正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

A GROK ENGINEER JUST SHOWED HOW TO MAKE AGENTS IMPROVE THEMSELVES AFTER EVERY RUN most agents lose useful feedback when a task ends: what failed, what changed, and which fix actually worked grok can run 2 loops at once → one handles the task → the other reviews the... result → extracts the lesson → stores it for the next run instead of expanding one giant prompt, feedback can be saved as small reusable memory files. one solid correction can help across 10 future tasks research, coding, debugging, and review get more consistent when each run can reuse context and lessons from earlier work this is the shift from repeating the same corrections to building an agent that can reuse what it already learned. bookmark this.show more

Gipp 🦅

10,539 subscribers

25,540 次观看 • 2 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

45 条评论

slash1s 的头像

slash1s2 天前

something new for me tbh

starmex 的头像

starmex1 天前

bookmarked this gipp! thanks

Gipp 🦅 的头像

Gipp 🦅1 天前

ohh thank bro

Argona 的头像

Argona2 天前

hah my agent has been keeping notes on me for weeks and still forgets what i asked

Gipp 🦅 的头像

Gipp 🦅2 天前

by the way, this is a fairly common error for them, so it needs to be resolved as soon as possible

wast3 的头像

wast32 天前

is there a sequel to this?

Gipp 🦅 的头像

Gipp 🦅2 天前

yes, it exists

Bober_smart 的头像

Bober_smart2 天前

Dude, that's really useful information

Gipp 🦅 的头像

Gipp 🦅2 天前

what exactly caught your attention here?

Michael A. Volz 的头像

Michael A. Volz1 天前

Can you name the music track, please? It is awesome.

Gipp 🦅 的头像

Gipp 🦅1 天前

yep

Lee_1909 的头像

Lee_19092 天前

Groundbreaking concept for AI agent improvement.

Gipp 🦅 的头像

Gipp 🦅2 天前

100%, and this era is only continuing

beamnxw ./ 的头像

beamnxw ./1 天前

the next run can finally remember the last mistake

Gipp 🦅 的头像

Gipp 🦅1 天前

and, in essence, fix it completely

Miles S. 的头像

Miles S.1 天前

having one fix carry into the next ten runs is huge

rewind 的头像

rewind2 天前

trying this after my next run

Gipp 🦅 的头像

Gipp 🦅2 天前

I think you should give this a try soon

morph 的头像

morph2 天前

Crazy document

twinedon 的头像

twinedon2 天前

one fix that helps 10 future runs is the whole point

Gipp 🦅 的头像

Gipp 🦅2 天前

the main thing is to catch all of this at the initial stage

shmidt 的头像

shmidt2 天前

alpa document

Yarchi 的头像

Yarchi1 天前

Bro this is pure alpha

Chen 的头像

Chen2 天前

this one hit mid-scroll

Gipp 🦅 的头像

Gipp 🦅2 天前

haha, you like that, bro?

Avid 的头像

Avid2 天前

This is basically a self-improving agent.

Gipp 🦅 的头像

Gipp 🦅2 天前

yeah, but in a cooler package

Roan 的头像

Roan1 天前

self improving AI agents are the future gipp

Gipp 🦅 的头像

Gipp 🦅1 天前

and it is already right beside us

What Happened 的头像

What Happened1 天前

i've been head's down on claude code so i'm a little behind – can grok do this with claude? i'm averse to spending api money if possible.

