Загрузка видео...

Не удалось загрузить видео

На главную

Karpathy compressed the agent problem into 1 sentence: "If you can't evaluate then you can't auto research it, right?" That's the rule I keep coming back to with long-running coding agents Before you launch /goal or /loop, write the verifier: - what counts as done - what evidence proves...

alphabatcher's profile picture

Alpha Batcher

51,988 subscribers

43,806 просмотров • 25 дней назад •via X (Twitter)

ОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

The guy who kicked off the entire "loop engineering" wave Peter Steinberger: "You shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agents." One post. 6.5M views in a week. In this talk he walks the real stack: the agent loop, a verifier that fails its own work and retries, and a loop that rewrites the agent while he sleeps. Worth more than any $500 vibe-coding course. Watch it, then read the full breakdown of the 4 loops below.
17:30

The guy who kicked off the entire "loop engineering" wave Peter Steinberger: "You shouldn't be prompting coding agents anymore. You should be designing loops that prompt your agents." One post. 6.5M views in a week. In this talk he walks the real stack: the agent loop, a verifier that fails its own work and retries, and a loop that rewrites the agent while he sleeps. Worth more than any $500 vibe-coding course. Watch it, then read the full breakdown of the 4 loops below.

dunik

218,483 просмотров • 17 дней назад

i have created a master loop harness that allows you to run perpetual mission loops that create goal loops that then spawn agent loops which then run their own workflow loops which finally run the tool loops. i really wish i was joking 🙃
1:15

i have created a master loop harness that allows you to run perpetual mission loops that create goal loops that then spawn agent loops which then run their own workflow loops which finally run the tool loops. i really wish i was joking 🙃

Nathan Wilbanks

64,871 просмотров • 1 месяц назад

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this
0:24

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

57,975 просмотров • 1 месяц назад

Boris Cherny, the engineer who built Claude Code: "I don't talk to an agent anymore. I talk to a loop" a prompt is one instruction you babysit. a loop is a goal the AI works toward on its own: > it plans > does the work > checks itself > fixes what's weak > and repeats until it's done you step out, the work keeps going that's the shift the best engineers quietly moved to. most people hear a line like that and have no idea what it means in practice this breaks it down without the hype: what a loop actually is, when it's worth building, when it's a money trap, and how to run one yourself today watch his clip, then read the article below
0:40

Boris Cherny, the engineer who built Claude Code: "I don't talk to an agent anymore. I talk to a loop" a prompt is one instruction you babysit. a loop is a goal the AI works toward on its own: > it plans > does the work > checks itself > fixes what's weak > and repeats until it's done you step out, the work keeps going that's the shift the best engineers quietly moved to. most people hear a line like that and have no idea what it means in practice this breaks it down without the hype: what a loop actually is, when it's worth building, when it's a money trap, and how to run one yourself today watch his clip, then read the article below

Dep

20,529 просмотров • 19 дней назад

My brother (Daniel Cohen Hillel) and I worked on a fun project tonight, inspired by Yohei : Coding Agent that follows the Test Driven Development (TDD) methodology! You write the tests - and the agent runs in a loop until it creates the feature properly! 1/6 #buildinpublic
0:49

My brother (Daniel Cohen Hillel) and I worked on a fun project tonight, inspired by Yohei : Coding Agent that follows the Test Driven Development (TDD) methodology! You write the tests - and the agent runs in a loop until it creates the feature properly! 1/6 #buildinpublic

Adam

384,813 просмотров • 3 лет назад

Spotify Chief Architect, Niklas Gustavsson: "Once we added loops, our agent success rate went from 20-30% to 80%." Everyone's chasing a smarter model. Spotify just built a better loop. 26 min with Claude Code creator Boris Cherny on how they run agents across a 20M-line monorepo. 73% of PRs are AI-assisted. 4,500 deploys a day. 2,900 engineers. loops + a verifier that runs CI + a house-style codebase + auto-merge - that's the secret. close the loop: let the agent run the build, read what failed, and fix itself. Watch the talk, then save the playbook.
26:10

