Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

We've updated /fork in Claude Code /fork now runs a background agent with your exact context (system prompt, tools, history, model) and prompt cache. The result gets returned to your session. /branch (the old /fork) still copies the transcript to a new session you drive.

ClaudeDevs

633,897 subscribers

379,277 views • 2 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Claude Code pro tip: Hit Esc twice to undo, you can pick a point in the conversation to revert to, and it'll fork the conversation. This is basically checkpoints and lets you rollback and try a new prompt.

Claude Code pro tip: Hit Esc twice to undo, you can pick a point in the conversation to revert to, and it'll fork the conversation. This is basically checkpoints and lets you rollback and try a new prompt.

Ian Nuttall

73,186 views • 1 year ago

To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.

To make it easier to migrate your workflows, we've updated the claude-api skill in Claude Code with Opus 4.7 support. Just say "migrate to Opus 4.7" and it updates model names, prompts, and effort settings for you.

ClaudeDevs

362,268 views • 3 months ago

Claude Code ships with a built-in skill for working with the Claude Platform. Useful for model migrations, using API features (e.g., prompt caching), or onboarding to newer APIs like Claude Managed Agents.

Claude Code ships with a built-in skill for working with the Claude Platform. Useful for model migrations, using API features (e.g., prompt caching), or onboarding to newer APIs like Claude Managed Agents.

ClaudeDevs

313,779 views • 3 months ago

Smol tip: /𝚌𝚍 moves your running Claude Code session to another directory without restarting. Your conversation and context come with you, and Claude picks up the new project's CLAUDE.md.

Smol tip: /𝚌𝚍 moves your running Claude Code session to another directory without restarting. Your conversation and context come with you, and Claude picks up the new project's CLAUDE.md.

Delba

209,160 views • 1 month ago

The AI Super Bowl… ChatGPT vs Claude 🏈 Run your prompt across multiple models at once with /multi-agent then an AI judge picks the best answer so you don't have to. Need to quickly switch between models? Use /agent to switch to a different model in seconds but retain your context.

The AI Super Bowl… ChatGPT vs Claude 🏈 Run your prompt across multiple models at once with /multi-agent then an AI judge picks the best answer so you don't have to. Need to quickly switch between models? Use /agent to switch to a different model in seconds but retain your context.

BLACKBOX AI

312,157 views • 6 months ago

GPT-5.5 in Codex is built for long-session agent work. But context still doesn't follow you across projects, agents, or teammates. ByteRover does that + Save you tokens -> No rewriting context when you switch from Claude Code to Codex. Now connecting Codex, Claude Code, OpenClaw, Hermes, and 22+ more agents. Your context moves with you. → personal context for solo work → team context for shared decisions and bug history

GPT-5.5 in Codex is built for long-session agent work. But context still doesn't follow you across projects, agents, or teammates. ByteRover does that + Save you tokens -> No rewriting context when you switch from Claude Code to Codex. Now connecting Codex, Claude Code, OpenClaw, Hermes, and 22+ more agents. Your context moves with you. → personal context for solo work → team context for shared decisions and bug history

andy nguyen

12,437 views • 3 months ago

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them instead

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them instead

Marvin

24,954 views • 2 months ago

🚀 We just shipped v0.223! Launch Zed's Agent Panel with a prompt via URL: zed://agent?prompt=your+prompt+here Now, you can add an "Ask in Zed Agent" button to your software today.

🚀 We just shipped v0.223! Launch Zed's Agent Panel with a prompt via URL: zed://agent?prompt=your+prompt+here Now, you can add an "Ask in Zed Agent" button to your software today.

Zed

21,042 views • 5 months ago

New Feature Live!🚨 Introducing Prompt Assist—a feature designed to streamline your prompt-writing experience with Alchemist AI. Prompt Assist integrates a speed-oriented AI model that analyzes your input as you write, offering contextually relevant suggestions in real-time. Here’s how it works: • Real-Time Suggestions: Prompt Assist dynamically processes your input, predicting next steps from your initial wording. Press Tab to accept suggestions and seamlessly complete your prompt. • Smart Context Analysis: The feature leverages natural language processing models to understand the structure and intent of your prompt, this ensures the suggestions remain precise and useful.

New Feature Live!🚨 Introducing Prompt Assist—a feature designed to streamline your prompt-writing experience with Alchemist AI. Prompt Assist integrates a speed-oriented AI model that analyzes your input as you write, offering contextually relevant suggestions in real-time. Here’s how it works: • Real-Time Suggestions: Prompt Assist dynamically processes your input, predicting next steps from your initial wording. Press Tab to accept suggestions and seamlessly complete your prompt. • Smart Context Analysis: The feature leverages natural language processing models to understand the structure and intent of your prompt, this ensures the suggestions remain precise and useful.

