Vivek Nair
1.1K posts
Vivek Nair
@virtuallyvivek
MTS @AnthropicAI
Brooklyn, NYC Sumali Ocak 2012
674 Sinusundan646 Mga Tagasunod
Claude for Excel and Claude for PowerPoint now sync together seamlessly.
When you’ve got more than one file open, Claude shares the full context of your conversation between them.
Pull data from spreadsheets, build out tables, and update a deck — without re-explaining a step.
English
We're bringing the Claude in Office ecosystem closer together. Would love to know what you think. I poured my soul into this one and want it to feel great!
Claude@claudeai
Claude for Excel and Claude for PowerPoint now sync together seamlessly. When you’ve got more than one file open, Claude shares the full context of your conversation between them. Pull data from spreadsheets, build out tables, and update a deck — without re-explaining a step.
English
I’m so grateful to work here. Very proud of the tough, principled decisions we’re making here.
Anthropic@AnthropicAI
A statement on the comments from Secretary of War Pete Hegseth. anthropic.com/news/statement…
English
Vivek Nair nag-retweet
Vivek Nair nag-retweet
Simile is out of stealth!
At Simile, we have built the first AI simulation of society, populated by agents based on real humans.
We are building a foundation model that predicts human behavior in any situation, and a product that deploys it at scale.
Thrilled to be on this mission.
Simile@simile_ai
English
Not gonna lie but Opus 4.6 Max is an absolute beast. No model could one shot a neutral net playground like this before 🤯
Impressive.
🔗 visual-backprop-play-4snm.bolt.host
English
excited to share that i've joined Anthropic!
ive been a user of Claude / Claude Code for a while and have seen how fast the frontier moves.
i want to help people get the most out of Claude's rapidly expanding capabilities.
English
Truly privileged to have worked on this!
We're bringing Claude to millions of knowledge workers - beyond just coding.
If you're heavy in finance (or just an Excel nerd), let us know what you think.
Claude@claudeai
Claude in Excel is now available on Pro plans. Claude now accepts multiple files via drag and drop, avoids overwriting your existing cells, and handles longer sessions with auto compaction. Get started: claude.com/claude-in-excel
English
Vivek Nair nag-retweet
Finally, AI designs you can edit.
Moda - create brand assets on a fully editable canvas.
This is not another ChatGPT or nano banana wrapper.
We actually taught an agent layout, typography, and color. We gave it taste.
Use it for slides, social, infographics, e-books …
English
@arpit_bhayani Pretty good for a high-level description!
Causal masking is a pretty important omission though. I would focus on that to improve this further.
Each token should only be able to attend to prior tokens during auto regression.
English
Wrote an article on how LLM inference works. I spent about a week trying to build a clear understanding, and this is my distilled version of it. It covers the full inference journey: embeddings, attention, KV caching, quantization, and more.
I am no expert, but if you are looking for a starting point, this might help. Give it a read.
English
The best part about working on @modal is watching our customers literally build the future. Today, they’re using @modal for everything from generating AI music to powering real-world robots to curing cancer.
And yet, this is just the beginning. We have so much more to build.
If you like making computers do impossible things to solve user problems, please reach out. Especially if you are interested in low-level or large-scale systems, applied AI, GPU performance, delightful user experiences, security, or any combination of these.
Erik Bernhardsson@bernhardsson
It's true – @modal has raised a $87M Series B at a $1.1B valuation to advance the future of AI infrastructure. Thank you to @Lux_Capital, @Redpoint, @AmplifyPartners, and others. Now more than ever, AI demands a complete reinvention of traditional compute infrastructure
English
We spent the first year at @GentraceAI helping customers run traditional LLM evaluations. But we realized late last year that agents changed everything.
Agents don't just generate text - they take actions, make decisions, and interact across multiple steps.
Traditional "hallucination" checks can't evaluate whether your agent booked the right flight or resolved the customer’s support ticket correctly.
Old LLM observability tools were built for simple input/output prompts. They break in an agentic world.