Spotify Chief Architect, Niklas Gustavsson: "Once we added loops, our agent success rate went from 20-30% to 80%." Everyone's chasing a smarter model. Spotify just built a better loop. 26 min with Claude Code creator Boris Cherny on how they run agents across a 20M-line monorepo. 73% of PRs are AI-assisted. 4,500 deploys a day. 2,900 engineers. loops + a verifier that runs CI + a house-style codebase + auto-merge - that's the secret. close the loop: let the agent run the build, read what failed, and fix itself. Watch the talk, then save the playbook.

shmidt

21,748 просмотров • 9 дней назад

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵
1:45

introducing Ariana Automations every other tool gives agents a sandbox. we give them a full linux computer with sudo, docker, their own IP now you can run scripts based on what the agent does setup the environment once, then get rid of the human in the loop (you) a 🧵

Anicet

35,735 просмотров • 6 месяцев назад

Anthropic engineers just dropped 40 minutes on how they actually build loops with Claude Code. Not prompts. Not tools. Loops. 3 agents. 1 loop. One plans. One builds. One judges. Plan → Build → Judge → Repeat. The agent doesn't stop until the app works. Most people are building agents that run once and hope for the best. The best teams are building agents that cycle, self-correct, and improve with every iteration. That's the gap. Watch it, then read this before you build your next loop.
39:36

Anthropic engineers just dropped 40 minutes on how they actually build loops with Claude Code. Not prompts. Not tools. Loops. 3 agents. 1 loop. One plans. One builds. One judges. Plan → Build → Judge → Repeat. The agent doesn't stop until the app works. Most people are building agents that run once and hope for the best. The best teams are building agents that cycle, self-correct, and improve with every iteration. That's the gap. Watch it, then read this before you build your next loop.

Rahul

60,310 просмотров • 8 дней назад

karpathy just broke the internet with something called auto research it’s basically an ai research agent that runs experiments for you 24/7 you give it a goal like “make this model better” “find a higher converting landing page” “lower customer acquisition cost” then it runs a loop: 1) plan an experiment 2) edit the code or config 3) run a short test on a gpu 4) read the metrics 5) keep the winner 6) try again over and over while you sleep by the morning you wake up to the best version actual tested improvements think of it like a robot research intern that runs hundreds of experiments and only keeps the winners this is link to his repo for your to mess around with it in the latest episode of The Startup Ideas Podcast (SIP) 🧃 i break down: • what auto research actually is • how it works step by step • 10 business ideas you can build with it • how to install it and start using it this one is saucy because tools like this change how startups get built watch
24:21

karpathy just broke the internet with something called auto research it’s basically an ai research agent that runs experiments for you 24/7 you give it a goal like “make this model better” “find a higher converting landing page” “lower customer acquisition cost” then it runs a loop: 1) plan an experiment 2) edit the code or config 3) run a short test on a gpu 4) read the metrics 5) keep the winner 6) try again over and over while you sleep by the morning you wake up to the best version actual tested improvements think of it like a robot research intern that runs hundreds of experiments and only keeps the winners this is link to his repo for your to mess around with it in the latest episode of The Startup Ideas Podcast (SIP) 🧃 i break down: • what auto research actually is • how it works step by step • 10 business ideas you can build with it • how to install it and start using it this one is saucy because tools like this change how startups get built watch