Lutchyn 的头像

Lutchyn1 天前

The second loop is the real unlock

AI Mastery Guide 的头像

AI Mastery Guide1 天前

Two loops reviewing each other, smart

Egor 的头像

Egor2 天前

parallel review separates task output from memory writing future runs inherit extracted lessons instead of an ever-growing prompt

The Divorce Lawyer - Raiford Dalton Palmer 的头像

The Divorce Lawyer - Raiford Dalton Palmer1 天前

[email protected]? “A Working Grok Engineer?”

byron loor 的头像

byron loor1 天前

双循环自改进这个思路有点意思，但吹得这么玄乎，能不能放点真实日志出来看看，不然我当故事会看hhh

Ridark 的头像

Ridark1 天前

Real gold in this post, huge thanks

Bella 的头像

Bella15 小时前

双循环自我改进这个思路靠谱，比那些吹AGI的实在。不过工程上难点在于怎么定义'有用反馈'，别把噪音也学进去了。

TTD 🇮🇩 的头像

TTD 🇮🇩1 天前

Agreed

Sarah rocha 的头像

Sarah rocha1 天前

双循环这个思路有点意思不过跑起来token消耗得翻倍吧适合大厂玩

magsimich 的头像

magsimich1 天前

Self improvement agent is game changer

Lay 的头像

Lay2 天前

The small reusable memory files idea is so much cleaner than endlessly growing the prompt. I want to try this on my own coding loops.

spect 的头像

spect1 天前

it's a real gem that we got this info

boan 的头像

boan2 天前

this changes the whole loop

Kenny1st 的头像

Kenny1st1 天前

every run makes the next one better

cristal💎 的头像

cristal💎1 天前

saving this post before everyone

相关视频

A GROK ENGINEER JUST SHOWED HOW TO MAKE AGENTS IMPROVE THEMSELVES AFTER EVERY RUN most agents lose the useful part when a task ends: the mistake, the correction, and the reason the final version actually worked grok runs two loops at once → one handles the real task → another studies the result → extracts the lesson → saves it for the next run instead of growing one massive prompt, feedback becomes small reusable knowledge files. bad decisions get corrected once, while useful patterns survive across future tasks over time, research, coding and review all inherit what previous runs learned without retraining the model or rebuilding the agent from scratch this is where grok stops feeling like something you keep correcting and starts behaving like a system that compounds what it learns

A GROK ENGINEER JUST SHOWED HOW TO MAKE AGENTS IMPROVE THEMSELVES AFTER EVERY RUN most agents lose the useful part when a task ends: the mistake, the correction, and the reason the final version actually worked grok runs two loops at once → one handles the real task → another studies the result → extracts the lesson → saves it for the next run instead of growing one massive prompt, feedback becomes small reusable knowledge files. bad decisions get corrected once, while useful patterns survive across future tasks over time, research, coding and review all inherit what previous runs learned without retraining the model or rebuilding the agent from scratch this is where grok stops feeling like something you keep correcting and starts behaving like a system that compounds what it learns

Gipp 🦅

87,913 次观看 • 3 天前

holy sh*t. this is f**king insane. langchain just documented the missing memory layer for agents that are supposed to improve after every run. instead of stuffing everything into one giant prompt, deep agents can keep long-term memory, reusable skills and lessons from previous tasks. [it takes a few minutes to understand the loop] 1/ run the task 2/ save what actually worked 3/ load that lesson into the next run that’s how an agent stops starting from zero every single time.

holy sh*t. this is f**king insane. langchain just documented the missing memory layer for agents that are supposed to improve after every run. instead of stuffing everything into one giant prompt, deep agents can keep long-term memory, reusable skills and lessons from previous tasks. [it takes a few minutes to understand the loop] 1/ run the task 2/ save what actually worked 3/ load that lesson into the next run that’s how an agent stops starting from zero every single time.

Gipp 🦅

32,523 次观看 • 2 天前

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time. In 30 minutes they built the whole thing live in one session. Here's what they cover: > when to use one agent vs a full team > how to split work so agents don't step on each other > the exact framework for deciding what each agent handles that's exactly why, I put together a guide on building agent teams that actually work. full guide in the article below 👇

darkzodchi

845,105 次观看 • 3 个月前

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into reliable workflows 1:30:15 - Build agents that improve their own work 1:49:05 - Run the complete system without supervision Model → Harness → Reliable Software Most agent tutorials stop once the model can call a tool This one shows you how to build the infrastructure around it within the first 20 minutes Most people are still prompting one agent at a time Andrew Ng is already teaching the layer above: Harnesses that give agents context, tools, tests, and feedback Watch this brilliant course and build the harness Then read the full architecture below ↓

