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。

MOST PEOPLE USE CLAUDE CODE LIKE CHATGPT WITH A TERMINAL That is why they only get 30% of the value. They paste a task, wait for an answer, then keep explaining the same rules again when the context gets messy. The real power starts when you stop treating it... like a chatbot and start treating it like an operating system for work. The useful commands are not flashy. They just remove the parts that quietly waste hours: > /init builds the project memory > /memory edits the rules Claude should keep > /clear resets the chat without losing the setup > /compact compresses a long session before quality drops > /context shows where your tokens are going > /rewind rolls back when an edit breaks the direction > /plan forces a blueprint before execution > /model matches the brain to the task > /goal lets it work toward a clear finish line This is the difference between asking AI for help and actually managing an AI worker. One mode gives you random useful answers. The other gives you memory, boundaries, checkpoints, context control and repeatable execution. Most people are still trying to write better prompts. The better move is building a better system around the model. save thisshow more

Asteri

2,325 subscribers

15,347 次观看 • 4 个月前 •via X (Twitter)

科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Most people use Claude Code like a chatbot. That is the mistake. The real power is not in better prompts. It is in controlling the session. /init gives the project memory. /memory keeps the rules alive. /clear removes old context. /compact saves the important parts. /context shows where the tokens go. /rewind fixes bad turns. /plan stops blind edits. /model matches the brain to the task. Claude Code gets 10x better when you stop letting the conversation run itself. Memory. Context. Boundaries. Rollback. Planning. That is the system. Stop asking Claude Code to “just do it”. Teach it what to remember, what to forget, and when to stop. Bookmark this before your next session turns into 40 messages of context debt.

Most people use Claude Code like a chatbot. That is the mistake. The real power is not in better prompts. It is in controlling the session. /init gives the project memory. /memory keeps the rules alive. /clear removes old context. /compact saves the important parts. /context shows where the tokens go. /rewind fixes bad turns. /plan stops blind edits. /model matches the brain to the task. Claude Code gets 10x better when you stop letting the conversation run itself. Memory. Context. Boundaries. Rollback. Planning. That is the system. Stop asking Claude Code to “just do it”. Teach it what to remember, what to forget, and when to stop. Bookmark this before your next session turns into 40 messages of context debt.

Fluixo

19,226 次观看 • 4 个月前

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.

THIS GUY BUILT AN AUTONOMOUS AI AGENT OUT OF CLAUDE CODE + OBSIDIAN and this is way more interesting than another “use AI to take notes” demo the trick is simple: Obsidian is not the writing app here. it becomes the agent’s memory, task board, and context folder. Claude Code is not just answering prompts. it reads the vault, edits files, follows instructions, and keeps moving through the work like a junior operator with a filesystem. the reusable setup looks like this: 1. create an Obsidian vault for one project 2. keep goals, rules, tasks, decisions, and references as markdown files 3. point Claude Code at the folder 4. give it a clear operating loop: read context → choose next task → execute → write back what changed 5. use the notes as persistent memory instead of re-explaining the project every chat that’s the part people miss. the “agent” is not magic. it’s the boring combination of: - local files - explicit rules - task state - write access - a model that can run through the repo/vault Obsidian makes the memory human-readable. Claude Code makes the memory executable. that combo is why the video worked: it turns a notes app into an operating surface for actual work. best use cases: - content systems - research vaults - coding projects - client ops docs - personal knowledge bases that need actions, not just storage the caveat: if your vault is messy, your agent becomes messy too. folders, naming, “done” criteria, and forbidden actions matter more than the prompt. but once the structure is clean, this is one of the easiest ways to build an agent that remembers what happened yesterday without paying for a full custom app.

