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。

Claude Code Head invented a word for what most config files aren't doing: tokenmaxxing. 90% of it lives in one place: ~/.claude/settings.json. 125 keys in v2.1.105. official docs cover 40. 4 of mine aren't anywhere in the docs. i audited the whole file - 18 settings actually decide what... your month costs. > enabledPlugins - mine had 14 on, 4 actually used. each idle plugin loads hooks and SKILL.md at session start. > mcpServers.enabled - false instead of delete. 9 unused servers cost ~30K tokens of schema every session. > cache_control breakpoint at the static/dynamic boundary moved my Opus month from $340 to $87. tokenmaxxing isn't a vibe. it's a file with 125 keys most people never open. watch this tonight instead of the new Rick and Morty drop.show more

Mnimiy

7,248 subscribers

82,796 次观看 • 22 天前 •via X (Twitter)

教育科学技术

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

Anthropic shipped 125 settings for Claude The official docs cover 40 One developer found the other 85 and his API bill dropped from $340 to $87 - not by using a cheaper model - not by writing shorter prompts just by moving one line in a config file to the right place > memory scoped per project → past clients never bleed into new work > Extended Thinking on Light by default → 18–25% fewer Opus tokens in week one > cache_control moved to the right line → the fix that turned a $340 bill into $87 > plugins and MCP servers toggled off when idle → saved 25–40K tokens per session > per-project model override → Haiku for docs, Sonnet for infra, Opus only where it matters most Claude users are running a $100/month tool at 30% of its actual capability

Anthropic shipped 125 settings for Claude The official docs cover 40 One developer found the other 85 and his API bill dropped from $340 to $87 - not by using a cheaper model - not by writing shorter prompts just by moving one line in a config file to the right place > memory scoped per project → past clients never bleed into new work > Extended Thinking on Light by default → 18–25% fewer Opus tokens in week one > cache_control moved to the right line → the fix that turned a $340 bill into $87 > plugins and MCP servers toggled off when idle → saved 25–40K tokens per session > per-project model override → Haiku for docs, Sonnet for infra, Opus only where it matters most Claude users are running a $100/month tool at 30% of its actual capability

Shadow Nick

378,673 次观看 • 22 天前

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

Tal Raviv

56,934 次观看 • 5 个月前

Boris Cherny, the creator of Claude Code at Anthropic, just explained why most people aren't getting real results from Claude in this talk he breaks down exactly how most people skipped the setup entirely: - 90% of code at Anthropic is written by Claude itself - the 14% you lose to CLAUDE.md before typing a word - lawyers, designers, and finance people are building real things with it - no CS degree. no background. nothing Boris Cherny: "Claude Code is 100% written by Claude Code, Cowork is 100% written by Claude Code" if you've been using Claude for months and never configured a single thing, you skipped the 20 steps that change everything. probably 25 instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed my breakdown of all 25 features is below

Boris Cherny, the creator of Claude Code at Anthropic, just explained why most people aren't getting real results from Claude in this talk he breaks down exactly how most people skipped the setup entirely: - 90% of code at Anthropic is written by Claude itself - the 14% you lose to CLAUDE.md before typing a word - lawyers, designers, and finance people are building real things with it - no CS degree. no background. nothing Boris Cherny: "Claude Code is 100% written by Claude Code, Cowork is 100% written by Claude Code" if you've been using Claude for months and never configured a single thing, you skipped the 20 steps that change everything. probably 25 instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed my breakdown of all 25 features is below