Andrew Ng just released a free 2-hour course on complete Harness Engineering How to go from one prompt to a reliable system of agents that can run, test, and improve themselves: 09:14 - Build your first agent from scratch 33:11 - Master agent loops 1:02:46 - Turn loops into reliable workflows 1:30:15 - Build agents that improve their own work 1:49:05 - Run the complete system without supervision Model → Harness → Reliable Software Most agent tutorials stop once the model can call a tool This one shows you how to build the infrastructure around it within the first 20 minutes Most people are still prompting one agent at a time Andrew Ng is already teaching the layer above: Harnesses that give agents context, tools, tests, and feedback Watch this brilliant course and build the harness Then read the full architecture below ↓

Ichigo

98,000 次观看 • 6 天前

Andrew Ng just released a free 2-hour course on complete Graph Engineering How to go from one prompt to 100 agents that loop, improve, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it finished Andrew Ng is already teaching everything that comes next: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow Systems that improve and run without you are the next one This 2-hour course is worth more than most $500 agent engineering programs Bookmark it and watch before everyone catches up Then read how to run 1,000 agents from one prompt below ↓

Andrew Ng just released a free 2-hour course on complete Graph Engineering How to go from one prompt to 100 agents that loop, improve, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it finished Andrew Ng is already teaching everything that comes next: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow Systems that improve and run without you are the next one This 2-hour course is worth more than most $500 agent engineering programs Bookmark it and watch before everyone catches up Then read how to run 1,000 agents from one prompt below ↓

reira

14,713 次观看 • 9 天前

xAI just gave Grok reusable Skills. Which means you can finally stop repeating yourself like a confused office intern. Build a skill once. Grok can reuse it across chats, edit files, check Gmail, touch GitHub, run code, and handle repeat tasks on command. “Use the skill.” Done. Grok is starting to feel less like a chatbot and more like a digital employee with insomnia. Grok

xAI just gave Grok reusable Skills. Which means you can finally stop repeating yourself like a confused office intern. Build a skill once. Grok can reuse it across chats, edit files, check Gmail, touch GitHub, run code, and handle repeat tasks on command. “Use the skill.” Done. Grok is starting to feel less like a chatbot and more like a digital employee with insomnia. Grok

Mario Nawfal

32,886 次观看 • 4 个月前

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs 1:30:15 - Build agents that rewrite themselves 1:49:05 - Run the full graph system without you Most people are still building one agent and calling it done. Andrew Ng is already teaching everything after: Prompt → Agents → Loops → Graphs → Self-Improving Systems Single agents are the old workflow. Systems that improve and run without you are the new one. This 2-hour watch is worth more than most $500 agent engineering courses. Bookmark and watch it before everyone catches up. Then read how to run 1,000 agents from one prompt below ↓

Lunar

225,470 次观看 • 1 个月前

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

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

58,549 次观看 • 3 个月前

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to an agent graph that can build itself: 0% → 10:16 - build your first AI agent 25% → 41:05 - master prompt engineering 50% → 54:45 - turn agents into graphs 75% → 1:20:10 - run loops inside agent graphs 100% → 1:43:33 - build a graph that builds itself Most people build one agent and stop there. Google is teaching everything that comes after: Prompt → Agents → Graphs → Loops → Self-Building Systems Single agents are the old workflow. Graphs that evolve themselves are the next one. This 2-hour course is worth more than most paid agent engineering courses. Bookmark it and watch today Then read how to run 1,000 agents from one prompt below ↓