kocer

30,403 次观看 • 4 个月前

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

DegenCalls

20,124 次观看 • 4 个月前

Grok Bot + Kimi K3 can be turned into something bigger than an agent: an AI operating system the formula: AI OS = Router + Reasoning + Memory + Tools + Loops + Verification not one giant assistant. six layers that keep work moving without you step 1 -> Grok Bot becomes the operator. you give it the goal, it breaks the goal into jobs, assigns priorities and decides what part of the system should act next. step 2 -> Kimi K3 becomes the reasoning core. hard research, synthesis, long context and planning move here instead of forcing every task through the same model. step 3 -> externalize memory. store goals, decisions, failed attempts, artifacts and current state outside the chat. close the session, come back tomorrow, and the system still knows where it is. step 4 -> connect tools: search, code, files, APIs, docs and data. reasoning decides what should happen. tools actually make it happen. step 5 -> add the loop engine: plan -> execute -> inspect -> update memory -> retry. the loop can wait for new information, rerun a failed task, hand work to another agent or stop when the goal is complete. step 6 -> verify before output. tests, source checks, constraints and explicit completion rules decide whether the system ships the result or sends it back into the loop. that's the difference between an AI assistant and an AI operating system. an assistant waits for your next message. an operating system carries state, routes work and keeps moving. Grok Bot handles orchestration, Kimi K3 handles deeper reasoning, memory keeps the state alive, tools execute, the loop keeps the system running, verification decides when it is actually done. build one reliable loop and you have an agent. connect reasoning, memory, tools and multiple loops around it and you start building infrastructure. the full Grok Bot + Kimi K3 AI OS breakdown is below ↓

Grok Bot + Kimi K3 can be turned into something bigger than an agent: an AI operating system the formula: AI OS = Router + Reasoning + Memory + Tools + Loops + Verification not one giant assistant. six layers that keep work moving without you step 1 -> Grok Bot becomes the operator. you give it the goal, it breaks the goal into jobs, assigns priorities and decides what part of the system should act next. step 2 -> Kimi K3 becomes the reasoning core. hard research, synthesis, long context and planning move here instead of forcing every task through the same model. step 3 -> externalize memory. store goals, decisions, failed attempts, artifacts and current state outside the chat. close the session, come back tomorrow, and the system still knows where it is. step 4 -> connect tools: search, code, files, APIs, docs and data. reasoning decides what should happen. tools actually make it happen. step 5 -> add the loop engine: plan -> execute -> inspect -> update memory -> retry. the loop can wait for new information, rerun a failed task, hand work to another agent or stop when the goal is complete. step 6 -> verify before output. tests, source checks, constraints and explicit completion rules decide whether the system ships the result or sends it back into the loop. that's the difference between an AI assistant and an AI operating system. an assistant waits for your next message. an operating system carries state, routes work and keeps moving. Grok Bot handles orchestration, Kimi K3 handles deeper reasoning, memory keeps the state alive, tools execute, the loop keeps the system running, verification decides when it is actually done. build one reliable loop and you have an agent. connect reasoning, memory, tools and multiple loops around it and you start building infrastructure. the full Grok Bot + Kimi K3 AI OS breakdown is below ↓

Alex

13,312 次观看 • 2 个月前

Anthropic just revealed a trick to improve how Claude Opus 5.5 works. The idea is that Opus does the work while Fable 5.1 acts as a second opinion. All you have to do is open Claude Code and run: /advisor fable When Opus consults Fable, it gets the full context of the session, including the tools used and their results. It can be especially useful: → Before creating a large plan → When the same error keeps happening → Before marking a task as finished This gives you a second review without having to copy context between conversations. The feature is still experimental, requires access to Fable, and uses additional tokens. 🔖 Save this for your next session.

Anthropic just revealed a trick to improve how Claude Opus 5.5 works. The idea is that Opus does the work while Fable 5.1 acts as a second opinion. All you have to do is open Claude Code and run: /advisor fable When Opus consults Fable, it gets the full context of the session, including the tools used and their results. It can be especially useful: → Before creating a large plan → When the same error keeps happening → Before marking a task as finished This gives you a second review without having to copy context between conversations. The feature is still experimental, requires access to Fable, and uses additional tokens. 🔖 Save this for your next session.

Dean W. Perkins

56,146 次观看 • 1 个月前

I FINALLY FIGURED OUT WHY CLAUDE KEEPS FORGETTING THINGS. For months, I thought Claude’s memory was broken. I’d spend 20 minutes explaining my project few chats later, it would forget important stuff and remember something completely random. Turns out the problem wasn’t Claude. It was how I was using it. Here’s the system that fixed it LEVEL 1: Clean up the basics (5 mins) - Remove old memories you don’t need - Add proper project instructions - Tell Claude exactly what should and shouldn’t be remembered Most people never do this and then wonder why memory feels inconsistent. LEVEL 2: Build a context system (30-60 mins) Create a folder with: → Instructions.md → Memory.md → Context.md → Archive.md Now Claude has a dedicated place to store information instead of trying to remember everything from chat history. Massive difference. LEVEL 3: Build a real AI second brain → Connect Claude to your notes. → Research. → Documents. → Knowledge base. Instead of starting from zero every session, it builds context over time. This is when Claude stops feeling like a chatbot and starts feeling like an actual assistant. Most people are obsessed with prompts. The real power comes from building better context.

