Ananth Menon

Product @Cradlewise
Claude Code and Hermes Stan
Real Madrid & Bengaluru FC

[Ananth Menon @ananthm_10]

@rileybrown @cwRichardKim @Anthropic Add remote control to the mix and the loop is complete! 🙌🏻

[Ananth Menon @ananthm_10]

@iuditg 60db

[Ananth Menon @ananthm_10]

@mehulmpt Been there but decide to wake up one day and try the code on the desktop app. Haven’t gone back to the terminal in a week. (Normie, I know)
Remote control + other QoL improvements really come together with the new models.
If you have tried it and still prefer the CLI, why?

[Ananth Menon @ananthm_10]

QoL improvement!

[Daniel Nguyen @daniel_nguyenx]

To whoever fixed the remote control functionality in Claude Code: thank you. You’re my hero 🥹

[Ananth Menon @ananthm_10]

The $100 Claude subscription is basically unlimited frontier intelligence. Insane deal for knowledge workers!
The x.5 releases have always been bangers from Ant! 🔥

[Ananth Menon @ananthm_10]

@VincentBuilds @trq212 Where are these settings available??

[Tom Dollimore @FPL_Barbossa]

Amazon apparently already filming a new Man City series.

All for Nothing.

[Ananth Menon @ananthm_10]

@manavvnotop @ao_build Very interesting! Will check them out over the weekend! Thanks!

[Ananth Menon @ananthm_10]

@manavvnotop With the latest set of models, Fable, Astra and now Opus 5.5, treating them as “first mates” and asking them to only delegate and execute via subagents has help significantly reduce context bloat for main conversation + speed up tasks with parallelization + reduce token costs!

[Ananth Menon @ananthm_10]

@manavvnotop My use case for subagents is slightly different too I guess.. I use them more for broad research. Each subagent goes deep on a vertical (I ask the main agent to ensure the tasks have minimal overlap).

[Ananth Menon @ananthm_10]

@manavvnotop Interesting perspective!
While exploring codebases, I'd usually use subagents to explore specific parts and become
"experts" at those. Then the main agent (acting as orchestrator) can gain a full understanding of the codebase and the interactions with fewer tokens!

[Ananth Menon @ananthm_10]

💯

[Mckay Wrigley @mckaywrigley]

opus 5.5 = personality of opus 4.6 that we all *desperately* wanted back + the intelligence & taste of fable 5.1.

and a 25% usage bump!

i honestly don’t really see a reason to use another model right now?

s-tier release.

[Claude @claudeai]

Opus 5.5 communicates more naturally, addressing some of the most common feedback we heard on Opus 5.

It puts the most important information up front and follows the writing rules you give it, which makes long sessions easier to follow.

[Ananth Menon @ananthm_10]

GPT 6 Sol and Luna must be great, but next over the next few days I’m looking forward to more time with Opus 5.5! Giving Opus 4.8 vibes with the intelligence of Fable! Anthropic is so back!

[Ananth Menon @ananthm_10]

What a day! 🥳🥳

[Claude @claudeai]

One more thing: we’re increasing five-hour usage limits on Pro, Max, and Team plans. We’re also providing subscription users a rate limit reset, which you can save and use whenever you choose.

[Mayank Jain @jainmayank_943]

I'm scared of what Instinct will charge when it starts monetizing. The capex of training it to my taste and preferences means it'll be hard to let go. And I'll hate to pay a few hundred dollars a month.

[Ananth Menon @ananthm_10]

@DarrylRMFC Trent was terrible

[Stop That Football @stopthatfooty]

Stop that Benzema.