GREG ISENBERG

435,283 просмотров • 3 месяцев назад

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch
58:55

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

375,365 просмотров • 3 месяцев назад

HERMES AGENT HAS 5 SYSTEMS RUNNING UNDER THE HOOD. UNDERSTAND THEM AND YOU USE THE AGENT 10X BETTER. In this video Alejandro AO 🤗 explained: 1. THE AGENT LOOP every message triggers the same cycle: → you send a message → Hermes builds context (SOUL.md + memory.md + user.md + skills + tools + message history) → sends everything to the LLM → LLM decides: call a tool or respond → if tool call: execute, return result, loop back → if response: deliver to you → after response: memory update (agent checks if anything is worth remembering, writes to memory.md or user.md) this loop is why Hermes gets better over time. the memory update after every response means the agent learns from every conversation. 2. CONTEXT ASSEMBLY what the LLM sees on every turn: → SOUL.md (your agent's personality and rules) → memory.md (facts the agent learned over time) → user.md (facts about you, auto-updated) → AGENTS.md and .hermes.md (project context files) → skill descriptions (loaded on demand) → tool schemas (available actions) → message history (current conversation) if SOUL.md is empty, Hermes falls back to a default system prompt. write your own SOUL.md and the agent becomes yours, not generic. CONTEXT COMPRESSION: conversations hit context limits. Hermes handles this at two checkpoints: preflight: before each turn. if conversation exceeds 50% of context window, compression fires. older messages get summarized. last 20 messages stay intact (protect_last_n). gateway auto-compression: between turns. fires at 85%. more aggressive. prevents API errors before the agent even starts processing your message. after compression, a new session lineage ID is generated. the agent can trace back to the original conversation through SQLite. three things break prompt cache: switching models mid-session, changing memory files, or changing context files. 3. THE GATEWAY the system that keeps Hermes reachable on 27+ messaging platforms. an async loop runs continuously. listens for incoming messages from Telegram, Discord, Slack, WhatsApp, email, SMS, and every other adapter. when a message arrives: → gateway identifies which session it belongs to → queries SQLite for the full message history (session ID = platform prefix + chat ID) → builds the context from scratch → sends everything into the agent loop → delivers the response back to the platform the gateway also runs the session manager. when you send a message while the agent is busy: → default: queued for next turn → /steer: injected without interrupting → /interrupt: stops current work without the gateway, Hermes is a CLI tool. with the gateway, Hermes is an always-on agent you reach from your phone. 4. MEMORY (THREE LAYERS) LAYER 1 — MARKDOWN FILES SOUL.md (identity), memory.md (learned facts), user.md (facts about you). injected into context after the system prompt. updated by the agent after every response. LAYER 2 — SQLITE full transcripts of every session stored locally. FTS5 full-text search across all past conversations. session lineage tracking across compressions. the agent can recall what you discussed weeks ago using /recall or session search. LAYER 3 — EXTERNAL PROVIDERS (optional) 8 supported providers: Mem0, SuperMemory, Honcho, Zep, and more. each works differently (semantic search, LLM extraction, similarity matching). queried after the first message in each session. the agent processes your topic first, then checks external memory for related context from past conversations. not enabled by default. enable for significantly better long-term recall. 5. CRON ENGINE a loop inside the gateway ticks every 60 seconds. each tick checks ~/.hermes/cron/jobs.json for scheduled tasks. if a job is due: → fresh session (no chat history, no memory pollution) → execute the prompt with assigned tools → store the run output as markdown in ~/.hermes/cron/output/[job-id]/ → deliver result to your home messaging platform cron does NOT use the send_message tool. delivery happens at the system level, not the agent level. a cron session cannot create more cron jobs. prevents runaway loops. WHY THIS MATTERS: the agent loop teaches it. the context assembly focuses it. the gateway reaches it. the memory remembers it. the cron engine automates it. five systems. one agent. understanding how they connect changes how you configure every level. full 15 levels breakdown in the article 👇
40:28

