Building @PortkeyAI - the production platform for AI teams. 1st OSS project crossed 10k stars! passionate about LLMs in prod
Joined September 2008
- Tweets5.8K
- Following1.4K
- Followers3.4K
- Likes6.7K
Fun stuff with @amazonIN today
It delivers a wrong product to me which lists to be 10 day returnable.
I submit a return request.
The website says - sorry not possible.
So I call the customer care center and they confirm that I’m right a wrong product was delivered.
Phew. But..
Now they need a week to set up an inquiry.
For what?
To see what exactly happened.
Meanwhile, what should I do?
“Sir, that I don’t know”
Can I order again from Amazon?
“sir I can’t say anything there. inquiry will decide”
Felt like I was back at UCO Bank in Pilani in 2007 🤣
I have a feeling we need to install firewalls per house now.
I’m going to get one soon next to the router which restricts outgoing access proactively.
Wouldn’t want a hacker to get access to my fridge!
Rohit Agarwal retweeted
Today we're reintroducing @quivlyai, backed by @ycombinator.
Quivly is the AI workforce for everything after the sale, built especially for companies with usage-based pricing.
Teams using Quivly take customers live in 7 days instead of 30, then expand them 4.3x on average.
Our agents turn kickoff calls into launch plans, chase blockers, catch risk and expansion signals, and have the full account story ready at renewal.
Closing the deal is just the beginning. Quivly handles everything after that.
This is a big fallacy in token cost conversions today.
With caching in effect and model switching at play, blended costs are usually between 0.6 to 1.1 dollars per million tokens even for frontier usage.
poteto's cursor profile is public. She's used 1.5T tokens in the last 30 days.
Assuming an avg rate of $8/M that's $384k/day or $11m. In the last 30 days. Per year thats $132M.
Let's assume Cursor has some insane deal with Anthropic and gets 90% off. That comes out to $38k/day or $1.1M in Sept/Oct.
$13m will get me 26 sassy staff-level all stars for $500k/yr
Readers added context they thought people might want to know
The Cursor profile at cursor.com/@lauren shows 1.5T tokens used. Cost estimates at $8/M do not account for prompt caching common in agent coding, where cache reads are billed at ~10% of input rates per analyses of Anthropic pricing. This results in lower effective costs.
cursor.com/@lauren chudi.dev/blog/claude-pr… carlosaragon.online/blog/anthropic…
Rohit Agarwal retweeted
Introducing Graphical.
It's a simple, powerful, and fun tool to design visual languages, style components, and work with coding agents to create interfaces that look memorable and feel unique.
I hope you'll check it out at graphicalui.com!
2900 fixes is the bar for a minor release now.
Bun 1.4
- Fixes over 2,900 GitHub issues
- +1,517 tests from the Node.js test suite
- Reduces idle CPU by 5x
- Reduces memory usage by up to 35%
- Starts up to 50% faster on Linux
- Rewrites Bun in Rust
Thank you everyone who contributed since Bun 1.3!
bun.com/blog/bun-v1.4
Rohit Agarwal retweeted
bribes.fyi/ - report bribes demanded from you.
Sqlite is winning. I like that!
Introducing celld: a self-hosted, distributed Durable Objects and Workers implementation
- celld = V8 + S3 + SQLite + LTX+ Tokio
- programmed with exactly the Cloudflare Workers/DO JavaScript APIs and config
- order of magnitude cheaper at scale
- writes are durable before they're acknowledged, RPO=0
- only depends on an S3 compatible bucket - no other infrastructure
- ~4 MB memory per cell instance overhead
- hibernated cells cost ~nothing, just their S3 storage
- open source, Apache 2 licensed
Rohit Agarwal retweeted
The new stateless MCP specification has rekindled my interest in MCP, and inspired some new projects, including mcp-explorer and datasette-mcp simonwillison.net/2026/Jul/3…
Rohit Agarwal retweeted
We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them.
