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.

I reverse-engineered Claude Code's binary to add a feature I always wanted: When context fills up - instead of nuking everything with /compact - I can now surgically strip tool calls/results and thinking blocks while keeping all actual messages intact.

Convergence Boy

2,794 subscribers

197,831 views • 3 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

OMG I can't believe I reverse engineered Apple Notes with Claude Code. I can import everything from Apple Notes like folders, notes, images and everything. Also this is realtime, not sped up. Now everyone can migrate from Apple Notes to Grape.

OMG I can't believe I reverse engineered Apple Notes with Claude Code. I can import everything from Apple Notes like folders, notes, images and everything. Also this is realtime, not sped up. Now everyone can migrate from Apple Notes to Grape.

Ozgur Ozer

172,959 views • 2 months ago

I reverse-engineered Claude Code's binary. Found a flag they hid from --help. --sdk-url Enable it and the terminal disappears. The CLI becomes a WebSocket client. We built a server to catch the connection. Added a React UI on top. Now I run Claude Code from my browser. From my phone. From anywhere. Same $200/month subscription. Zero extra API costs. bunx the-vibe-companion

I reverse-engineered Claude Code's binary. Found a flag they hid from --help. --sdk-url Enable it and the terminal disappears. The CLI becomes a WebSocket client. We built a server to catch the connection. Added a React UI on top. Now I run Claude Code from my browser. From my phone. From anywhere. Same $200/month subscription. Zero extra API costs. bunx the-vibe-companion

Stan Girard

693,001 views • 3 months ago

While working on my new Goku SSJ Mid I thought that maybe I can do what I've always wanted to with a SSJ hair and turn it gold when charging KI, well, since we can actually add code to the BPs now, I managed to do just that and change materials when Charging or in Sparking mode

While working on my new Goku SSJ Mid I thought that maybe I can do what I've always wanted to with a SSJ hair and turn it gold when charging KI, well, since we can actually add code to the BPs now, I managed to do just that and change materials when Charging or in Sparking mode

Millennium

259,302 views • 1 year ago

"I can recall every detail, the bones and everything, as I lost my leg," 14-year-old Obaida told DCIP. "I wanted to stand up while my leg was still intact. As I attempted to move, it dislocated and amputated itself."

"I can recall every detail, the bones and everything, as I lost my leg," 14-year-old Obaida told DCIP. "I wanted to stand up while my leg was still intact. As I attempted to move, it dislocated and amputated itself."

Defense for Children

18,303 views • 5 months ago

I've been writing #rstats packages and coding web maps for a decade now. Despite this, while I've always wanted a story map feature in R, I never really knew how. With Claude Sonnet and Cursor, I got a working prototype in a morning, and now it's on CRAN for you to use.

I've been writing #rstats packages and coding web maps for a decade now. Despite this, while I've always wanted a story map feature in R, I never really knew how. With Claude Sonnet and Cursor, I got a working prototype in a morning, and now it's on CRAN for you to use.

Kyle Walker

21,259 views • 1 year ago

Abadon actually speaks breaking down their pronouns with their actual voice while keeping kayfabe intact. I swear every episode of Hey! (EW) just keeps getting better.

Abadon actually speaks breaking down their pronouns with their actual voice while keeping kayfabe intact. I swear every episode of Hey! (EW) just keeps getting better.

Drainmaker

283,012 views • 2 years ago

Joe Rogan: "I think marijuana’s a tool. Like everything else. I think you can learn things from it. And I think it’s steroids for comedy. You can come up with some stuff when you're high..."

Joe Rogan: "I think marijuana’s a tool. Like everything else. I think you can learn things from it. And I think it’s steroids for comedy. You can come up with some stuff when you're high..."

Joe Rogan Podcast News

64,484 views • 3 months ago

reverse engineered discord to record discord calls (cuz dax wanted)

reverse engineered discord to record discord calls (cuz dax wanted)

soham

96,641 views • 3 months ago

Ranamon is one of those characters I wanted to dedicate an entire animation to. Mostly because of those amazing feet. It has been on my plate for quite a while now and I can proudly say that I'm satisfied with the results.

Ranamon is one of those characters I wanted to dedicate an entire animation to. Mostly because of those amazing feet. It has been on my plate for quite a while now and I can proudly say that I'm satisfied with the results.

BlueHulkhog

17,360 views • 2 years ago

YOU CAN NOW SEND FOLLOW UP MESSAGES TO CHATGPT WHILE ITS THINKING!!!!!!

YOU CAN NOW SEND FOLLOW UP MESSAGES TO CHATGPT WHILE ITS THINKING!!!!!!

nic

46,052 views • 3 months ago

Vibe coded this Threejs avatar gallery with over 300 3D open source avatars in my spare time. Cursor + Claude doing all of the heavy lifting while I watched Features a complete VRM inspector tool and Japanese support! Probably over engineered but works

ToxSam

22,174 views • 1 year ago

I'm SO impressed by Claude Skills. They are the best way to package custom instructions (and code) for the agent to access. (I prefer this to Claude Code's subagents because of the way it handles context) I used the skill-creator skill (comes default inside Claude) to create a skill for designing a presentation like Steve Jobs or Seth Godin, then used that skill to create a PPT about Claude Code. Below is a walkthrough of the results. The output when using the above mentioned skill vs when i don't is so clear. I'm bullish on what this implies for both Claude web and Claude Code. Extremely powerful. Anthropic cooked! 🔥