I FINALLY FIGURED OUT WHY CLAUDE KEEPS FORGETTING THINGS. For months, I thought Claude’s memory was broken. I’d spend 20 minutes explaining my project few chats later, it would forget important stuff and remember something completely random. Turns out the problem wasn’t Claude. It was how I was using it. Here’s the system that fixed it LEVEL 1: Clean up the basics (5 mins) - Remove old memories you don’t need - Add proper project instructions - Tell Claude exactly what should and shouldn’t be remembered Most people never do this and then wonder why memory feels inconsistent. LEVEL 2: Build a context system (30-60 mins) Create a folder with: → Instructions.md → Memory.md → Context.md → Archive.md Now Claude has a dedicated place to store information instead of trying to remember everything from chat history. Massive difference. LEVEL 3: Build a real AI second brain → Connect Claude to your notes. → Research. → Documents. → Knowledge base. Instead of starting from zero every session, it builds context over time. This is when Claude stops feeling like a chatbot and starts feeling like an actual assistant. Most people are obsessed with prompts. The real power comes from building better context.

nordin.eth

50,500 次观看 • 5 个月前

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

Gipp 🦅

14,940 次观看 • 5 个月前

Anthropic team: "Most people are prompting Claude wrong" They dropped a 24-minute workshop on how Claude prompts are actually built Free From the people who built the model There are 6 elements in a real Claude prompt Most people use 1 That is why their outputs feel generic Better wording is not enough Claude rewards structure, context, examples, constraints, and feedback I watched it twice Then built a Claude Skill that applies all 6 automatically You write normally The skill structures the prompt before Claude sees it Bookmark and watch this Then save the setup below

Anthropic team: "Most people are prompting Claude wrong" They dropped a 24-minute workshop on how Claude prompts are actually built Free From the people who built the model There are 6 elements in a real Claude prompt Most people use 1 That is why their outputs feel generic Better wording is not enough Claude rewards structure, context, examples, constraints, and feedback I watched it twice Then built a Claude Skill that applies all 6 automatically You write normally The skill structures the prompt before Claude sees it Bookmark and watch this Then save the setup below

rari

15,655 次观看 • 4 个月前

Most discussions around Claude Code focus on model quality or capability. But when you actually use it, the friction shows up earlier, more at the system level than the model itself. Token limits get the blame, but a lot of it comes from inefficient sessions: repeated context, extra tool calls, and small loops that quietly stack up. So it starts to feel less like “is the model good enough?” and more like “is the workflow slowing it down?” That’s where WozCode comes in. It helps streamline sessions, less repetition, smarter batching of tool calls, and tighter context usage so you can actually get more work done within the same limits. Woz just launched on Product Hunt. If Claude Code felt a bit restrictive before, it’s worth trying again with a cleaner workflow setup. Same model. Smoother execution. Upvote here:

Most discussions around Claude Code focus on model quality or capability. But when you actually use it, the friction shows up earlier, more at the system level than the model itself. Token limits get the blame, but a lot of it comes from inefficient sessions: repeated context, extra tool calls, and small loops that quietly stack up. So it starts to feel less like “is the model good enough?” and more like “is the workflow slowing it down?” That’s where WozCode comes in. It helps streamline sessions, less repetition, smarter batching of tool calls, and tighter context usage so you can actually get more work done within the same limits. Woz just launched on Product Hunt. If Claude Code felt a bit restrictive before, it’s worth trying again with a cleaner workflow setup. Same model. Smoother execution. Upvote here:

Parul Gautam

15,079 次观看 • 6 个月前

Meet the minds building supermemory! 🧠 Our research engineer Prasanna breaks down how memory actually works, in your head, and in AI. inside the episode: → why forgetting is a feature and not a failure → what your hippocampus inside brain is really doing all day → how "dreaming" turns a messy day into long-term memory → what the AI labs get right, and wrong, when they copy the brain → why a bigger context window still isn't memory the line worth sitting with: stop asking where memory is stored. start asking what gets kept, and why the brain chose it. full episode below ↓