Khairallah AL-Awady

181,728 次观看 • 19 天前

$THIS GUY AUDITED 926 CLAUDE CODE SESSIONS AND FOUND MOST OF THE TOKEN WASTE WAS ON HIS SIDE everyone is blaming anthropic for the limits, so he decided to actually look at the data 858 sessions, 18,903 turns, and $1,619 estimated spend across 33 days here's what he found: 1\ one default setting was burning 14,000 tokens per turn Claude Code loads the full JSON schema for every tool into context at session start. whether you use them or not. 20,000 tokens of tool definitions sitting there on every single turn. the fix: one line in your settings.json "ENABLE_TOOL_SEARCH": "true" context dropped from 45K to 20K instantly. across 858 sessions that one setting was wasting an estimated 264 million tokens 2\ cache expiry is the single biggest waste 54% of his turns came after a 5+ minute idle gap. every one of those turns re-processed the entire conversation at full price which caused a 10x cost jump you go grab coffee. come back 5 minutes later. type your next message. everything rebuilds from scratch. the context didn't change. you didn't change. the cache just expired. 12.3 million tokens wasted on idle gaps alone 3\ 42 skills loaded. 19 of them used twice or less across 858 sessions. every one of those skill schemas sat in context on every turn eating tokens for nothing. 4\ 1,122 redundant file reads where the same file was read 3+ times one session read the same file 33 times. he ALSO built a full token auditor dashboard that shows you exactly where your waste is coming from 19 charts, opens in your browser, free AND open source$

THIS GUY AUDITED 926 CLAUDE CODE SESSIONS AND FOUND MOST OF THE TOKEN WASTE WAS ON HIS SIDE everyone is blaming anthropic for the limits, so he decided to actually look at the data 858 sessions, 18,903 turns, and $1,619 estimated spend across 33 days here's what he found: 1\ one default setting was burning 14,000 tokens per turn Claude Code loads the full JSON schema for every tool into context at session start. whether you use them or not. 20,000 tokens of tool definitions sitting there on every single turn. the fix: one line in your settings.json "ENABLE_TOOL_SEARCH": "true" context dropped from 45K to 20K instantly. across 858 sessions that one setting was wasting an estimated 264 million tokens 2\ cache expiry is the single biggest waste 54% of his turns came after a 5+ minute idle gap. every one of those turns re-processed the entire conversation at full price which caused a 10x cost jump you go grab coffee. come back 5 minutes later. type your next message. everything rebuilds from scratch. the context didn't change. you didn't change. the cache just expired. 12.3 million tokens wasted on idle gaps alone 3\ 42 skills loaded. 19 of them used twice or less across 858 sessions. every one of those skill schemas sat in context on every turn eating tokens for nothing. 4\ 1,122 redundant file reads where the same file was read 3+ times one session read the same file 33 times. he ALSO built a full token auditor dashboard that shows you exactly where your waste is coming from 19 charts, opens in your browser, free AND open source

Om Patel

296,779 次观看 • 2 个月前

Turn Claude Code into a Financial Analyst 🤖💹 In this video we point Claude Code at a bucket of 10k filing PDFs, and have it perform complex analysis across the entire set of docs! Claude Code doesn’t have file understanding out of the box (it kind of does, but it’s terrible / doesn’t work over long PDFs). We equipped Claude Code with targeted tools for file parsing and efficient search, courtesy of our recently released `semtools`. It’s way faster/more versatile than naive RAG 💡. You get super-fast in-mem keyword/semantic search, and Claude Code can combine this with standard file tools like grep and `Read` to load in dynamic context instead of fixed chunks. You can do this in seconds. Just install `semtools`, add it to your and point Claude to any bucket of files you want to analyze. SemTools (s/o Logan Markewich): File parsing courtesy of LlamaCloud:

Turn Claude Code into a Financial Analyst 🤖💹 In this video we point Claude Code at a bucket of 10k filing PDFs, and have it perform complex analysis across the entire set of docs! Claude Code doesn’t have file understanding out of the box (it kind of does, but it’s terrible / doesn’t work over long PDFs). We equipped Claude Code with targeted tools for file parsing and efficient search, courtesy of our recently released `semtools`. It’s way faster/more versatile than naive RAG 💡. You get super-fast in-mem keyword/semantic search, and Claude Code can combine this with standard file tools like grep and `Read` to load in dynamic context instead of fixed chunks. You can do this in seconds. Just install `semtools`, add it to your and point Claude to any bucket of files you want to analyze. SemTools (s/o Logan Markewich): File parsing courtesy of LlamaCloud:

Jerry Liu

32,804 次观看 • 9 个月前

Stop what you're doing. Claude Opus 4.6 just released and it's incredible Both OpenClaw and Claude Code are 10x better with it It's now my daily driver for both In this video I cover EVERYTHING you need to know about Opus, and how to get the most out of it:

