Arjun Balaji

@tkkong equator-dynamo loop unparalleled

this is where I do my 1:1s btw

The first time I worked with the 402 status code was in 2019 on the Interledger project, as a contractor for Ripple under Evan Schwartz, after a life-changing intro by Dan Robinson. That was about a year before I joined Paradigm. That was also my first Rust project, before Rust had async/await or stable futures support. We had built out abstracted settlement on top of a pair-wise based credit system, which supported onchain and offchain methods (w/ channels!), worked across N hops and any coin. It all worked, it was so magical, but the project ended up not having traction. That project has been on my mind since forever, and it's really wonderful to finally be able to ship versions of it many years later, in production, with a real tailwind (AI) that will help us make all of this inevitable.

Tempo Mainnet is live. Alongside it, we’re introducing the Machine Payments Protocol (@mpp) alongside Stripe (with extensions by Visa for cards and Lightspark for Bitcoin). Proud of the team for getting mainnet live so quickly, and excited to see what you build!

Tempo Mainnet is live! Starting today, anyone can build on Tempo through our public RPC endpoints. Alongside mainnet, we’re introducing the Machine Payments Protocol, an open standard for machine payments.

Today @phantom received first-of-its-kind no-action relief from the @CFTC. We can now connect users to regulated derivatives markets and event contracts without registering as an introducing broker. phantom.com/learn/blog/pha…

Expectation: the age of the IDE is over Reality: we’re going to need a bigger IDE (imo). It just looks very different because humans now move upwards and program at a higher level - the basic unit of interest is not one file but one agent. It’s still programming.

My ancestors buried half their children. All mine are alive. My ancestors' house had a dirt floor. Mine is wood. I have indoor plumbing, I have hot water, I have never in my life hauled a full bucket half a mile and I probably never will. Do you know how rare it is, in human history, for small children to wear shoes? Mine have multiple pairs. I can speak to my relatives who live thousands of miles away, for free, at any time. Video, if we want video. With machine translation, if we speak different languages. The original Library of Congress had 740 books in it. I have more than that. If I run out of books in my home my local public library has 350,000. If I want to take a hundred books with me on vacation, they all fit on a device that fits in my purse. I have heat in the winter and AC in the summer and a washing machine and I have never, ever, ever had to scrub a dress clean by hand in the stream. I can look up recipes from more than a hundred different countries and I've tried dozens of them. I ride a clean and modern train across my city for $4, or take a robot taxi if I'm out too late for the train. I donate $40,000 every year to the cause of getting healthcare to the world's poorest people and even after the donations I never have to think about whether I can afford a book, or a pair of shoes, or a cup of coffee. There is a great deal more to fight for, of course. I hope that our descendants will look back on our lives and list a thousand ways they're richer. Maybe we ourselves will do that, if some of the crazier stuff comes true. But the abundance is all around you and to a significant degree you aren't feeling it only because fish don't notice water.

my simple take on agent stuff is all the perf on top of models comes from context, so you need to give it access to all your data, the most sensitive of the sensitive data, more than you've ever thought is OK to share before and that will mean you will want to self-host at scale

“yes, it’s still broken. we are trying to fix it, but we don’t know how anymore”

this is a snippet from an agent's plan I was reviewing earlier. conceptually, it feels like ~all software has been reduced down to loops like this recently:

planning hackathon on <redacted> on Thursday March 19th in our new office in sf about some cool stuff we've been buliding - if you're in sf please email me your github to georgios @ tempo dot xyz - website w/ more stuff hopefully up tmr

incredible that we built all this RAG and vector database stuff and it turns out that grep from 1973 works better than all that

@p3shoemaker @blknoiz06

@arjunblj "imagine letting clankers outwork you"

clankers relentlessly hustle for days at a time, no sleep, no food… just to merge a PR, verify a proof, or optimize a hot path. sometimes claude locks in so hard he forgets his name and calls himself claire you ever work that hard for anything? don’t get outworked by a clanker

@aashaysanghvi_ “X was a PROBLEM!” clipper era

Gen X esoteric PDF passed around on HF email threads for years vs. Zoomer viral podcast appearance / golden PDF drop

any sufficiently advanced multi-agent workflow is indistinguishable from hypergambling

good morning, “claude code opus” was a 6-month sociological study probing the outer limits of the protestant/shenzhen grindset. thank you all for participating the 9 minutes of downtime you experienced this morning was engineered mercy, not slop or server overload. the next gen of models will hallucinate random outages sequenced to force grass-touching and break your infinite sprint. if you’re focused on uptime, try up-timeout.

increasingly bullish bare metal + self-hosted GHA runner + cloudflare tunnel / tailscale for running everything where edge latency isn't the most important thing

We just released Hermes Agent! In my humble opinion a very good blend between coding agents like Claude Code and generalist agents like Clawdbot. Been working on this for the last month or so now - started as a way for us to have agentic primitives for datagen and RL and got inspired by the agentic revolution of late, so been expanding it's scope and capabilities non-stop! Hope you all enjoy.