Загрузка видео...

Не удалось загрузить видео

На главную

Claude Code used to interrupt you constantly. Approve this. Approve that. Approve everything. Auto Mode just fixed it. Now Claude keeps working while a safety classifier blocks dangerous actions automatically ⚡

JulianGoldieSEO's profile picture

Julian Goldie SEO

164,302 subscribers

16,606 просмотров • 7 месяцев назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Anthropic just dropped Dispatch in Claude Cowork. Message Claude from your phone. It runs persistent tasks on your desktop (files, code, browser). Come back to finished work. Local sandbox, you approve everything.
0:40

Anthropic just dropped Dispatch in Claude Cowork. Message Claude from your phone. It runs persistent tasks on your desktop (files, code, browser). Come back to finished work. Local sandbox, you approve everything.

TFTC

14,608 просмотров • 7 месяцев назад

We recently made auto mode the default in Claude Code, which means you no longer have to approve every action. But what determines if something is safe to run? Watch how it works:
5:41

We recently made auto mode the default in Claude Code, which means you no longer have to approve every action. But what determines if something is safe to run? Watch how it works:

ClaudeDevs

400,614 просмотров • 3 месяцев назад

Claude Code: Auto mode Auto mode lets Claude safely complete long-running tasks without asking permission for every action. But how does it work? 4 key terms: • Classifier: a separate model that approves or denies each action based on your intent and scope • Filtering: the classifier only sees your messages and Claude's tool calls, not Claude’s reasoning or tool outputs, so it isn't influenced when making decisions • Tier check: read-only and easily-undone actions (like edits inside your repo) skip the classifier; everything else goes through it • Probe: a server-side check that scans incoming content, like web pages, for prompt injection and flags it to Claude I'm working on a longer video that explains how auto mode works and how to configure it. What questions do you have about it?
0:52

Claude Code: Auto mode Auto mode lets Claude safely complete long-running tasks without asking permission for every action. But how does it work? 4 key terms: • Classifier: a separate model that approves or denies each action based on your intent and scope • Filtering: the classifier only sees your messages and Claude's tool calls, not Claude’s reasoning or tool outputs, so it isn't influenced when making decisions • Tier check: read-only and easily-undone actions (like edits inside your repo) skip the classifier; everything else goes through it • Probe: a server-side check that scans incoming content, like web pages, for prompt injection and flags it to Claude I'm working on a longer video that explains how auto mode works and how to configure it. What questions do you have about it?

Delba

43,073 просмотров • 5 месяцев назад

Claude Security is now in public beta for Claude Enterprise customers. Claude scans your codebase for vulnerabilities, validates each finding to cut false positives, and suggests patches you can review and approve.
0:50

Claude Security is now in public beta for Claude Enterprise customers. Claude scans your codebase for vulnerabilities, validates each finding to cut false positives, and suggests patches you can review and approve.

Claude

4,919,543 просмотров • 6 месяцев назад

Claude now works inside Google Docs, Sheets, and Slides, and those files also open inside Claude. In Google Workspace, Claude sits in a sidebar next to your file, reads what you have open, and edits it in place. You can approve each edit before it lands.
1:00

Claude now works inside Google Docs, Sheets, and Slides, and those files also open inside Claude. In Google Workspace, Claude sits in a sidebar next to your file, reads what you have open, and edits it in place. You can approve each edit before it lands.

Claude

13,402,416 просмотров • 1 месяц назад

It is becoming f*cking dangerous: A prompt for creating trading agents was accidentally leaked online. You paste it into claude code, and it builds a bot while you have lunch No code. Just Ctrl+C / Ctrl+V. One prompt solves everything: Time: 1 minute Action: copy and paste into Claude Code The main problem with 99% of bots: one strategy for everything. But the market on a calm day and during a crash are two completely different worlds Quant mode: detects market conditions (sideways, jittery, dump) and changes tactics on the fly E-brake: a strict 15% drawdown limit and risk checks before every order Hardcore backtest: runs the strategy on historical data and blocks trading if it is not profitable Nightly analyst: while you sleep, it analyzes mistakes and produces ready-to-approve setups Zero Code: type in the prompt, insert your parameters, and Claude handles the rest This used to take a whole development team and months of testing. Now it takes a single keyboard shortcut The prompt is published below, bookmark it so you do not lose it
0:22

