Varun Jain

Well, it’s important that you find Koramangala in your life. Or that it finds you.

generalists are about to win big If you understand a little of tech, business, and people, and can connect everything fast. you're sitting on a goldmine right now.

One of the biggest lessons thus far in building AI agents is you have to be brutally unsentimental in your architecture. The models get better and better at handling things you previously built scaffolding for, you need to ruthlessly jettison your prior tech to get those new performance gains. The rough loop of building AI agents looks something like: 1. Build a bunch of systems around the LLM to ensure that the agent can solve specific tasks very well 2. The model capabilities dramatically improve, rendering many of those systems redundant or even harmful 3. Remove prior scaffolding to get the new performance gains from the agent 4. New capabilities emerge in the models that let you solve a new set of much harder problems 5. Go back to step 1 For instance, in our new Box Agent, from the moment we designed the original architecture to the ultimate release, we had to evolve multiple components of agent harness simply because some parts were creating unnecessary constraints for the agents as models improved. The models continued to get insanely good at more complex reasoning, improvements in using search and other tools, writing code on the fly for new capabilities, improving context window performance for accuracy, and more. Many of the mitigations we put in place for the Box Agent (like to appropriately find data that users were looking for, or ways of chunking text to deal with context window limitations), eventually meat we got lower quality results or meant we were overfitting for specific use-cases, as soon as the models got better. The main lesson is always make sure you’re taking advantage of the frontier capabilities and don’t become nostalgic around the tech you’ve already built.

@kevinrose @garrytan Super helpful. Wrapped a layer on top of it to create initiative/project/ticket on linear and then run gstack skills to determine if what you are building needs ceo review, design review, eng review etc. Supercharged dev flow which has elevated decision making

I’ve been pretty skeptical of AI “brainstorming” partners - they tend to default to the south park "loving this idea...". That said, @garrytan’s gstack has been genuinely useful, one of the best tools I’ve tried.

@ku1deep @last9io Insane! Who are the unsung heroes in the team responsible for scaling this system reliably? Would love to learn.

I don’t brag about work a lot but we have a pipeline doing ONE BILLION RPM right now without breaking the customers bank account. Just another Saturday. I am intensely proud of @last9io

Wow, I totally disagree with this statement. At the current state, AI actually amplifies the developer to developer difference. If you were a 10x developer, you had good ideas + architectural clarity, this is a brutal advantage when using AI. Steering is a fundamental part of today's AI development.

We need to bring back courtyards. It was such a stupid idea to follow western modern minimalist architecture inspite of us having these.

A lot of people have been asking if this can be done for their dogs and for people. I'm speaking with everyone involved to see what is possible here. If you would like to be involved, please complete the following Google form: bit.ly/4bkaowg

this is actually insane > be tech guy in australia > adopt cancer riddled rescue dog, months to live > not_going_to_give_you_up.mp4 > pay $3,000 to sequence her tumor DNA > feed it to ChatGPT and AlphaFold > zero background in biology > identify mutated proteins, match them to drug targets > design a custom mRNA cancer vaccine from scratch > genomics professor is “gobsmacked” that some puppy lover did this on his own > need ethics approval to administer it > red tape takes longer than designing the vaccine > 3 months, finally approved > drive 10 hours to get rosie her first injection > tumor halves > coat gets glossy again > dog is alive and happy > professor: “if we can do this for a dog, why aren’t we rolling this out to humans?” one man with a chatbot, and $3,000 just outperformed the entire pharmaceutical discovery pipeline. we are going to cure so many diseases. I dont think people realize how good things are going to get

how do you produce urgency in an organization, at scale? it seems really stupid but "commit to an insanely aggressive deadline and pretend like it won't slip, then let it slip" is the best solution tbh. Elon does this constantly

@dexhorthy If you have profits, you show profits. If you don’t, you show EBITDA. If you don’t have that, you show revenue. If there’s no revenue, you show users. If no users, you show app downloads. If nothing, you show token burn.

us: we are struggling to figure out the best way to use coding agents, we don't have clarity yet everyone else: our team is moving at speeds unheard of, all our PRs are ai generated, we've cleared 6 years of backlog man we must really suck huh

The people getting the most out of AI tools aren't juniors. It's people with a backlog of ideas they couldn't build because the implementation cost was too high. Suddenly that cost has dropped 10-50x.

My 3yo wanted to use the computer like me so I made him his own terminal. He types whatever he wants, it responds with fun messages. No external deps, no ads, just keyboard practice and cause-and-effect thinking. He thinks he's hacking. github.com/meimakes/tiny-…

The opportunity cost of employees who need to be told what to do has gone through the roof.

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

@JohnONolan @Ghost Congrats @JohnONolan

Today @Ghost crossed $10M ARR, as a bootstrapped non-profit foundation building open source software. Indie publisher revenue earned with Ghost now ~$130M, and accelerating. The world of technology is shifting rapidly, and so is the world of media, creators and journalism. It's hard to keep up with, and even harder to predict. My strong belief, though, is that open software that you own and control is going to be even more important and relevant in the future than it is now. So we're going to keep building it.

Claude or Codex?

@nickgraynews SendPost can help: sendx.io/sendpost

SendGrid is disabling their webhooks for 3 weeks 😭 I loved using the SendGrid API but this is untenable When will Cloudflare do emails please??

@soumitrashukla9 @tszzl Hands down. Have been using Codex for interesting problem statements and it just gets a ton of edge cases which CC never gets despite detailed plan mode / architecture etc. Quality of code is also better with lot less bugs.

I have to say the OpenAI folks completely cooked with the Codex App. There's nothing like it and CC has a lot to do to catch up, as their current offering simply doesn't cut it. It is not even in the same league. Congrats to my friends @tszzl