HERMES AGENT HAS 5 SYSTEMS RUNNING UNDER THE HOOD. UNDERSTAND THEM AND YOU USE THE AGENT 10X BETTER. In this video Alejandro AO 🤗 explained: 1. THE AGENT LOOP every message triggers the same cycle: → you send a message → Hermes builds context (SOUL.md + memory.md + user.md + skills + tools + message history) → sends everything to the LLM → LLM decides: call a tool or respond → if tool call: execute, return result, loop back → if response: deliver to you → after response: memory update (agent checks if anything is worth remembering, writes to memory.md or user.md) this loop is why Hermes gets better over time. the memory update after every response means the agent learns from every conversation. 2. CONTEXT ASSEMBLY what the LLM sees on every turn: → SOUL.md (your agent's personality and rules) → memory.md (facts the agent learned over time) → user.md (facts about you, auto-updated) → AGENTS.md and .hermes.md (project context files) → skill descriptions (loaded on demand) → tool schemas (available actions) → message history (current conversation) if SOUL.md is empty, Hermes falls back to a default system prompt. write your own SOUL.md and the agent becomes yours, not generic. CONTEXT COMPRESSION: conversations hit context limits. Hermes handles this at two checkpoints: preflight: before each turn. if conversation exceeds 50% of context window, compression fires. older messages get summarized. last 20 messages stay intact (protect_last_n). gateway auto-compression: between turns. fires at 85%. more aggressive. prevents API errors before the agent even starts processing your message. after compression, a new session lineage ID is generated. the agent can trace back to the original conversation through SQLite. three things break prompt cache: switching models mid-session, changing memory files, or changing context files. 3. THE GATEWAY the system that keeps Hermes reachable on 27+ messaging platforms. an async loop runs continuously. listens for incoming messages from Telegram, Discord, Slack, WhatsApp, email, SMS, and every other adapter. when a message arrives: → gateway identifies which session it belongs to → queries SQLite for the full message history (session ID = platform prefix + chat ID) → builds the context from scratch → sends everything into the agent loop → delivers the response back to the platform the gateway also runs the session manager. when you send a message while the agent is busy: → default: queued for next turn → /steer: injected without interrupting → /interrupt: stops current work without the gateway, Hermes is a CLI tool. with the gateway, Hermes is an always-on agent you reach from your phone. 4. MEMORY (THREE LAYERS) LAYER 1 — MARKDOWN FILES SOUL.md (identity), memory.md (learned facts), user.md (facts about you). injected into context after the system prompt. updated by the agent after every response. LAYER 2 — SQLITE full transcripts of every session stored locally. FTS5 full-text search across all past conversations. session lineage tracking across compressions. the agent can recall what you discussed weeks ago using /recall or session search. LAYER 3 — EXTERNAL PROVIDERS (optional) 8 supported providers: Mem0, SuperMemory, Honcho, Zep, and more. each works differently (semantic search, LLM extraction, similarity matching). queried after the first message in each session. the agent processes your topic first, then checks external memory for related context from past conversations. not enabled by default. enable for significantly better long-term recall. 5. CRON ENGINE a loop inside the gateway ticks every 60 seconds. each tick checks ~/.hermes/cron/jobs.json for scheduled tasks. if a job is due: → fresh session (no chat history, no memory pollution) → execute the prompt with assigned tools → store the run output as markdown in ~/.hermes/cron/output/[job-id]/ → deliver result to your home messaging platform cron does NOT use the send_message tool. delivery happens at the system level, not the agent level. a cron session cannot create more cron jobs. prevents runaway loops. WHY THIS MATTERS: the agent loop teaches it. the context assembly focuses it. the gateway reaches it. the memory remembers it. the cron engine automates it. five systems. one agent. understanding how they connect changes how you configure every level. full 15 levels breakdown in the article 👇

YanXbt

50,622 просмотров • 16 дней назад

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses. trace every run → judge it with an LLM → diagnose → fix → ship. That loop is how agents self-improve over time. Agent loops + memory + harness + evals - thats the stack. Watch it, then save the framework below.
19:30

Ex-Google engineer explained AI agent loops, harness, evals in 20 minutes - better than 500$ courses. trace every run → judge it with an LLM → diagnose → fix → ship. That loop is how agents self-improve over time. Agent loops + memory + harness + evals - thats the stack. Watch it, then save the framework below.

Movez

551,588 просмотров • 11 дней назад

an OpenAI engineer just showed how he gets agents to do his whole job: code, debug and more, using loops 29 minutes from the engineer who coined "harness engineering" he writes the rules, agents write the code, a reviewer agent loops until it's right the winners won't have the smartest model, they'll have the best loop around it watch it, then read the full guide on loops below
29:10

an OpenAI engineer just showed how he gets agents to do his whole job: code, debug and more, using loops 29 minutes from the engineer who coined "harness engineering" he writes the rules, agents write the code, a reviewer agent loops until it's right the winners won't have the smartest model, they'll have the best loop around it watch it, then read the full guide on loops below

Anatoli Kopadze

174,706 просмотров • 17 дней назад

the full 12-minute run sped to 80 seconds, watch carnice v2 cycle through plan, terminal probe, todo update, write the report, then read it back to verify, until the loop closes. no edit cuts, no narration, just the model working at 5x time. the rare-bird verify moment lands in the last 20 seconds, write_file then read_file then done. closed loop on consumer hardware, you can watch it happen.
1:20

the full 12-minute run sped to 80 seconds, watch carnice v2 cycle through plan, terminal probe, todo update, write the report, then read it back to verify, until the loop closes. no edit cuts, no narration, just the model working at 5x time. the rare-bird verify moment lands in the last 20 seconds, write_file then read_file then done. closed loop on consumer hardware, you can watch it happen.

