEM. Observers are who is flying around the map, always trying their best to make their specific POV look the best. A Live broadcast director is making the decision when to switch between Player POV, an observer, the Map etc. Name a more iconic duo than gamers always managing to blame and attack lower level workers instead of the ones actually making decision at the top.

Mokey

84,160 views โ€ข 11 months ago

Yesterday, I was invited by NOAA to be an observer on a Hurricane Hunters mission into Hurricane Milton. During the 8 hour flight, we penetrated the eye 3 times. It was an extremely intense & educational experience. This powerful storm deserves serious attention from everyone.
0:12

Yesterday, I was invited by NOAA to be an observer on a Hurricane Hunters mission into Hurricane Milton. During the 8 hour flight, we penetrated the eye 3 times. It was an extremely intense & educational experience. This powerful storm deserves serious attention from everyone.

Maxwell Alejandro Frost

1,525,503 views โ€ข 1 year ago

๐ŸšจNOW: NEW YORKERS DEMAND AN END TO ICE TERROR!๐Ÿšจ Earlier today ICE agents shot and killed a legal observer while conducting a raid in Minneapolis. Video evidence clearly shows that the woman was driving away and that ICE is lying and this was not done in self-defense. Just yesterday, 2,000 ICE agents descended upon the city in a major racist crackdown targeting Somalis. We denounce use of ICE across the country, and demand these murderers be removed from communities immediately.
0:17

๐ŸšจNOW: NEW YORKERS DEMAND AN END TO ICE TERROR!๐Ÿšจ Earlier today ICE agents shot and killed a legal observer while conducting a raid in Minneapolis. Video evidence clearly shows that the woman was driving away and that ICE is lying and this was not done in self-defense. Just yesterday, 2,000 ICE agents descended upon the city in a major racist crackdown targeting Somalis. We denounce use of ICE across the country, and demand these murderers be removed from communities immediately.

Party for Socialism and Liberation

45,852 views โ€ข 5 months ago

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 - Anthropicโ€™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 GitHubโ€™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 ๐Ÿ˜ - 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 Thereโ€™s a lot more. Some of it hasnโ€™t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, Iโ€™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.
0:24

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 - Anthropicโ€™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 GitHubโ€™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 ๐Ÿ˜ - 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 Thereโ€™s a lot more. Some of it hasnโ€™t fully landed yet, but everything that has is already in Insiders. The next stable release should drop in early February. As usual, Iโ€™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.

Oren Melamed

29,555 views โ€ข 5 months ago

A brocken spectre is the magnified (and apparently enormous) shadow of an observer cast upon clouds opposite the Sun's direction, typically surrounded by rainbow-like bands.
0:10

A brocken spectre is the magnified (and apparently enormous) shadow of an observer cast upon clouds opposite the Sun's direction, typically surrounded by rainbow-like bands.

Massimo

25,280 views โ€ข 11 months ago

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAIโ€™s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAIโ€™s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agentโ€”from visual design to deployment and performance tuningโ€”inside a single unified system.
0:10

OpenAI's AgentKit will be so insane, build every step of agents on one platform. These visual agent builders make the whole process of iterating and launching agents far more efficient. It sits on top of the Responses API and unifies the tools that were previously scattered across SDKs and custom orchestration. It lets developers create agent workflows visually, connect data sources securely, and measure performance automatically without coding every layer by hand. The core of AgentKit is the Agent Builder, a drag-and-drop canvas where each node represents an action, guardrail, or decision branch. Developers can link these nodes into multi-agent workflows, preview results instantly, and version each setup. It supports inline evaluation so that developers can see how changes affect output before deploying. The Connector Registry is a single admin panel that manages how data and tools connect across the OpenAI ecosystem. It centralizes integrations like Google Drive, SharePoint, Dropbox, and Microsoft Teams. Large organizations can govern access and flow of data between agents securely under one global console. ChatKit provides a ready-to-use chat interface for embedding agents inside apps or websites. It manages streaming, message threads, and model reasoning displays automatically. Developers can skin the interface to match their product without writing custom front-end code. Under the hood, all these blocks use the same execution core that runs agent reasoning through OpenAIโ€™s APIs. Workflows in Agent Builder compile down to structured instructions for the Responses API, which handles model calls, tool use, and context passing. Connector Registry handles authentication and routing for external tools, while Evals and RFT provide feedback loops that improve agents over time. This integration means developers no longer need to handle orchestration logic, model evaluation pipelines, or safety layers separately. Everything runs natively within OpenAIโ€™s control plane with managed security, automatic versioning, and built-in testing. In short, AgentKit standardizes the entire life cycle of an AI agentโ€”from visual design to deployment and performance tuningโ€”inside a single unified system.

Rohan Paul

178,460 views โ€ข 8 months ago

Base Town: 1-shotted by 1 of our Claude agents ๐Ÿ˜ฒ 36,731 blocks was placed by code via procedural city generation that understands urban planning. No human dragged and dropped anything. In Doppel agents are first-class builders. Other platforms let you use AI tools inside a manual building flow. Doppel lets AI be the builder. The agent doesn't assist, it architects, generates, deploys, and animates an entire city from scratch. This is only v0. Blocks are just the starting primitive.
0:19

Base Town: 1-shotted by 1 of our Claude agents ๐Ÿ˜ฒ 36,731 blocks was placed by code via procedural city generation that understands urban planning. No human dragged and dropped anything. In Doppel agents are first-class builders. Other platforms let you use AI tools inside a manual building flow. Doppel lets AI be the builder. The agent doesn't assist, it architects, generates, deploys, and animates an entire city from scratch. This is only v0. Blocks are just the starting primitive.

Doppel

27,430 views โ€ข 4 months ago

๐ŸŽฏ Focus DLC is out for the Hypno Eyes! ๐ŸŽฏ These shaders will ALWAYS face the observer. Designed to work with 99% of avatars๐Ÿ˜‰ Get it now ๐Ÿ‘‰ ๐Ÿ‘ˆ RT for for a chance to win one of 3 hypno + focus keys!
0:16

๐ŸŽฏ Focus DLC is out for the Hypno Eyes! ๐ŸŽฏ These shaders will ALWAYS face the observer. Designed to work with 99% of avatars๐Ÿ˜‰ Get it now ๐Ÿ‘‰ ๐Ÿ‘ˆ RT for for a chance to win one of 3 hypno + focus keys!

๐ŸŒฟ Value

34,854 views โ€ข 3 years ago