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to an agent graph that can build itself: 0% → 10:16 - build your first AI agent 25% → 41:05 - master prompt engineering 50% → 54:45 - turn agents into graphs 75% → 1:20:10 - run loops inside agent graphs 100% → 1:43:33 - build a graph that builds itself Most people build one agent and stop there. Google is teaching everything that comes after: Prompt → Agents → Graphs → Loops → Self-Building Systems Single agents are the old workflow. Graphs that evolve themselves are the next one. This 2-hour course is worth more than most paid agent engineering courses. Bookmark it and watch today Then read how to run 1,000 agents from one prompt below ↓

Lunar

43,779 次观看 • 4 天前

xAI is rolling out Skills on This new feature lets you create custom skills that Grok can reuse across conversations. Skills run inside Grok’s sandbox environment, so they can edit files, use your Connectors (Gmail, GitHub, Notion, etc.), run code, or perform any repeatable task you define. Once you create one, you simply tell Grok “use the [skill name] skill and do…” and it executes it instantly. You can also import skills.md files from other AI tools to bring them over quickly. It turns Grok from a one-shot chat tool into a more persistent, customizable workspace. This is a huge upgrade for anyone who uses Grok regularly.

xAI is rolling out Skills on This new feature lets you create custom skills that Grok can reuse across conversations. Skills run inside Grok’s sandbox environment, so they can edit files, use your Connectors (Gmail, GitHub, Notion, etc.), run code, or perform any repeatable task you define. Once you create one, you simply tell Grok “use the [skill name] skill and do…” and it executes it instantly. You can also import skills.md files from other AI tools to bring them over quickly. It turns Grok from a one-shot chat tool into a more persistent, customizable workspace. This is a huge upgrade for anyone who uses Grok regularly.

Myrhe𝕩

878,498 次观看 • 4 个月前

ByteDance Seed delivered again. They released EdgeBench, to test whether AI agents can improve through experience, using 134 real-world tasks that run for at least 12 hours. The big deal is that it shifts AI evaluation from “what does the model already know?” to “can the model learn while doing real work?” Huge, because future AI agents will not just answer questions from training data. They will enter messy environments, use tools, make attempts, read feedback, fix mistakes, and slowly build better solutions. Most current benchmarks are too short for that, so they mostly test memory, coding skill, or one-shot reasoning. EdgeBench instead gives agents 12-hour real-world tasks with feedback loops, so it can measure whether the agent improves through experience. Each task has a local workspace for fast trial and error, plus a hidden judge that gives stronger feedback on submitted work, which is meant to feel closer to real expert work. The authors then ran frontier agents for about 38,000 total hours and tracked how their best score changed as they kept interacting with the task environment. The big result is that when scores are averaged across many tasks, learning follows a very clean log-sigmoid curve, meaning progress is slow, then faster, then starts to level off. They also found that newer agents seem to learn from environments much faster, with the top models roughly doubling their 2-hour learning speed every 3 months.

ByteDance Seed delivered again. They released EdgeBench, to test whether AI agents can improve through experience, using 134 real-world tasks that run for at least 12 hours. The big deal is that it shifts AI evaluation from “what does the model already know?” to “can the model learn while doing real work?” Huge, because future AI agents will not just answer questions from training data. They will enter messy environments, use tools, make attempts, read feedback, fix mistakes, and slowly build better solutions. Most current benchmarks are too short for that, so they mostly test memory, coding skill, or one-shot reasoning. EdgeBench instead gives agents 12-hour real-world tasks with feedback loops, so it can measure whether the agent improves through experience. Each task has a local workspace for fast trial and error, plus a hidden judge that gives stronger feedback on submitted work, which is meant to feel closer to real expert work. The authors then ran frontier agents for about 38,000 total hours and tracked how their best score changed as they kept interacting with the task environment. The big result is that when scores are averaged across many tasks, learning follows a very clean log-sigmoid curve, meaning progress is slow, then faster, then starts to level off. They also found that newer agents seem to learn from environments much faster, with the top models roughly doubling their 2-hour learning speed every 3 months.