Meet the minds building supermemory! 🧠 Our research engineer Prasanna breaks down how memory actually works, in your head, and in AI. inside the episode: → why forgetting is a feature and not a failure → what your hippocampus inside brain is really doing all day → how "dreaming" turns a messy day into long-term memory → what the AI labs get right, and wrong, when they copy the brain → why a bigger context window still isn't memory the line worth sitting with: stop asking where memory is stored. start asking what gets kept, and why the brain chose it. full episode below ↓

supermemory

14,752 次观看 • 3 个月前

IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago he runs loops instead, systems that write the prompts for him and keep working while he sleeps you type one request at a time and wait for the answer he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard here is how you make the jump step 1 stop treating the model like a chat box and start treating it like a worker you manage step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own step 3 add a second pass where the model grades its own work and retries whatever failed step 4 let it run on a timer so it keeps shipping while you are away from the screen the person still typing prompts one by one is doing the work of a intern the person running loops is doing the work of a whole team off one laptop prompting was never the skill, building the system that prompts for you is

IF YOU ARE STILL PROMPTING BY HAND IN 2026 YOU ARE ALREADY BEHIND the guy who built Claude Code at Anthropic said he stopped writing prompts a long time ago he runs loops instead, systems that write the prompts for him and keep working while he sleeps you type one request at a time and wait for the answer he built a machine that fires hundreds of requests, checks its own output and fixes itself with no hands on the keyboard here is how you make the jump step 1 stop treating the model like a chat box and start treating it like a worker you manage step 2 write a loop that takes a goal, breaks it into tasks and sends each one to the model on its own step 3 add a second pass where the model grades its own work and retries whatever failed step 4 let it run on a timer so it keeps shipping while you are away from the screen the person still typing prompts one by one is doing the work of a intern the person running loops is doing the work of a whole team off one laptop prompting was never the skill, building the system that prompts for you is

Atlas

16,641 次观看 • 3 个月前

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

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

378,296 次观看 • 7 个月前

Most people trying to fix AI slop keep rewriting their prompts. The actual fix looks more like onboarding a new hire. One operator described handing Claude some data for a root cause analysis. Before he'd finished reviewing it, Claude had already raced ahead and drafted a full pricing strategy doc nobody asked for. Not because the model is bad. Because it's built to please, fast, on partial information. Sound familiar? It's the exact failure mode of a sharp junior employee who hears one instruction and sprints to look impressive instead of asking what you actually need. Most people respond to this by tweaking the prompt. That's treating the symptom. The operators actually getting clean output do something different. They write the equivalent of a "how to work with me" doc, upfront, once. Ask clarifying questions before executing. Don't assume the first read of the task is the real task. Wait for the go-ahead before building anything. That single rule, stated once, does more than a hundred clever prompts. It changes what the model believes its job is: not "finish fast," but "understand first." The gap between AI users right now isn't who has better prompts. It's who's actually managing the thing instead of just talking to it. Manage it.

Most people trying to fix AI slop keep rewriting their prompts. The actual fix looks more like onboarding a new hire. One operator described handing Claude some data for a root cause analysis. Before he'd finished reviewing it, Claude had already raced ahead and drafted a full pricing strategy doc nobody asked for. Not because the model is bad. Because it's built to please, fast, on partial information. Sound familiar? It's the exact failure mode of a sharp junior employee who hears one instruction and sprints to look impressive instead of asking what you actually need. Most people respond to this by tweaking the prompt. That's treating the symptom. The operators actually getting clean output do something different. They write the equivalent of a "how to work with me" doc, upfront, once. Ask clarifying questions before executing. Don't assume the first read of the task is the real task. Wait for the go-ahead before building anything. That single rule, stated once, does more than a hundred clever prompts. It changes what the model believes its job is: not "finish fast," but "understand first." The gap between AI users right now isn't who has better prompts. It's who's actually managing the thing instead of just talking to it. Manage it.