I'm SO impressed by Claude Skills. They are the best way to package custom instructions (and code) for the agent to access. (I prefer this to Claude Code's subagents because of the way it handles context) I used the skill-creator skill (comes default inside Claude) to create a skill for designing a presentation like Steve Jobs or Seth Godin, then used that skill to create a PPT about Claude Code. Below is a walkthrough of the results. The output when using the above mentioned skill vs when i don't is so clear. I'm bullish on what this implies for both Claude web and Claude Code. Extremely powerful. Anthropic cooked! 🔥

Nityesh

62,918 views • 7 months ago

you're running /compact every 10 minutes to fix a problem that disappears the second you give Claude one job instead of five. Anthropic shipped a clean 4-minute video on context management. /compact when the window fills up. /clear to reset. small files over big files. the practical tips work. the video covers the cleanup. it doesn't cover why your window keeps filling up in the first place, and the answer is usually that you're holding too many jobs in one prompt. look at what most people put in a single Claude call: > guess the right answer > choose between options > set the position size > watch the exit window > read the news for sentiment five tools' worth of state in one conversation. of course the window fills. i ran into this on a Polymarket bot: the prediction-layer version ate context constantly. /compact every 8-10 turns. i thought i needed better memory hygiene. i needed fewer jobs per call. i stripped the prompt down to one job: veto an entry i had already decided to take. the context window stopped filling. /compact went from every 8 turns to once a session, if ever. over 90 days that prompt blocked 128 trades. watch the 4 min, then ask why your window keeps needing it. clean context. lean prompt. nothing to compact.

you're running /compact every 10 minutes to fix a problem that disappears the second you give Claude one job instead of five. Anthropic shipped a clean 4-minute video on context management. /compact when the window fills up. /clear to reset. small files over big files. the practical tips work. the video covers the cleanup. it doesn't cover why your window keeps filling up in the first place, and the answer is usually that you're holding too many jobs in one prompt. look at what most people put in a single Claude call: > guess the right answer > choose between options > set the position size > watch the exit window > read the news for sentiment five tools' worth of state in one conversation. of course the window fills. i ran into this on a Polymarket bot: the prediction-layer version ate context constantly. /compact every 8-10 turns. i thought i needed better memory hygiene. i needed fewer jobs per call. i stripped the prompt down to one job: veto an entry i had already decided to take. the context window stopped filling. /compact went from every 8 turns to once a session, if ever. over 90 days that prompt blocked 128 trades. watch the 4 min, then ask why your window keeps needing it. clean context. lean prompt. nothing to compact.

Mnimiy

20,635 views • 17 days ago

Claude reversing a binary using Binary Ninja via MCP while I get a snack blasty Ziyad Edher Vector 35

Claude reversing a binary using Binary Ninja via MCP while I get a snack blasty Ziyad Edher Vector 35

itszn

225,554 views • 1 year ago

Winter’s ment about ‘Blue’ “This is a song I wrote bc I wanted to bring comfort to MYs. So when you feel like you’ve lost a bit of confidence or when you need comfort, I hope you can listen to this song while thinking that I’m the one cheering u up and comforting you” 🥹

Winter’s ment about ‘Blue’ “This is a song I wrote bc I wanted to bring comfort to MYs. So when you feel like you’ve lost a bit of confidence or when you need comfort, I hope you can listen to this song while thinking that I’m the one cheering u up and comforting you” 🥹

Jazz

39,632 views • 3 months ago

Claude can now code @TradingView indicators for you! I've always wanted an indicator with all my key intraday levels in one place, the way I wanted to see them. I won't stop until my entire system is coded. Learn how to start creating yours here👇

Claude can now code @TradingView indicators for you! I've always wanted an indicator with all my key intraday levels in one place, the way I wanted to see them. I won't stop until my entire system is coded. Learn how to start creating yours here👇

Trader Diego

290,306 views • 1 month ago

Claude Cowork now supports the Slack MCP on all paid plans! The Slack connector is by far my favorite feature. I use it every morning to catch up on what I missed, highlight important messages, and draft replies for me to review before sending. Huge time saver.

Claude Cowork now supports the Slack MCP on all paid plans! The Slack connector is by far my favorite feature. I use it every morning to catch up on what I missed, highlight important messages, and draft replies for me to review before sending. Huge time saver.

Lydia Hallie ✨

200,543 views • 4 months ago

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

62,476 views • 1 month ago

I’ve been asked a lot why I keep Claude Code auto-compact turned off. Here’s why 👇 If you configure commands, sub-agents, and hooks properly, you almost never hit auto-compact. Every time it triggered for me, I lost important context. After looking at how compaction actually works, it was clear that key details were being dropped. So I disabled it and focused on better context management per session instead. If you want to see what happens under the hood when a compact runs: npx claude-code-templates@latest --chats You’ll get a full breakdown + per-session analytics to keep improving your workflows.

I’ve been asked a lot why I keep Claude Code auto-compact turned off. Here’s why 👇 If you configure commands, sub-agents, and hooks properly, you almost never hit auto-compact. Every time it triggered for me, I lost important context. After looking at how compaction actually works, it was clear that key details were being dropped. So I disabled it and focused on better context management per session instead. If you want to see what happens under the hood when a compact runs: npx claude-code-templates@latest --chats You’ll get a full breakdown + per-session analytics to keep improving your workflows.

Daniel San

105,569 views • 4 months ago

Wes Streeting, now: I always use disappearing messages on WhatsApp. Wes Streeting in February: *Released a batch of WhatsApp messages with Lord Mandelson, over a period of 14 months* I don’t believe Wes has disappearing messages on. He’s lying and part of the cover up.

Wes Streeting, now: I always use disappearing messages on WhatsApp. Wes Streeting in February: Released a batch of WhatsApp messages with Lord Mandelson, over a period of 14 months I don’t believe Wes has disappearing messages on. He’s lying and part of the cover up.

Chris Rose

125,049 views • 2 months ago