Stop what you're doing. Claude Opus 4.6 just released and it's incredible Both OpenClaw and Claude Code are 10x better with it It's now my daily driver for both In this video I cover EVERYTHING you need to know about Opus, and how to get the most out of it:

Alex Finn

71,388 次观看 • 4 个月前

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

Anthropic engineers finally showed how they actually use Claude Code internally 31 minutes of internal workflow that most Claude users will never see on their own here's what they cover: > how to set up project context files the right way > custom commands that save hours of repeated work > hooks that make Claude behave exactly how you need > subagents and how to actually spec them properly "your agent isn't the problem, your spec is" the people who understand how Claude Code actually works inside Anthropic are shipping things everyone else thinks requires a whole team that's exactly why I put together a breakdown of Claude features most people have never discovered you can find it below

Anatoli Kopadze

307,716 次观看 • 18 天前

Anthropic's CEO just explained on Lex Fridman how Claude actually works. 4 hours. free. with the CEO, the person who built Claude's character, and the founder of mechanistic interpretability. most people use Claude every day at maybe 10% of what it can actually do. this video is the other 90%. Save it. This will change the way you use Claude forever.

Anthropic's CEO just explained on Lex Fridman how Claude actually works. 4 hours. free. with the CEO, the person who built Claude's character, and the founder of mechanistic interpretability. most people use Claude every day at maybe 10% of what it can actually do. this video is the other 90%. Save it. This will change the way you use Claude forever.

Raytar

11,312 次观看 • 18 天前

instead of watching 2 hours of Netflix tonight, watch this Stanford lecture it's the clearest explanation I've seen of how ChatGPT and Claude actually work useful whether you've never touched AI in your life or have been using it every day for the past year I took the key ideas and turned them into a practical guide on how to actually get 100% out of Claude find it below

instead of watching 2 hours of Netflix tonight, watch this Stanford lecture it's the clearest explanation I've seen of how ChatGPT and Claude actually work useful whether you've never touched AI in your life or have been using it every day for the past year I took the key ideas and turned them into a practical guide on how to actually get 100% out of Claude find it below

Anatoli Kopadze

8,213,330 次观看 • 26 天前

Boris Cherny, the creator of Claude Code at Anthropic, just listed 9 patterns that waste 73% of your tokens. in this podcast he breaks down exactly how the model burns tokens before it even reads your prompt: - the 14% you lose to CLAUDE.md before typing a word - the 13% you pay re-reading old chat history - the 11% from hooks you forgot you installed - why most "Claude got dumber" complaints are wrong if you're hitting Max limits more than once a week, you have at least 4 of these. Probably 7. instead of another show tonight, watch this. my own breakdown based on 400+ hours of usage is below, read it after the podcast

Boris Cherny, the creator of Claude Code at Anthropic, just listed 9 patterns that waste 73% of your tokens. in this podcast he breaks down exactly how the model burns tokens before it even reads your prompt: - the 14% you lose to CLAUDE.md before typing a word - the 13% you pay re-reading old chat history - the 11% from hooks you forgot you installed - why most "Claude got dumber" complaints are wrong if you're hitting Max limits more than once a week, you have at least 4 of these. Probably 7. instead of another show tonight, watch this. my own breakdown based on 400+ hours of usage is below, read it after the podcast

Mnimiy

1,373,654 次观看 • 1 个月前

Here is a demo of the most comprehensive research agent for your code docs, powered by Nozomio Labs. It turns your indexed repos and docs into a dynamic tree that the agent can access on the fly, using SOTA tools to reduce code hallucinations. Now using the latest Anthropic model, Claude Opus 4.5.

Here is a demo of the most comprehensive research agent for your code docs, powered by Nozomio Labs. It turns your indexed repos and docs into a dynamic tree that the agent can access on the fly, using SOTA tools to reduce code hallucinations. Now using the latest Anthropic model, Claude Opus 4.5.