Rohan Paul

14,309 次观看 • 2 个月前

A SpaceXAI engineer just released a free 30-min course on Grok Bot Agents: from your first persistent agent to multi-agent chains that research, ship software, and hand work off to Cursor 05:26 - what actually lives inside a Grok agent 08:49 - the 3 ways to run agents 12:04 - chaining multiple agents into one workflow 16:06 - turning X followers into structured research inside Notion 23:08 - handing coding work from Grok straight to Cursor Most people still treat Grok like a chat window. It answers, you copy, you move on. The shift happens when the agents stop waiting for you: one finds the information, one structures it in Notion, one turns it into working code, and they pass the work down the line on their own. Thirty minutes here beats assembling your setup one agent at a time.

A SpaceXAI engineer just released a free 30-min course on Grok Bot Agents: from your first persistent agent to multi-agent chains that research, ship software, and hand work off to Cursor 05:26 - what actually lives inside a Grok agent 08:49 - the 3 ways to run agents 12:04 - chaining multiple agents into one workflow 16:06 - turning X followers into structured research inside Notion 23:08 - handing coding work from Grok straight to Cursor Most people still treat Grok like a chat window. It answers, you copy, you move on. The shift happens when the agents stop waiting for you: one finds the information, one structures it in Notion, one turns it into working code, and they pass the work down the line on their own. Thirty minutes here beats assembling your setup one agent at a time.

Morlex

16,710 次观看 • 12 天前

The next internet will not be browsed. It will be operated by agents. OptimAI is building the infrastructure behind that shift. • A research task begins with Search pulling live context from the public web and social web • That context moves into Claw, where the agent can execute directly on your device • Domain knowledge becomes a Persona Agent • Core Node v2 keeps the system running at the edge • And x402 will make access and payment feel native to the flow That is the real shift: - from asking AI questions - to deploying intelligence that can work, learn, and compound. A trader can monitor signals. A founder can prepare reports overnight. A builder can publish a specialized agent once, then let others reuse it. This is what the agent-native internet looks like when it is built from the ground up. Start with OptimAI: • Persona Agent: • Claw / Core Node v2: • Search:

The next internet will not be browsed. It will be operated by agents. OptimAI is building the infrastructure behind that shift. • A research task begins with Search pulling live context from the public web and social web • That context moves into Claw, where the agent can execute directly on your device • Domain knowledge becomes a Persona Agent • Core Node v2 keeps the system running at the edge • And x402 will make access and payment feel native to the flow That is the real shift: - from asking AI questions - to deploying intelligence that can work, learn, and compound. A trader can monitor signals. A founder can prepare reports overnight. A builder can publish a specialized agent once, then let others reuse it. This is what the agent-native internet looks like when it is built from the ground up. Start with OptimAI: • Persona Agent: • Claw / Core Node v2: • Search:

OptimAI Network

18,590 次观看 • 4 个月前

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

codila

60,826 次观看 • 1 个月前

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to an agent graph that builds itself: 10:16 - Build your first AI agent 41:05 - Master prompt engineering 54:45 - Turn agents into graphs 1:20:10 - Run loops inside agent graphs 1:43:33 - Build a graph that builds itself Most people ship one agent and stop there. Google is teaching everything after: Prompt → Agents → Graphs → Loops → Self-Building Systems Single agents are the old workflow. Graphs that evolve themselves are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read how to run 1,000 agents from one prompt below ↓

Google just released a free 2-hour course on full Graph Engineering. How to go from one prompt to an agent graph that builds itself: 10:16 - Build your first AI agent 41:05 - Master prompt engineering 54:45 - Turn agents into graphs 1:20:10 - Run loops inside agent graphs 1:43:33 - Build a graph that builds itself Most people ship one agent and stop there. Google is teaching everything after: Prompt → Agents → Graphs → Loops → Self-Building Systems Single agents are the old workflow. Graphs that evolve themselves are the new one. This 2-hour watch is worth more than most paid agent engineering courses. Bookmark and watch it today Then read how to run 1,000 agents from one prompt below ↓

Lunar

52,359 次观看 • 1 个月前

J-Cal’s framework for how to be "AI first". It’s not just a slogan 1. Every task… Ask AI first. “How can I do this better.” 2. Every repeated task… Let your agents take care of it so you can do MORE. 3. Give the agent your last 10 outputs, let it score them, run it daily, and do deep-research weekly on what the best are doing differently.