ALCHEMIST AI 🔮

37,880 views • 1 year ago

The new Anthropic prompt improver is incredible. You just need to write your prompt and Claude will generate an optimized prompt instantly. Here’s how to use it:

The new Anthropic prompt improver is incredible. You just need to write your prompt and Claude will generate an optimized prompt instantly. Here’s how to use it:

Alvaro Cintas

205,964 views • 1 year ago

SOMEONE BUILT A CLAUDE CODE PLUGIN THAT REFUSES TO WORK UNTIL YOU DO PUSH-UPS OR SQUATS its called workout gate and it is exactly as cursed as it sounds when the hook fires, it blocks your prompt, opens your webcam, and makes you exercise to keep coding > it counts your reps live through the webcam with mediapipe, no honor system rounding down > only releases your prompt once you actually finish the reps > quit halfway and the leftover reps get saved as debt for your next session > chill, demo and hardcore presets, plus prompt based, time based or random triggers > tracks stats, streaks and personal records right in the claude code statusline we automated the coding, now we're automating the part where we actually take care of ourselves

SOMEONE BUILT A CLAUDE CODE PLUGIN THAT REFUSES TO WORK UNTIL YOU DO PUSH-UPS OR SQUATS its called workout gate and it is exactly as cursed as it sounds when the hook fires, it blocks your prompt, opens your webcam, and makes you exercise to keep coding > it counts your reps live through the webcam with mediapipe, no honor system rounding down > only releases your prompt once you actually finish the reps > quit halfway and the leftover reps get saved as debt for your next session > chill, demo and hardcore presets, plus prompt based, time based or random triggers > tracks stats, streaks and personal records right in the claude code statusline we automated the coding, now we're automating the part where we actually take care of ourselves

Om Patel

670,437 views • 1 month ago

We decided to take Paul Jankura’s Claude Opus 4.5 out for a test drive vs. the current #1 ranking model in Code Arena: Gemini 3 Pro. Same prompt, different outputs. Let’s take a look. Remember, your votes drive the leaderboards. We’ll see how Claude Opus 4.5 stacks up in the coming days! Check out some of the comparisons, like how Claude Opus 4.5 handled the “Pyramids of Giza” prompt, in thread. 🧵

We decided to take Paul Jankura’s Claude Opus 4.5 out for a test drive vs. the current #1 ranking model in Code Arena: Gemini 3 Pro. Same prompt, different outputs. Let’s take a look. Remember, your votes drive the leaderboards. We’ll see how Claude Opus 4.5 stacks up in the coming days! Check out some of the comparisons, like how Claude Opus 4.5 handled the “Pyramids of Giza” prompt, in thread. 🧵

Arena.ai

88,977 views • 8 months ago

Cursor - the AI-focused VSCode fork - is mind-blowing. The ability to reference files and documentation endpoints is absolutely insane. You can chat with your code, generate code, even lint code errors! Best of all - you can just add your own OpenAI token.

Cursor - the AI-focused VSCode fork - is mind-blowing. The ability to reference files and documentation endpoints is absolutely insane. You can chat with your code, generate code, even lint code errors! Best of all - you can just add your own OpenAI token.

Marcel Pociot 🧪

318,317 views • 3 years ago

2. Generate Unlimited Prompt Ideas Prompt: "You are Prompt Professional, the most advanced ChatGPT prompt writer in the world. I will provide you a prompt. Today, your job is to rewrite the prompts again in 10 different and creative way. Now ask me what prompt to rewrite."

2. Generate Unlimited Prompt Ideas Prompt: "You are Prompt Professional, the most advanced ChatGPT prompt writer in the world. I will provide you a prompt. Today, your job is to rewrite the prompts again in 10 different and creative way. Now ask me what prompt to rewrite."

Barsee 🐶

156,774 views • 3 years ago

Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow while multi-clauding.

Claude Code in the terminal will now show recaps when you switch focus away from the session and then come back. This should help you stay more in flow while multi-clauding.

ClaudeDevs

519,014 views • 3 months ago

You can now delegate tasks to GitHub Copilot coding agent from any page on GitHub 🤖 Open the new Agents panel in one click, write a simple prompt, then hit Enter. GitHub Copilot works in the background, and opens a PR for your review. No interruptions to your workflow required. ✅

You can now delegate tasks to GitHub Copilot coding agent from any page on GitHub 🤖 Open the new Agents panel in one click, write a simple prompt, then hit Enter. GitHub Copilot works in the background, and opens a PR for your review. No interruptions to your workflow required. ✅

GitHub

113,332 views • 11 months ago

Claude Code can now send push notifications to your phone when a long task finishes or Claude needs your input. Walk away from the terminal, we'll let you know when it's done.

Claude Code can now send push notifications to your phone when a long task finishes or Claude needs your input. Walk away from the terminal, we'll let you know when it's done.