For the last 9 months, we rebuilt Gentrace from first principles 🔥 Here's our new approach:
- Chat with your AI trace data using our agent to discover what's actually breaking
- Describe problems in plain English
- Our agent creates custom AI-powered monitoring columns that catch these failures across all future traces
Example: Instead of checking "factual accuracy," you can now evaluate complex behaviors:
- "Figure out if a user is frustrated with my AI agent in the customer support chat"
- "Detect when my agent takes more than 5 steps to answer simple queries."
We stopped measuring outputs and started measuring outcomes. Watch @dougsafreno break down how to solve agent observability with Gentrace. 👇
Doug Safreno@dougsafreno
Agents are significantly more powerful than standalone LLM calls. But, debugging them is a nightmare. You can trace their reasoning and tool use, but traces get huge and are impossible to parse. To solve this, we spent the lasts several months building Gentrace for Agents, which puts our own agents to work on yours. In Gentrace for Agents, you can: • Chat with AI to debug agent traces • Create smart monitoring columns • Build out tailored evaluations It’s like a giant AI powered spreadsheet over your trace data, with a Cursor-style chat sidecar. If it sounds a little meta, it is, but it is very powerful in practice. We recorded this video to show you how it works. Take a look, and let me know what you think:
English
Vivek Nair nag-retweet
Just released a 20 minute beginner tutorial making a flight tracker app with @alexcodes_ai
Check it out if you're just getting started!
English
@tibo_maker I use “llmcat” and custom ripgrep commands. Works like a charm.
x.com/virtuallyvivek…
Vivek Nair@virtuallyvivek
llmcat - copies multiple file into an LLM friendly format github.com/azer/llmcat/tr…
English
Stupid question:
How do you easily "dump an entire codebase" into a LLM chat?
Yam Peleg@Yampeleg
Gemini’s attention to detail is wild. Fed a ~400k token codebase and forgot about it Found the tab still open a day later Just for fun, I dumped the entire project again after refactoring it for a full day and asked it to guess my goal
English
@DanielEdrisian His setup isn’t ergonomic at all. Really makes you wonder how he got so cracked
English
Got Alex his own computer.
Now I can browse twitter in peace.
daniel@DanielEdrisian
Alex has gotten so good that I just let it rip in the background while I browse twitter. And it's annoying cause sometimes it focuses Xcode when it's trying to compile the app and I'm reminded that a he's working his ass off the whole time. While I'm just... chilling on twitter. What is happening????
English
This team's progress blows me away every time I see an update.
daniel@DanielEdrisian
🎉 Introducing Alex 3.0 Hey everyone! We're so excited to release Alex 3.0. Here's what's new: - Automatically compile & fix errors 🔁 - Auto-apply code ⚡ - Agentically 📦 Add SPM packages, 🌐 Search the web, run terminal commands, and review your code. - Local LLM support + our rewritten streaming logic 🔀 + much more! Check it out: (+🧵)
English
@wadefoster It's far easier to polish software when the friction is so damn low.
Animations, responsiveness, consistency in colors and padding are much more managed.
More tactical developer example: custom ESLint rules are much simpler to make.
English
This is what we see at Zapier.
While some use cases replace human tasks. Far more are doing things humans couldn't or wouldn't do because of cost, tediousness, or time constraints.
I'm bullish on innovation in a whole host of areas that would have been considered "niche" in the past.
Aaron Levie@levie
The biggest mistake when thinking about AI Agents is to narrowly see them as replacing work that already gets done. The vast majority of AI Agents will be used to automate tasks that humans never got around to doing before because it was too expensive or time consuming.
English
Repo here for instructions to install.
No dependencies. No TS transpilation. Pure JS.
github.com/viveknair/diff…
English
Press ⌘ + C twice to copy to clipboard. This mimics Superhuman's behavior with copying an email thread.
If you're selecting text elsewhere on the page, the extension does not activate.
English
I made a simple Chrome Extension to copy a Github PR diff into your clipboard.
This makes it dead simple to understand what's changed.
English