It is becoming f*cking dangerous: A prompt for creating trading agents was accidentally leaked online. You paste it into claude code, and it builds a bot while you have lunch No code. Just Ctrl+C / Ctrl+V. One prompt solves everything: Time: 1 minute Action: copy and paste into Claude Code The main problem with 99% of bots: one strategy for everything. But the market on a calm day and during a crash are two completely different worlds Quant mode: detects market conditions (sideways, jittery, dump) and changes tactics on the fly E-brake: a strict 15% drawdown limit and risk checks before every order Hardcore backtest: runs the strategy on historical data and blocks trading if it is not profitable Nightly analyst: while you sleep, it analyzes mistakes and produces ready-to-approve setups Zero Code: type in the prompt, insert your parameters, and Claude handles the rest This used to take a whole development team and months of testing. Now it takes a single keyboard shortcut The prompt is published below, bookmark it so you do not lose it

Bober_smart

118,491 просмотров • 23 дней назад

Tired of manually approving agent mode tools? You can configure the setting to auto-approve all tools. And you can configure this setting only for your remote development environment, for some level of protection from any potentially destructive actions.
1:00

Tired of manually approving agent mode tools? You can configure the setting to auto-approve all tools. And you can configure this setting only for your remote development environment, for some level of protection from any potentially destructive actions.

Visual Studio Code

26,620 просмотров • 1 год назад

Claude Duet: now with Claude Code sessions Check what's running, approve changes and send updates - all from your phone. Works with sessions on your computer or in the cloud. /cc #!/bin/bryce and Josh Leibsly
0:29

Claude Duet: now with Claude Code sessions Check what's running, approve changes and send updates - all from your phone. Works with sessions on your computer or in the cloud. /cc #!/bin/bryce and Josh Leibsly

David Sutton

301,804 просмотров • 2 дней назад

Three new polls were just released and Trump's numbers are absolutely HORRIFIC! Fox News Poll - Overall Approval - 44% Approve - 55% Disapprove - Immigration - 47% Approve - 48% Disapprove - Foreign Policy - 40% Approve - 54% Disapprove - Economy - 38% Approve - 56% Disapprove - Tariffs - 33% Approve - 58% Disapprove - Inflation - 33% Approve - 59% Disapprove Ipsos / REUTERS Poll - Overall Approval - 42% Approve - 53% Disapprove - Economy - 37% Approve - 51% Disapprove - Immigration - 45% Approve - 46% Disapprove PewResearchCenter Poll - Overall Approval - 40% Approve - 59% Disapprove - Tariffs - 39% Approve - 59% Disapprove - DOGE Cuts - 44% Approve - 55% Disapprove - Economy - 45% Approve - 55% Disapprove
1:40

Three new polls were just released and Trump's numbers are absolutely HORRIFIC! Fox News Poll - Overall Approval - 44% Approve - 55% Disapprove - Immigration - 47% Approve - 48% Disapprove - Foreign Policy - 40% Approve - 54% Disapprove - Economy - 38% Approve - 56% Disapprove - Tariffs - 33% Approve - 58% Disapprove - Inflation - 33% Approve - 59% Disapprove Ipsos / REUTERS Poll - Overall Approval - 42% Approve - 53% Disapprove - Economy - 37% Approve - 51% Disapprove - Immigration - 45% Approve - 46% Disapprove PewResearchCenter Poll - Overall Approval - 40% Approve - 59% Disapprove - Tariffs - 39% Approve - 59% Disapprove - DOGE Cuts - 44% Approve - 55% Disapprove - Economy - 45% Approve - 55% Disapprove

Ed Krassenstein

1,133,306 просмотров • 1 год назад

Mercury Command is live. AI built directly into your Mercury account that completes financial work. Natural language, real actions, and you approve everything. This is how banking* works now.
0:24

Mercury Command is live. AI built directly into your Mercury account that completes financial work. Natural language, real actions, and you approve everything. This is how banking* works now.