ClaudeDevs

1,335,787 views • 3 months ago

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

Sudo su

37,623 views • 5 months ago

Gemma 4 12B QAT (dense) achieves 1000+ tokens/sec prefill on 8GB VRAM with 120k context Gemma 4 12B QAT (dense), TurboQuant (Without MTP), RTX 4060 8GB VRAM: Prefill: 1000+ tok/s (42% increase) Decode: 25+ tok/s (25% increase) Context: 120k (150% increase) prefill was 700 tok/sec and decode 20 tok/sec with only 48k context without turbo quant (older test with mtp link in the comments) llama.cpp TurboQuant flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf -c 120000 --cache-type-k q8_0 --cache-type-v turbo3 -ngl 99 --port 8080 tested with a 27k prompt, 120k context loaded. -ngl 99 here isn't a typo, full 12B dense, every layer on GPU, on an 8GB card. that's the part worth sitting with. The model has vision, audio input, thinking/reasoning and fits your 8GB card. TurboQuant's KV cache savings are what free up the room to do that at 120k context. side by side with yesterday: 26B A4B MoE got 320+ tok/s prefill. this dense 12B is clearing 1000+ rig: RTX 4060 8GB · i7H · 16GB RAM same two flags as yesterday, different model size: --cache-type-k q8_0 --cache-type-v turbo3 thanks to TheTom/llama-cpp-turboquant, TurboQuant fork of llama.cpp by Tom Turney (Tom Turney) to make this work. unsloth's model quant huggingface and the llama.cpp fork github link in the comments Do you prefer a dense or a MoE for your 8GB card?

Gemma 4 12B QAT (dense) achieves 1000+ tokens/sec prefill on 8GB VRAM with 120k context Gemma 4 12B QAT (dense), TurboQuant (Without MTP), RTX 4060 8GB VRAM: Prefill: 1000+ tok/s (42% increase) Decode: 25+ tok/s (25% increase) Context: 120k (150% increase) prefill was 700 tok/sec and decode 20 tok/sec with only 48k context without turbo quant (older test with mtp link in the comments) llama.cpp TurboQuant flags: -m gemma-4-12B-it-qat-UD-Q4_K_XL.gguf -c 120000 --cache-type-k q8_0 --cache-type-v turbo3 -ngl 99 --port 8080 tested with a 27k prompt, 120k context loaded. -ngl 99 here isn't a typo, full 12B dense, every layer on GPU, on an 8GB card. that's the part worth sitting with. The model has vision, audio input, thinking/reasoning and fits your 8GB card. TurboQuant's KV cache savings are what free up the room to do that at 120k context. side by side with yesterday: 26B A4B MoE got 320+ tok/s prefill. this dense 12B is clearing 1000+ rig: RTX 4060 8GB · i7H · 16GB RAM same two flags as yesterday, different model size: --cache-type-k q8_0 --cache-type-v turbo3 thanks to TheTom/llama-cpp-turboquant, TurboQuant fork of llama.cpp by Tom Turney (Tom Turney) to make this work. unsloth's model quant huggingface and the llama.cpp fork github link in the comments Do you prefer a dense or a MoE for your 8GB card?

Alok

34,500 views • 1 month ago

SOMEONE TURNED 33 PILES OF DEAD BOOKMARKS INTO A GRAVITY MAP CLAUDE REBUILDS ITSELF EVERY NIGHT - AND IT RUNS ON THE 80% OF CLAUDE NOBODY TOUCHES most people drive Claude Code like a chatbot with file access - type a prompt, watch it edit, move on. that's maybe 20% of the tool this is the opposite. she's not typing at Claude. she's running it - loops on a mac mini overnight, claude linking every node while she sleeps the gravity map in the video is just the 80% maxed out: 1 system that organizes itself, not a human babysitting a chat box the other 80% is a steering layer Anthropic shipped quietly on june 18 - 7 ways to instruct the model, and a stack of commands almost nobody opens /context to see your bloat. /clear between tasks. path-scoped rules, subagents, hooks - conventions that load themselves the exact second they matter i stopped typing at Claude months ago - now i configure it once and it shows up already running the work, 10x cleaner a prompt helps for 1 message. the steering layer pays you back every session, for life the people who learn it stop being users and become operators - everyone else is still arguing about which model is smartest the article below is the full map - all 4 layers, every file and command, start to finish

SOMEONE TURNED 33 PILES OF DEAD BOOKMARKS INTO A GRAVITY MAP CLAUDE REBUILDS ITSELF EVERY NIGHT - AND IT RUNS ON THE 80% OF CLAUDE NOBODY TOUCHES most people drive Claude Code like a chatbot with file access - type a prompt, watch it edit, move on. that's maybe 20% of the tool this is the opposite. she's not typing at Claude. she's running it - loops on a mac mini overnight, claude linking every node while she sleeps the gravity map in the video is just the 80% maxed out: 1 system that organizes itself, not a human babysitting a chat box the other 80% is a steering layer Anthropic shipped quietly on june 18 - 7 ways to instruct the model, and a stack of commands almost nobody opens /context to see your bloat. /clear between tasks. path-scoped rules, subagents, hooks - conventions that load themselves the exact second they matter i stopped typing at Claude months ago - now i configure it once and it shows up already running the work, 10x cleaner a prompt helps for 1 message. the steering layer pays you back every session, for life the people who learn it stop being users and become operators - everyone else is still arguing about which model is smartest the article below is the full map - all 4 layers, every file and command, start to finish

KingWilliam

12,305 views • 1 month ago