J-Cal’s framework for how to be "AI first". It’s not just a slogan 1. Every task… Ask AI first. “How can I do this better.” 2. Every repeated task… Let your agents take care of it so you can do MORE. 3. Give the agent your last 10 outputs, let it score them, run it daily, and do deep-research weekly on what the best are doing differently.

This Week in Startups

45,723 次观看 • 4 个月前

THIS GUY TURNED ONE OBSIDIAN VAULT INTO A SHARED BRAIN FOR 5 CLAUDE AGENTS BUILT TO HANDLE 80% OF A SOLO DEVELOPER’S WORK. 00:03 he zooms out and hundreds of connected notes appear on screen. it is the perfect visual for Claude working from one shared project memory instead of starting from zero every session. most developers give Claude 1 file and 1 prompt. this setup gives it the architecture, coding rules, tests, client briefs, and previous decisions before it writes anything. obsidian becomes the memory layer, storing everything in markdown files Claude can read alongside the codebase. every agent works from the same context instead of repeating the same questions. then 5 specialists split the job. one researches, one plans, one codes, one reviews, and one deploys while the developer only controls the important decisions. one vault, 5 agents, 2 model tiers, and a $50 to $150 monthly stack can turn Claude from a chatbot into a small development team.

THIS GUY TURNED ONE OBSIDIAN VAULT INTO A SHARED BRAIN FOR 5 CLAUDE AGENTS BUILT TO HANDLE 80% OF A SOLO DEVELOPER’S WORK. 00:03 he zooms out and hundreds of connected notes appear on screen. it is the perfect visual for Claude working from one shared project memory instead of starting from zero every session. most developers give Claude 1 file and 1 prompt. this setup gives it the architecture, coding rules, tests, client briefs, and previous decisions before it writes anything. obsidian becomes the memory layer, storing everything in markdown files Claude can read alongside the codebase. every agent works from the same context instead of repeating the same questions. then 5 specialists split the job. one researches, one plans, one codes, one reviews, and one deploys while the developer only controls the important decisions. one vault, 5 agents, 2 model tiers, and a $50 to $150 monthly stack can turn Claude from a chatbot into a small development team.

Gipp 🦅

10,799 次观看 • 2 个月前

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

We raised $3M on one observation: Agents learn on your dime. And forget. Every run, your agent figures out the same APIs, makes the same calls, hits the same failures. Because nothing saved what worked. We built Rote by Modiqo Inc to fix this. Point it at any API. Rote reads the spec and builds a surface your agent can call: auth, endpoints, schemas. That's the adapter. When your agent finishes a task, Rote saves the exact calls that worked. That's the flow. Config in. Code out. Runs on your machine. Nothing to watch over. Agents stop starting from scratch. Teams stop paying for the same work twice. Install →

chetan conikee

469,301 次观看 • 3 个月前

Interestingly, as we have AI agents that run in the background, the speed of AI becomes incrementally less important than the core underlying capability level. When you could only give AI small bits of work, then the speed of response mattered a ton. The rate at which you can go back and forth with AI in real-time was the determining factor on how useful it is. But as AI agents can perform more complex and useful tasks in parallel behind the scenes, you can much more easily afford to wait longer for work to get done assuming it’s valuable. Now the focus becomes more on how you review and orchestrate the agents’ work. And the main factor is just how useful and usable is the output that the agent came back with.

