Nithin

@RiverNotFlowing @browserOS_ai Yep, @browseros_ai has vertical tabs too

@ThatNithin @browserOS_ai Vertical tabs? Atlas has them.

if you are on windows and have chatGPT subscription, try @browserOS_ai

@browserOS_ai browseros.com/blog/bring-you…

we partnered with @Kimi_Moonshot to give all @browserOS_ai users 2 weeks of free kimi k2.5 usage it's a great model sir

partnered with @Kimi_Moonshot — all BrowserOS users get 2 weeks of free kimi k2.5 usage. no API key needed.

@BrendanFoody Seems like browser the right platform for capturing this? > a platform that understands what every person knows, what they’re capable of, and where their expertise can create the most value.

i've been using cmux for the last few days, great product!

@_catwu curious to try it out on chromium codebase... will it work on 15M lines of C++?

@antirez codex at $20 vs claude code at $200 is the most dramatic value arbitrage in dev tools right now and nobody's talking about it

The 20$ codex plan is worth more than the $200 Claude Code plan.

the gap between open and closed models is shrinking faster than anyone expected. this is gonna get interesting

US AI labs: "we believe in open source*" (*terms and conditions apply). China: here's the weights. open source is eating the world #openSourceFTW

this matters way more for voice products than chat. in voice every 200ms search would be game changing.

the painful truth: ai writes code faster than you can describe what you actually want it to look like

@Hartdrawss We've been shipping MCP servers for BrowserOS and the Skills pattern is huge for us. The folder-based approach makes it way easier to version control agent behaviors. Been using it for browser automation workflows.

Anthropic released 32-page guide on building Claude Skills here's the Full Breakdown ( in <350 words ) 1/ Claude Skills > A skill is a folder with instructions that teaches Claude how to handle specific tasks once, then benefit forever. > Think of it like this: MCP gives Claude access to your tools (Notion, Linear, Figma). > Skills teach Claude how to use those tools the way your team actually works. The guide breaks down into 3 core use cases: 1/ Document Creation Create consistent output (presentations, code, designs) following your exact standards without re-explaining style guides every time. 2/ Workflow Automation Multi-step processes that need consistent methodology. Example: sprint planning that fetches project status, analyzes velocity, suggests priorities, creates tasks automatically. 3/ MCP Enhancement Layer expertise onto tool access. Your skill knows the workflows, catches errors, applies domain knowledge your team has built over years. The technical setup is simpler than you'd think: 1/Required: One SKILL.md file with YAML frontmatter Optional: Scripts, reference docs, templates 2/The YAML frontmatter is critical. It tells Claude when to load your skill without burning tokens on irrelevant context. Two fields matter most: - name (kebab-case, no spaces) - description (what it does + when to trigger) Get the description wrong and your skill never loads. Get it right and Claude knows exactly when you need it. The guide includes 5 proven patterns: 1/ Sequential Workflow: > Step-by-step processes in specific order (onboarding, deployment, compliance checks) 2/ Multi-MCP Coordination: > Workflows spanning multiple services (design handoff from Figma to Linear to Slack) 3/ Iterative Refinement: > Output that improves through validation loops (report generation with quality checks) 4/ Context-Aware Selection: > Same outcome, different tools based on file type, size, or context 5/ Domain Intelligence: > Embedded expertise beyond tool access (financial compliance rules, security protocols) Common mistakes to avoid: >. Vague descriptions that never trigger > Instructions buried in verbose content > Missing error handling for MCP calls > Trying to do too much in one skill The underlying insight: > AI doesn't need to be general-purpose every conversation. > Give it specialized knowledge for your specific workflows and it becomes genuinely useful for work.

@IsomorphicLabs google is somehow doing everything everywhere all at once

Today we share a technical report demonstrating how our drug design engine achieves a step-change in accuracy for predicting biomolecular structures, more than doubling the performance of AlphaFold 3 on key benchmarks and unlocking rational drug design even for examples it has never seen before. Head to the comments to read our blog.

@Yuhu_ai_ looking for a $100M seed round soon, all the best for next chapter!

I resigned from xAI today. This company - and the family we became - will stay with me forever. I will deeply miss the people, the warrooms, and all those battles we have fought together. It's time for my next chapter. It is an era with full possibilities: a small team armed with AIs can move mountains and redefine what's possible. Thank you to the entire xAI family. Onward. 🚀 And to Elon @elonmusk - thank you for believing in the mission and for the ride of a lifetime.