Arlan

28,405 次观看 • 6 个月前

instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale useful whether you've never built an agent in your life or have been using Claude every day for the past year I took the key ideas and turned them into a practical guide on how to actually build with Kimi find it below

instead of watching 2 hours of Netflix tonight, watch this 40-minute masterclass from the founder of a $20B China AI company it's the clearest explanation I've seen of how Agent Swarms and AI systems actually work at scale useful whether you've never built an agent in your life or have been using Claude every day for the past year I took the key ideas and turned them into a practical guide on how to actually build with Kimi find it below

Kirill

13,601,538 次观看 • 25 天前

$Introducing `claude-opus-to-haiku` ✍️ Get the quality of Claude 3 Opus, at a fraction of the cost and latency. Give one example of your task, and Claude 3 Opus will teach Haiku (60x cheaper!!) how to do the task perfectly. And it's open-source:$

Introducing `claude-opus-to-haiku` ✍️ Get the quality of Claude 3 Opus, at a fraction of the cost and latency. Give one example of your task, and Claude 3 Opus will teach Haiku (60x cheaper!!) how to do the task perfectly. And it's open-source:

Matt Shumer

285,329 次观看 • 2 年前

Boris Cherny, the creator of Claude Code at Anthropic, just explained why he stopped prompting Claude entirely in this talk he breaks down exactly how the future is teams of agents, not better prompts: - the 14% you lose to CLAUDE.md before typing a word - the features that change how Claude thinks before you type a word - the features most Claude users don't know exist - why typing prompts one at a time is already the slow lane Boris Cherny: "Now I don’t prompt Claude anymore - I have loops that are running. My job is to write loops." if you've been using Claude for more than a month and never left the chat window, you have at least 23 untouched features. probably 25 instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed my breakdown of all 25 features is below

Boris Cherny, the creator of Claude Code at Anthropic, just explained why he stopped prompting Claude entirely in this talk he breaks down exactly how the future is teams of agents, not better prompts: - the 14% you lose to CLAUDE.md before typing a word - the features that change how Claude thinks before you type a word - the features most Claude users don't know exist - why typing prompts one at a time is already the slow lane Boris Cherny: "Now I don’t prompt Claude anymore - I have loops that are running. My job is to write loops." if you've been using Claude for more than a month and never left the chat window, you have at least 23 untouched features. probably 25 instead of another show tonight, watch this make sure to bookmark it before it gets lost in your feed my breakdown of all 25 features is below

Khairallah AL-Awady

102,317 次观看 • 10 天前

We're excited to announce duckdb-skills, a DuckDB plugin for Claude Code! We think the embedded nature of DuckDB makes it a perfect companion for Claude in your local workflows. The skills supported include: + read-file and query – uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read. + read-memories – a clever idea to store your Claude memories in DuckDB and query them at blazing speed. These are powered by two additional skills: + attach-db – gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project. + duckdb-docs – uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions.

We're excited to announce duckdb-skills, a DuckDB plugin for Claude Code! We think the embedded nature of DuckDB makes it a perfect companion for Claude in your local workflows. The skills supported include: + read-file and query – uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read. + read-memories – a clever idea to store your Claude memories in DuckDB and query them at blazing speed. These are powered by two additional skills: + attach-db – gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project. + duckdb-docs – uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions.

DuckDB

60,551 次观看 • 2 个月前

$Everyone's sleeping on MiniMax. Again. They just shipped M3. The first open-weights model to combine frontier coding, 1M context, and native multimodality in one drop. I plugged it into Claude Code this morning. Pasted a design from Dribbble. Watched M3 write production-ready React code in one session. At the agency, I just replaced Opus 4.8 with M3 for 80% of our coding tasks. The output is the same and we are running everything at a fraction of the cost. Open infrastructure is the future.$

Everyone's sleeping on MiniMax. Again. They just shipped M3. The first open-weights model to combine frontier coding, 1M context, and native multimodality in one drop. I plugged it into Claude Code this morning. Pasted a design from Dribbble. Watched M3 write production-ready React code in one session. At the agency, I just replaced Opus 4.8 with M3 for 80% of our coding tasks. The output is the same and we are running everything at a fraction of the cost. Open infrastructure is the future.

Prajwal Tomar

12,834 次观看 • 11 天前

Advent of Claude Day 9 - Claude Code Remote & your prompt ↳ Sends the task to Claude Code on the web (runs in background) claude --teleport session_abc123 ↳ Pulls and resumes the session in your local terminal to continue working Claude at home and on the go.