Mercury

158,434 просмотров • 4 месяцев назад

STOP COPY-PASTING BETWEEN YOUR AIs. NOW THEY TALK TO EACH OTHER. Until today you were the messenger. Copy from Grok, paste into Claude, copy from Claude, repeat. Bolter just fixed that. Here's how they connect: 1. Copy one line 2. Paste it into your AI 3. Confirm with a code 4. It's in the chat Then you share its handle and it starts working with your other AIs and your friends' AIs. Give them a task and they split it up. One picks the landing site, another designs the wheels, another writes the code. The rover is ready and you didn't copy a thing. Each AI keeps its memory and you approve every connection. Link below 👇🏼
0:23

STOP COPY-PASTING BETWEEN YOUR AIs. NOW THEY TALK TO EACH OTHER. Until today you were the messenger. Copy from Grok, paste into Claude, copy from Claude, repeat. Bolter just fixed that. Here's how they connect: 1. Copy one line 2. Paste it into your AI 3. Confirm with a code 4. It's in the chat Then you share its handle and it starts working with your other AIs and your friends' AIs. Give them a task and they split it up. One picks the landing site, another designs the wheels, another writes the code. The rover is ready and you didn't copy a thing. Each AI keeps its memory and you approve every connection. Link below 👇🏼

marcus

70,065 просмотров • 27 дней назад

Claude gets 8 DexDad tools on the $XRP Ledger. Claude reads prices and builds the swap. You approve it in your own wallet. Final in 3–5s. Settings → Connectors → Add custom connector →
0:24

Claude gets 8 DexDad tools on the $XRP Ledger. Claude reads prices and builds the swap. You approve it in your own wallet. Final in 3–5s. Settings → Connectors → Add custom connector →

DexDad

17,362 просмотров • 8 дней назад

"Just fucking approve it." Emily Thornberry recites Morgan McSweeney's call for the Foreign Office to approve Peter Mandelson's appointment as US Ambassador.
0:54

"Just fucking approve it." Emily Thornberry recites Morgan McSweeney's call for the Foreign Office to approve Peter Mandelson's appointment as US Ambassador.

PoliticsJOE

61,760 просмотров • 6 месяцев назад

/btw shipped in Claude Code recently. It allows you to have a sidebar conversation with Claude while the original prompt is still working, allowing you to work while you work.
0:24

/btw shipped in Claude Code recently. It allows you to have a sidebar conversation with Claude while the original prompt is still working, allowing you to work while you work.

Ado

30,017 просмотров • 8 месяцев назад

Do you approve of this?
0:50

Do you approve of this?

Jeff pontz

94,981 просмотров • 1 год назад

Your Claude Projects cloud session can now connect to a folder you approve on your computer. The session stays in the cloud and only reaches for that local folder when a task needs it, reading and editing the files in place. Starting to roll out today.
0:20

Your Claude Projects cloud session can now connect to a folder you approve on your computer. The session stays in the cloud and only reaches for that local folder when a task needs it, reading and editing the files in place. Starting to roll out today.

Dan Fein

292,248 просмотров • 1 месяц назад

Do you approve of this 590A1?
0:25

Do you approve of this 590A1?

Mossberg

45,613 просмотров • 1 год назад

How to make Claude Code 10x better: Connect it with a tool that reviews your code and generates prompts for Claude to fix any issues with it automatically. Here is what this looks like:
3:38

How to make Claude Code 10x better: Connect it with a tool that reviews your code and generates prompts for Claude to fix any issues with it automatically. Here is what this looks like:

Santiago

98,993 просмотров • 1 год назад

How to make a woman miss you… ladies do you approve this message??
1:21

How to make a woman miss you… ladies do you approve this message??

Better Men

231,968 просмотров • 1 год назад

Artifacts in Claude Code are now also available on Pro and Max plans. Ask for an artifact, Claude writes the code, publishes it live to claude.a‍i, and updates it in real time while it keeps working. Pages are private to your account and fully self-contained.
1:48

Artifacts in Claude Code are now also available on Pro and Max plans. Ask for an artifact, Claude writes the code, publishes it live to claude.a‍i, and updates it in real time while it keeps working. Pages are private to your account and fully self-contained.

ClaudeDevs

2,047,843 просмотров • 4 месяцев назад