Voice mode inside Claude Code is so nice. It... does a really good job at capturing tech jargon and while I'm still pretty skeptical of voice as a primary input medium in general, I have found myself using it more and more.show more

I'm just so happy that gyuvin is becoming more... and more confident in showing his vocals, his voice is so pretty 😭show more

noah's deep voice that only last for a minute... 💜 PLLI said that i sounds so cool when i'm speaking in deep voice so i've been keeping it since the self introduction 💙 oh nice concept~~ 💜 look at the comments! “the deep voice is really nice” “sexy~” 🖤 “you sound like you have a fever” 💜 I DON'T HAVE A COLD YOU KNOW! ❤️ HAHAHA 😂show more

A good bench vice does more than just hold... your workpiece for you, It could move mountains if you wanted it to. Mine cops quite a bit of misuse yet is still solid as a rock and does the job without fail every time.show more

Daisy’s new voice actress is doing a great job... as her so far! 🌼🌼🌼 Whoever it is, I give you a round of a applause and best of luck in future titles! #SuperMarioBrosWonder #PrincessDaisyshow more

💬: your voice is still hoarse 🧸: still just... a little bit, nearly… 👨🏻‍🦱: a sexy voice 😂 🧸: ah yes, a sexy voice. It is said that they like me to have a cold, cause the voice is sexy. I told that to myself. But I don’t like to have a cold 😂 MIU NATSHA AT AMR POP-UP HK #AMRDeSaisonXMiu #MiuNatsha #หมิวณัชชาshow more

So as it turns out, staying up all night... and morning not sleeping AND generally not taking care of myself while I'm outside is, in fact, not a good life plan! I got sick so I'm gonna slow down on working on him for a couple daysshow more

I have more than 2k hours in this game... and I still find new things 😭 Today it was this pretty glitter flower I found while chests hunting ཐི infinitynikki ❀ untiltideends ཋྀshow more

We (Claude and I) made a new package: voxmlx... It's an MLX implementation of Mistral's Voxtral mini realtime speech recognition model. It supports streaming audio and runs pretty fast on a laptop. To use it, simply: `uvx voxmlx` Also I did not write a single line of code for this package. Every line of code was written by Claude Code. More on that in thread.show more

Hey... so... Claude Code is really good at design??... 👀 This was a ONE SHOT PROMPT. 🤯 We always asked Lovable to build "Design System" pages for our apps and they were always meh. We asked Claude Code to take a swing at it just based on our logo, a font, and brand colors. This is... really, really good for a one-shot prompt.show more

I think the error in the dummy is correct.... I recorded it myself and tried playing it, and tech roll was possible. I'm glad it wasn't a terrible bug..show more

i built a plugin that lets Claude Code continuously... self-improve ie, while you work, it notices patterns and asks to upgrade itself by absorbing them as new commands, skills, or even agents so the more you build together, the more capable it becomesshow more

BREAKING: Anthropic just dropped Opus 4.8—and it is a... MONSTER We've been testing for about a week Every 📧 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 📧:show more

Why does Google Antigravity have voice input for Gemini... models but not Claude? Is this just a feature limitation or is Google intentionally pushing users toward Gemini?show more