Advent of Claude Day 9 - Claude Code Remote & your prompt ↳ Sends the task to Claude Code on the web (runs in background) claude --teleport session_abc123 ↳ Pulls and resumes the session in your local terminal to continue working Claude at home and on the go.

Ado

38,702 次观看 • 6 个月前

Get ready to start talking to your Google Docs. With Docs Live, you’ll be able to workshop docs and projects in a freewheeling conversational way, instead of a series of hyper-specific instructional prompts. Take a look at the demo from #GoogleIO 👀

Get ready to start talking to your Google Docs. With Docs Live, you’ll be able to workshop docs and projects in a freewheeling conversational way, instead of a series of hyper-specific instructional prompts. Take a look at the demo from #GoogleIO 👀

TechCrunch

13,611 次观看 • 27 天前

THIS GUY TURNED A DESK LAMP INTO A LIVE CLAUDE CODE STATUS INDICATOR the lamp changes color based on what claude code is doing in real time when claude is thinking it's one color. when it's writing code it shifts. when it's done it changes again. when it errors out you know instantly without even looking at your screen the lamp is a moonside halo and i'm already tryna to buy one I might even buy multiple for the multiple claude sessions running in the background and turn my room into a disco if the color reflected the operational status of claude it would just be red 24/7 it could also track your usage limit. green at the start of the session, slowly fading to red as your tokens drain people are already hooking this up to their philips hue and govee setups at home

THIS GUY TURNED A DESK LAMP INTO A LIVE CLAUDE CODE STATUS INDICATOR the lamp changes color based on what claude code is doing in real time when claude is thinking it's one color. when it's writing code it shifts. when it's done it changes again. when it errors out you know instantly without even looking at your screen the lamp is a moonside halo and i'm already tryna to buy one I might even buy multiple for the multiple claude sessions running in the background and turn my room into a disco if the color reflected the operational status of claude it would just be red 24/7 it could also track your usage limit. green at the start of the session, slowly fading to red as your tokens drain people are already hooking this up to their philips hue and govee setups at home

Om Patel

107,681 次观看 • 1 个月前

the bottleneck Karpathy keeps pointing at isn't the model. it's the file you wrote three months ago telling it how to work. his whole framing: code isn't the verb anymore. > you express your will to agents 16 hours a day. > running more of them in parallel is the unlock. > and he drops this line halfway through, no fanfare: "now you can have optimization over the instructions." that's the sentence. the instructions are the new bottleneck. and almost nobody has a process for optimizing them. i built one for myself. it reads 100 of my past Claude Code sessions and rewrites my CLAUDE.md from what the transcripts show, not from what i thought i wrote. one Saturday morning later: a 38-line memory file. 73% of my old CLAUDE.md got deleted. most of it was one-off corrections that hardened into permanent rules months ago and were quietly steering every agent i ran. four behavior patterns surfaced that i had never written down. the loudest one: my prose corrections outnumber code corrections 8.2 to 1. that ratio was running silently through every session for 90 days. you don't need a smarter model. you need an instruction file that still describes how you actually work. listen to the podcast for the framing. open the article for the script that does the optimization.

the bottleneck Karpathy keeps pointing at isn't the model. it's the file you wrote three months ago telling it how to work. his whole framing: code isn't the verb anymore. > you express your will to agents 16 hours a day. > running more of them in parallel is the unlock. > and he drops this line halfway through, no fanfare: "now you can have optimization over the instructions." that's the sentence. the instructions are the new bottleneck. and almost nobody has a process for optimizing them. i built one for myself. it reads 100 of my past Claude Code sessions and rewrites my CLAUDE.md from what the transcripts show, not from what i thought i wrote. one Saturday morning later: a 38-line memory file. 73% of my old CLAUDE.md got deleted. most of it was one-off corrections that hardened into permanent rules months ago and were quietly steering every agent i ran. four behavior patterns surfaced that i had never written down. the loudest one: my prose corrections outnumber code corrections 8.2 to 1. that ratio was running silently through every session for 90 days. you don't need a smarter model. you need an instruction file that still describes how you actually work. listen to the podcast for the framing. open the article for the script that does the optimization.

Mnimiy

50,181 次观看 • 1 个月前