Aakash Gupta

10,813 次观看 • 4 个月前

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

New short course: LLMs as Operating Systems: Agent Memory, created with Letta, and taught by its founders Charles Packer and Sarah Wooders. An LLM's input context window has limited space. Using a longer input context also costs more and results in slower processing. So, managing what's stored in this context window is important. In the innovative paper MemGPT: Towards LLMs as Operating Systems, its authors (which include the instructors) proposed using an LLM agent to manage this context window. Their system uses a large persistent memory that stores everything that could be included in the input context, and an agent decides what is actually included. Take the example of building a chatbot that needs to remember what's been said earlier in a conversation (perhaps over many days of interaction with a user). As the conversation's length grows, the memory management agent will move information from the input context to a persistent searchable database; summarize information to keep relevant facts in the input context; and restore relevant conversation elements from further back in time. This allows a chatbot to keep what's currently most relevant in its input context memory to generate the next response. When I read the original MemGPT paper, I thought it was an innovative technique for handling memory for LLMs. The open-source Letta framework, which we'll use in this course, makes MemGPT easy to implement. It adds memory to your LLM agents and gives them transparent long-term memory. In detail, you’ll learn: - How to build an agent that can edit its own limited input context memory, using tools and multi-step reasoning - What is a memory hierarchy (an idea from computer operating systems, which use a cache to speed up memory access), and how these ideas apply to managing the LLM input context (where the input context window is a "cache" storing the most relevant information; and an agent decides what to move in and out of this to/from a larger persistent storage system) - How to implement multi-agent collaboration by letting different agents share blocks of memory This course will give you a sophisticated understanding of memory management for LLMs, which is important for chatbots having long conversations, and for complex agentic workflows. Please sign up here!

Andrew Ng

201,127 次观看 • 2 年前

Most people are not Vibe Coding. They are panic prompting. They open Cursor, paste a vague idea, accept every diff, break the app, prompt harder, create a worse bug, then blame the model. Anthropic just showed the better version: AI is not the engineer. AI is the system around your engineering judgment. 16 minutes. free. from the people building Claude. better than most $1000 AI coding courses because it teaches the part people skip: how to think with the agent before asking it to write code. the loop: 1. context before code 2. plans before diffs 3. CLAUDE.md before chaos 4. Git before experiments 5. tests before trust 6. small scopes before big asks 7. taste before autopilot AI agents will not replace engineering judgment. they will expose who never had it. watch it. then read the 6-month roadmap below.

Most people are not Vibe Coding. They are panic prompting. They open Cursor, paste a vague idea, accept every diff, break the app, prompt harder, create a worse bug, then blame the model. Anthropic just showed the better version: AI is not the engineer. AI is the system around your engineering judgment. 16 minutes. free. from the people building Claude. better than most $1000 AI coding courses because it teaches the part people skip: how to think with the agent before asking it to write code. the loop: 1. context before code 2. plans before diffs 3. CLAUDE.md before chaos 4. Git before experiments 5. tests before trust 6. small scopes before big asks 7. taste before autopilot AI agents will not replace engineering judgment. they will expose who never had it. watch it. then read the 6-month roadmap below.

Ziwen

14,391 次观看 • 5 个月前

Martin Keen from IBM just explained the one thing separating "chatbot users" from $300K AI architects > most people use Claude Opus 4.8 as a temporary tool -> the pros build it a permanent memory it's called the CoALA framework. the 4 layers your agent actually needs: > Working Memory - the context window. fast but resets every session. this is the RAM, not the brain > Semantic Memory - your knowledge base. CLAUDE.md, rules, facts the agent never forgets regardless of session > Procedural Memory - skills. workflows and instructions that load only when a specific task begins > Episodic Memory - past lessons. the agent remembers every bug it fixed yesterday so it doesn't repeat it today if your agent doesn't have all four, it's a fancy autocomplete the 2026 job market isn't looking for prompt engineers > it's looking for people who can build AI brains - and the ones doing it now aren't waiting for job postings save this or watch someone else use it to get your next raise 👇

Martin Keen from IBM just explained the one thing separating "chatbot users" from $300K AI architects > most people use Claude Opus 4.8 as a temporary tool -> the pros build it a permanent memory it's called the CoALA framework. the 4 layers your agent actually needs: > Working Memory - the context window. fast but resets every session. this is the RAM, not the brain > Semantic Memory - your knowledge base. CLAUDE.md, rules, facts the agent never forgets regardless of session > Procedural Memory - skills. workflows and instructions that load only when a specific task begins > Episodic Memory - past lessons. the agent remembers every bug it fixed yesterday so it doesn't repeat it today if your agent doesn't have all four, it's a fancy autocomplete the 2026 job market isn't looking for prompt engineers > it's looking for people who can build AI brains - and the ones doing it now aren't waiting for job postings save this or watch someone else use it to get your next raise 👇

Mr. Buzzoni

10,442 次观看 • 5 个月前

I gave Qoder a task instead of a prompt. And it actually did the work. It read the context, made a plan, used the tools it needed, executed the task, and verified the result before finishing. That’s the big difference with Qoder. It feels less like chatting with AI and more like handing a task to an AI agent on your computer. You describe the outcome you want. Qoder can then: • Read your workspace and context • Plan how to complete the task • Execute commands and make file changes • Use the browser or desktop when needed • Let you pause, adjust, or take over • Verify the result when it’s done And right now, Qwen3.8-Flash runs at 0.0x Credits through September 30. New users can also get 600 Credits in total. Try Qoder here: If you already use AI for coding or everyday computer work, this is worth experimenting with.