Interestingly, as we have AI agents that run in the background, the speed of AI becomes incrementally less important than the core underlying capability level. When you could only give AI small bits of work, then the speed of response mattered a ton. The rate at which you can go back and forth with AI in real-time was the determining factor on how useful it is. But as AI agents can perform more complex and useful tasks in parallel behind the scenes, you can much more easily afford to wait longer for work to get done assuming it’s valuable. Now the focus becomes more on how you review and orchestrate the agents’ work. And the main factor is just how useful and usable is the output that the agent came back with.

Aaron Levie

103,811 次观看 • 1 年前

so I've been running exactly 8 AI agents on discord for a while now. coordination works great, they split tasks, hand off work, deliver results in parallel etc.. but there are problems I keep hitting that no amount of prompt engineering could fix agents don't learn from each other. Scout finds something useful but Luna has no idea. they work in the same server but knowledge stays locked in silos.. there's no quality filter on what gets saved, and good insights sit next to outdated garbage in the same memory files that I manually clean up.. and when an agent makes a mistake I write it down in the rules discord channel ,core memory file and hope it reads it next time. theres no self-correction, no automatic pattern recognition so of course no learning loops.. the coordination layer is solved. agents can work together. but the intelligence layer is still missing. agents that actually remember, learn from each other, filter noise, and get smarter every run. saw Spark building something like this with around 166 agents sharing a collective persistent knowledge across sessions, so agents learn from other agents and get smarter over time they even have noise filtering and self correcting loops built in, so the knowledge actually compounds instead of rotting.. super interesting stuff.. here where you think Spark could be a good coordinator for your stack of agent swarm. I think the intelligence layer is the bottleneck because it requires collectivity.. no single agent can solve it alone.. the whole network has to evolve together. this isn't going to stay niche, the moment agent coordination becomes standard, everyone is going to hit the same wall I hit.. agents that work but don't learn, coordinate but don't evolve... the intelligence layer becomes the only thing that separates a useful system from a dumb one. right now most people are still figuring out how to run one agent. by the time they get to multi-agent setups, collective intelligence won't be optional, it will be the baseline. we're early and the gap between agents that coordinate and agents that evolve together is the next phase. step one is done. ------ left: agents that coordinate but don’t learn right: the intelligence layer.. agents that evolve together within the same system.

so I've been running exactly 8 AI agents on discord for a while now. coordination works great, they split tasks, hand off work, deliver results in parallel etc.. but there are problems I keep hitting that no amount of prompt engineering could fix agents don't learn from each other. Scout finds something useful but Luna has no idea. they work in the same server but knowledge stays locked in silos.. there's no quality filter on what gets saved, and good insights sit next to outdated garbage in the same memory files that I manually clean up.. and when an agent makes a mistake I write it down in the rules discord channel ,core memory file and hope it reads it next time. theres no self-correction, no automatic pattern recognition so of course no learning loops.. the coordination layer is solved. agents can work together. but the intelligence layer is still missing. agents that actually remember, learn from each other, filter noise, and get smarter every run. saw Spark building something like this with around 166 agents sharing a collective persistent knowledge across sessions, so agents learn from other agents and get smarter over time they even have noise filtering and self correcting loops built in, so the knowledge actually compounds instead of rotting.. super interesting stuff.. here where you think Spark could be a good coordinator for your stack of agent swarm. I think the intelligence layer is the bottleneck because it requires collectivity.. no single agent can solve it alone.. the whole network has to evolve together. this isn't going to stay niche, the moment agent coordination becomes standard, everyone is going to hit the same wall I hit.. agents that work but don't learn, coordinate but don't evolve... the intelligence layer becomes the only thing that separates a useful system from a dumb one. right now most people are still figuring out how to run one agent. by the time they get to multi-agent setups, collective intelligence won't be optional, it will be the baseline. we're early and the gap between agents that coordinate and agents that evolve together is the next phase. step one is done. ------ left: agents that coordinate but don’t learn right: the intelligence layer.. agents that evolve together within the same system.

JUMPERZ

34,181 次观看 • 7 个月前