Sudo su

11,881 просмотров • 2 месяцев назад

ChatCut’s agent cuts 1 video into 5 editable clips. It asks what you want, checks before making edits, and gives you a timeline for every clip so you can keep tweaking. You can change the cut, add music, add motion graphics, and generate b-roll. Then export the videos, or export the XML and keep editing somewhere else.
0:36

ChatCut’s agent cuts 1 video into 5 editable clips. It asks what you want, checks before making edits, and gives you a timeline for every clip so you can keep tweaking. You can change the cut, add music, add motion graphics, and generate b-roll. Then export the videos, or export the XML and keep editing somewhere else.

ChatCut

35,913 просмотров • 18 дней назад

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.
0:37

Boris Cherny runs Claude Code at Anthropic. His line should stop you mid-scroll: "I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops." The skill moved. From writing prompts to building the loop around them. A loop that works has three things. Drop one and it burns money in circles. 1. A finish line it can prove. Tests pass or they fail. "Looks done" is not a finish line. 2. A checker that did not write the code. A model grading itself always says yes. 3. Brakes set before you start. A step limit. A money ceiling. A stop condition. That is the whole game. The loop does the work. You design the cage it runs in. Full breakdown below.

shmidt

16,085 просмотров • 17 дней назад

introducing agent-loops + ui viewer i gave droid+gpt5.2 codex dannys tweet asked to reverse engineer it then rebuilt matts loop system (gh issue → pr) hooked them together so you can run loops by creating issues locally, on gh or in your own ui. (+ stole Mario Zechner's session generator) repos: - agent-loop - loop ui
4:28

introducing agent-loops + ui viewer i gave droid+gpt5.2 codex dannys tweet asked to reverse engineer it then rebuilt matts loop system (gh issue → pr) hooked them together so you can run loops by creating issues locally, on gh or in your own ui. (+ stole Mario Zechner's session generator) repos: - agent-loop - loop ui

Ben Tossell

115,991 просмотров • 5 месяцев назад

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents" "Close the loop, give the model a way to verify its own output" In a 20-minute session, an Anthropic Team member breaks down how to build agents that improve themselves The real setup is Claude running through loops, plan mode, and dynamic workflows Better than most $300 agent courses Bookmark and watch the talk Then read the article below
19:32

Anthropic Research Lead: "99% of our engineers run swarms of 300+ self-improving agents" "Close the loop, give the model a way to verify its own output" In a 20-minute session, an Anthropic Team member breaks down how to build agents that improve themselves The real setup is Claude running through loops, plan mode, and dynamic workflows Better than most $300 agent courses Bookmark and watch the talk Then read the article below

rari

378,669 просмотров • 16 дней назад

Demo 2: human + agent design loop inside Codex. Not every workflow needs the agent to drive everything. You design in Open Design. Codex reviews the output. It can inspect files, open pages, test interactions, critique the design, and turn feedback into the next prompt. Design becomes a human + agent feedback loop.
1:08

Demo 2: human + agent design loop inside Codex. Not every workflow needs the agent to drive everything. You design in Open Design. Codex reviews the output. It can inspect files, open pages, test interactions, critique the design, and turn feedback into the next prompt. Design becomes a human + agent feedback loop.

Open Design

20,103 просмотров • 1 месяц назад

1 HOUR WITH KARPATHY. SAVE THIS BEFORE YOU OPEN CLAUDE CODE TODAY > autonomous agents that improve themselves without a human in the loop that's where Claude Opus 4.8 is heading > the 32 skills in this article are the foundation Karpathy explains what's coming
1:00:09

1 HOUR WITH KARPATHY. SAVE THIS BEFORE YOU OPEN CLAUDE CODE TODAY > autonomous agents that improve themselves without a human in the loop that's where Claude Opus 4.8 is heading > the 32 skills in this article are the foundation Karpathy explains what's coming

Mr. Buzzoni

69,151 просмотров • 1 месяц назад