I gave Qoder a task instead of a prompt. And it actually did the work. It read the context, made a plan, used the tools it needed, executed the task, and verified the result before finishing. That’s the big difference with Qoder. It feels less like chatting with AI and more like handing a task to an AI agent on your computer. You describe the outcome you want. Qoder can then: • Read your workspace and context • Plan how to complete the task • Execute commands and make file changes • Use the browser or desktop when needed • Let you pause, adjust, or take over • Verify the result when it’s done And right now, Qwen3.8-Flash runs at 0.0x Credits through September 30. New users can also get 600 Credits in total. Try Qoder here: If you already use AI for coding or everyday computer work, this is worth experimenting with.

Shushant Lakhyani

143,473 次观看 • 1 个月前

your agent reviewing its own work is not a check. it is a second opinion from the same source. this is the most common gap in agent systems and it hides in plain sight, because the step exists. there is a review. it just cannot do the thing you think it does. here is the mechanism. the model produced an output from a context. you then ask the same model, holding the same context, whether that output is correct. it answers fluently, because that is what it does. and the answer is drawn from the same distribution that produced the thing being judged. same weights, same window, same blind spots. if the reason the output is wrong is something the model does not know, the review does not know it either. if the reason is something the context does not contain, the review has the same context. the failure mode and the detector share a cause. > why it feels like it works because most of the time the output is fine, and the review says fine. agreement is not evidence of detection. a reviewer that says pass on everything agrees with reality most of the time too. what you actually want to measure is what happens on the cases that are wrong. that is the only place a check earns its name, and it is exactly the place where a self-review is weakest. there is research on this. Huang and colleagues at DeepMind showed at ICLR 2024 that intrinsic self-correction, revising without external grounding, does not reliably help and often makes things worse. > what to actually do move the check outside the model. a test that runs, a schema that validates, a file that exists or does not, an exit code from something you did not write. these are not smarter than the model. they are just not correlated with it, and that is the entire value. when the judgement genuinely needs a model, at minimum use a different family. same family means shared blind spots, and frontier judges measurably inflate scores for outputs that look like their own. and split the work by kind. anything objectively checkable goes to code. only the genuinely semantic calls go to a judge, and those get a rubric written as one line. a review inside the loop tells you the model is confident. a check outside it tells you whether the work is done. save this - then read the eval setup below

your agent reviewing its own work is not a check. it is a second opinion from the same source. this is the most common gap in agent systems and it hides in plain sight, because the step exists. there is a review. it just cannot do the thing you think it does. here is the mechanism. the model produced an output from a context. you then ask the same model, holding the same context, whether that output is correct. it answers fluently, because that is what it does. and the answer is drawn from the same distribution that produced the thing being judged. same weights, same window, same blind spots. if the reason the output is wrong is something the model does not know, the review does not know it either. if the reason is something the context does not contain, the review has the same context. the failure mode and the detector share a cause. > why it feels like it works because most of the time the output is fine, and the review says fine. agreement is not evidence of detection. a reviewer that says pass on everything agrees with reality most of the time too. what you actually want to measure is what happens on the cases that are wrong. that is the only place a check earns its name, and it is exactly the place where a self-review is weakest. there is research on this. Huang and colleagues at DeepMind showed at ICLR 2024 that intrinsic self-correction, revising without external grounding, does not reliably help and often makes things worse. > what to actually do move the check outside the model. a test that runs, a schema that validates, a file that exists or does not, an exit code from something you did not write. these are not smarter than the model. they are just not correlated with it, and that is the entire value. when the judgement genuinely needs a model, at minimum use a different family. same family means shared blind spots, and frontier judges measurably inflate scores for outputs that look like their own. and split the work by kind. anything objectively checkable goes to code. only the genuinely semantic calls go to a judge, and those get a rubric written as one line. a review inside the loop tells you the model is confident. a check outside it tells you whether the work is done. save this - then read the eval setup below

