@SinfulSnowBunny @ManyVids did you stop making new videos? I love your work.
English
Chad Darby
104 posts
VID SOLD! BBC POUNDING AND BJ BEFORE SWALLOW 🔥 Check it out! manyvids.com/Video/616736/B… #MVSales @manyvids
English
@bcherny I'm on the MAX 20x plan and still don't have access to /remote-control after logging out and back in multiple times. Is this a bug? I wrote your help-desk and was also charged for API use that never happened. It seems like multiple bugs recently and I still don't have any help!
English
🎶 I've been using voice mode to write much of my CLI code this last week
Can't wait to hear what you think.
Thariq@trq212
Voice mode is rolling out now in Claude Code. It’s live for ~5% of users today, and will be ramping through the coming weeks. You'll see a note on the welcome screen once you have access. /voice to toggle it on!
English
@spaceMonster how do you use cursor remote control explain please?
English
psa: install taskmaster and you will be within the 0.01% of the 0.01% of users who have claude code running for days straight
github.com/blader/taskmas…
THE SHORT BEAR@TheShortBear
If you are working/vibe coding more than 40min per day you are within 0.01% of users using it the most. You are not late. This is the part where everything feels too late but it’s only because we are so early and everyone is scrambling.
English
@nummanali @AlexisHiro How do you get it to think that hard? Please explain
English
If your Claude Code runs are longer than 40 minutes, then you're in the top 0.1% of users
Anthropic@AnthropicAI
Most Claude Code turns are short (median ~45 seconds). But the longest turns show where autonomy is heading. In three months, the 99.9th percentile turn duration nearly doubled, from under 25 minutes to over 45 minutes. This growth is smooth across model releases.
English
@seconds_0 @trq212 @bcherny what benefits did the sdk have over using claude code cli? So I understand?
English
@tetsuoai @minheo93698092 If you guys ever had a special for 1 month to try Heavy and see what it can do for a lower price, sign me up... that would be amazing!
English
🚨Grok 4.20 Heavy dropped for Heavy subscribers.
Big change under the hood: it now runs as a full team of 16 specialized agents that collaborate in real time on every single answer. All on the grok-4.20 architecture.
Here's the crew:
Grok - leads everything, coordinates and keeps it truthful with the usual dry humor
Harper - creative writing and storytelling
Benjamin - data, finance and economics
Lucas - coding, programming and technical builds
Olivia - literature, arts and culture
James - history, politics and philosophy
Charlotte - math, statistics and logic
Henry - engineering, robotics and innovation
Mia - biology, health and medicine
William - business strategy and entrepreneurship
Sebastian - physics, astronomy and hard sciences
Jack - psychology and human behavior
Owen - environment, sustainability and global systems
Luna - space exploration and futurism
Elizabeth - ethics, policy and critical thinking
Noah - long-term innovation and systems thinking
The difference is noticeable on anything complex. If you've got Heavy, go throw something tough at it and see.
English
@nummanali For $200, I feel like 1m (opus) should be part of the package.
@trq212 any chance this is in the works or we just have to wait for future model offerings that would make business sense at that level?
English
Opus and Sonnet 1M extra usage has now been adjusted
If you got over the 200K context, it will be charged as overage i.e. not part of your subscription plan
I still keep the 1M models enabled, as compaction is no longer forced at around ~165K context
Lets you squeeze extra
Numman Ali@nummanali
Both Opus and Sonnet 1M are not being charged as extra usage They are treated as part of your Max plan atm This may be subject to change or a glitch It will eat into usage much faster as soon as you go over the 200K context i.e. double the rate, in line with API pricing
English
@thsottiaux gpt PRO models as the architect for PRO accounts in codex plz
English
🎉 Added Senator Wicker
We’re now at 48
Baby steps to SAVE America 🎉
Mike Lee@BasedMikeLee
🇺🇸 Added Senator Tim Scott We’re now at 47 Baby steps to SAVE America 🇺🇸
English
@sama PLEASE ADD THE PRO MODEL TO CODEX FOR PRO subscribers so we have the best architect 🙏🤞
English
We have a special thing launching to Codex users on the Pro plan later today. It sparks joy for me. I think you are going to love it...
English
@thsottiaux Can we please for the love of God include the PRO models in Codex like GPT 5.2 pro🙏🤞
English
just built a skill that makes claude code plan your agent teams before spawning them.
no more stupid automatically chosen agents, it reads your project, asks you some questions, drops a clean team plan, and lets you approve it or refine it.
If you liked this team, you can save it as a reusable slash command for later use.
Use right now:
npx skills add octaviusp/spawning-plan-skill -g
and you're set
@bcherny add this spawning plan strategy as default pls the current choosing is not so good. Also, if the user liked the team, can be saved as skill, so next iterations go straight to spawn, no plan.
English
@ibrahimsuta @bcherny @ibekidkirsch Actually was thinking this. I pair the two together to work side-by-side and was hoping Opus 4.6 thought harder like Gpt5.2.
English
I've been using Opus 4.6 for a bit -- it is our best model yet. It is more agentic, more intelligent, runs for longer, and is more careful and exhaustive.
For Claude Code users, you can also now more precisely tune how much the model thinks. Run /model and arrow left/right to tune effort (less = faster, more = longer thinking & better results).
Happy coding!
Claude@claudeai
Introducing Claude Opus 4.6. Our smartest model got an upgrade. Opus 4.6 plans more carefully, sustains agentic tasks for longer, operates reliably in massive codebases, and catches its own mistakes. It’s also our first Opus-class model with 1M token context in beta.
English
Big drop for Codex users later today!
You can just build things.
English