Anubhav Gupta

AGENTS FTW! Cofounder @TralgAi (Launching soon!), Ex- @Google Ads, IIT-BHU'23 building the future of financial markets in an agentic world

[Anubhav Gupta @anugup]

@nishanth_who curious to know what you were building

[lauren @poteto]

i feel like swe interviews could probably collapse into just 2 technical rounds:

• system design (how well can you articulate your ideas, do you actually know how to engineer something)
• onsite project to build a real thing with agents (can you translate your intent into high quality outcomes)

everything else we used to ask is no longer necessary

[Anubhav Gupta @anugup]

@dominikmartn Really cool UX

[lauren @poteto]

volume does matter
look, i get it. if you were an engineer before agents came along, you're rightfully skeptical about lines of code and number of PRs being used as a metric for any kind of productivity. and i agree! or at least, i used to. for ease of explanation i will talk about this from the perspective as being an engineer on a large team of at least 50.

volume didn't matter before because we focused on impact. you could have high impact even with a few PRs: for example you could make a one line config change and save the company millions of dollars.

but before agents, the times where i saw volume come into the conversation were for the outliers. on the negative end you might have someone who is struggling to perform, on the other end you might have someone who was a "coding machine" archetype. a coding machine was someone who could just lock themselves in a room and emerge with a stack of PRs that solve a huge number of problems. so volume did matter, but only at the tail ends of the distribution, and combined with impact.

if you've ever worked at a large tech company before, you'll get what i mean. the thing about agents is that big tech co problems are now small-medium co problems as well.

how do agents change this calculus? well, everyone now has the ability to become a coding machine. you have incredibly capable frontier models that can write code better than any of us, at a rate much faster than we can. in this world, if you're still producing the same number of PRs as before, why wouldn't you pause to wonder why you're not being more productive? alien intelligence is here, and yet you can't outship a human coding machine?

this brings me back to why i keep talking about trust (https://t.co/7fzYZV8LGH). if you haven't put in the work to trust your agent's output, it is very difficult to scale up your productivity.

and yes, this approach does require more tokens, but i think about this in terms of cost per intelligence. before agents, this cost was very high - you needed to hire many software engineers with high 6 figure salaries to do the work. tokens are still expensive today, but are likely to get cheaper over time (https://t.co/gTBZx7pl14) factoring in the cost of intelligence. what looks exorbitant today will likely be affordable in 6 moths to a year. a single engineer with agents can do the work of tens if not hundreds of engineers, at a fraction of the cost.

the reality that i don't think has hit yet is that job of the software engineer has truly changed. our job is not merely to produce software any longer (well tbh it was never only about the code, but bear with me for the sake of the explanation), but the machine that writes the software. this idea of a software factory, or a Michelin kitchen as i like to call it, is still a topic of research. and it's the type of stuff i like to share, not to flex, but to show you what's possible when you put a lot of rigor into using agents at scale

[Anubhav Gupta @anugup]

@ttyler What does your webapp do?

[Anubhav Gupta @anugup]

@Oldnoob007 congrats bro! its worth every single penny

[Anubhav Gupta @anugup]

@claudeai Claude is cooking

[Anubhav Gupta @anugup]

Really love this. For those of us who are building AI products using Anthropic's plans and Claude code, and then buying credits as well from Anthropic, this is a real good deal.

The way this lands along with Haiku 5.5 and other 5.5 series is that Anthropic is trying to increase API usage among folks who were earlier using cheaper models for their product's inference.

These monthly credits directly bring those developers back to Anthropic, and while models are easy to swap, most people dont have the time to evaluate every week whether the newest model works out better in their product.

[ClaudeDevs @ClaudeDevs]

We’re rolling out monthly Claude Platform API credits for Max and Team plans:

Max 5x: $100
Max 20x: $200
Team: up to $500, pooled

Works on any model, including Haiku 5.5, in your code or third-party harnesses.

How it works and full terms: https://t.co/qmWL6xVGwr

[Anubhav Gupta @anugup]

@iPritamX fingers crossed, hopefully its fast

[Anubhav Gupta @anugup]

If you have still not applied: apply here: https://t.co/LbDXEcnQeC

[Anubhav Gupta @anugup]

Just got my invite to the OpenAI DevDay in blr. Cant wait to see what everyone else is building..

[j🫪e @0x_Osprey]

ICANN released the new domain applications

Google, Meta, and OpenAI going for a lot

Anthropic not so much

[Anubhav Gupta @anugup]

@alexandr_wang heard its really good. when is it coming to india?

[Anubhav Gupta @anugup]

@ajinkyabhagwat @grok where to get this train data

[Anubhav Gupta @anugup]

@aicodeking Haiku, GPT-Mini, On device models are smartphones. They are really new and we dont know how to use them well, but the one who figures out the perfect usecase will win.

[Anubhav Gupta @anugup]

@jhalakkgupta Looks like someone just kept pressing the suggested words on top of the keyboard.

[Anubhav Gupta @anugup]

@poteto @thsottiaux @grok what is the probability that these two are in love?

[Anubhav Gupta @anugup]

@GauravGupta_RE 2000cr

[Anubhav Gupta @anugup]

@code_kartik not free, but been using @typelessdotcom and it has been a delight

[Anubhav Gupta @anugup]

@arsh_goyal Sarvam maybe