Hanako

14,325 次观看 • 3 个月前

Qwen3.8-Flash-Next is still going strong at 364.7K tokens of context on an M5 Max. And this isn’t just a static long-context test. The model was reasoning about how to speed up its own workflow while using tools, and the tool calls kept working without misses. Setup: • Qwen3.8-Flash-Next • M5 Max • 128GB unified memory • MLX-Serve PR #363 • OpenCode 2 • 364.7K context The interesting part isn’t simply getting hundreds of thousands of tokens into memory. It’s what happens once the context gets this large. Long-context inference usually comes with a painful tradeoff. As the KV cache grows, memory pressure increases and generation can slow down. But this setup is still pushing through 364K tokens while maintaining a usable agent workflow. The model can reason, call tools, inspect results, continue working, and keep the session moving. And the tool calls reportedly haven’t missed so far. That’s important for agentic coding. A huge context window is only useful if the model can actually operate reliably inside it. A 400K-token context that constantly breaks tool calls isn’t very useful. A 364K session that can keep reasoning and executing tools is a different story. And the test isn’t finished yet. The current run is approaching 400K tokens, with the expectation that it can keep going. This is also another interesting example of why Apple Silicon keeps showing up in local LLM experiments. The M5 Max’s unified memory gives a large model and its growing KV cache access to one shared memory pool. With MLX-Serve continuing to improve, these machines are becoming surprisingly capable long-context inference boxes. The bigger takeaway: Context length is becoming a workload, not just a model specification. Running a model at 256K is one thing. Keeping an agent alive at 300K+ while it reasons and uses tools is much more interesting. And Qwen3.8-Flash-Next is showing that this can be pushed surprisingly far on a single 128GB Mac. 364.7K and counting. Next stop: 400K.

Qwen3.8-Flash-Next is still going strong at 364.7K tokens of context on an M5 Max. And this isn’t just a static long-context test. The model was reasoning about how to speed up its own workflow while using tools, and the tool calls kept working without misses. Setup: • Qwen3.8-Flash-Next • M5 Max • 128GB unified memory • MLX-Serve PR #363 • OpenCode 2 • 364.7K context The interesting part isn’t simply getting hundreds of thousands of tokens into memory. It’s what happens once the context gets this large. Long-context inference usually comes with a painful tradeoff. As the KV cache grows, memory pressure increases and generation can slow down. But this setup is still pushing through 364K tokens while maintaining a usable agent workflow. The model can reason, call tools, inspect results, continue working, and keep the session moving. And the tool calls reportedly haven’t missed so far. That’s important for agentic coding. A huge context window is only useful if the model can actually operate reliably inside it. A 400K-token context that constantly breaks tool calls isn’t very useful. A 364K session that can keep reasoning and executing tools is a different story. And the test isn’t finished yet. The current run is approaching 400K tokens, with the expectation that it can keep going. This is also another interesting example of why Apple Silicon keeps showing up in local LLM experiments. The M5 Max’s unified memory gives a large model and its growing KV cache access to one shared memory pool. With MLX-Serve continuing to improve, these machines are becoming surprisingly capable long-context inference boxes. The bigger takeaway: Context length is becoming a workload, not just a model specification. Running a model at 256K is one thing. Keeping an agent alive at 300K+ while it reasons and uses tools is much more interesting. And Qwen3.8-Flash-Next is showing that this can be pushed surprisingly far on a single 128GB Mac. 364.7K and counting. Next stop: 400K.

FHILY👑

39,982 次观看 • 2 个月前

Claude Code creator: "100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too. The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops" in this interview he breaks down exactly how a system changes everything: - the memory and context features that turn Claude into a second brain - the knowledge architecture most users don't know Claude can build - the integration layer that connects Claude to your actual workflow - why typing one question at a time is the most expensive way to use Claude if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed full guide in the article below

Claude Code creator: "100% of our pull requests at Anrtopic are run by Claude Code. 80–90% of code review too. The feature I’m using the most today is /loops. I’m not prompting Claude anymore - I’m building loops" in this interview he breaks down exactly how a system changes everything: - the memory and context features that turn Claude into a second brain - the knowledge architecture most users don't know Claude can build - the integration layer that connects Claude to your actual workflow - why typing one question at a time is the most expensive way to use Claude if you've been using Claude for months and still start every conversation from scratch with zero context, you don't have a Claude problem. you have a system problem instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed full guide in the article below

Khairallah AL-Awady

39,381 次观看 • 4 个月前