Rashmin | eigi.ai (@rashcasm) header
Rashmin | eigi.ai (@rashcasm) profile picture

How lean teams run on AI? @eigiai | ex-Quant | @solanaturbine

Singularity
Joined December 2024
Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)Photo by Rashmin | eigi.ai (@rashcasm)
Rashmin | eigi.ai retweeted
The dominant intelligence of the next era will be artificial. The post-AGI economy will look drastically different from the current social contract of capitalism. We’re on a mission to make sure Humanity wins. Come join us at eigi.ai. We’re growing our tribe.
6
9
147
Rashmin | eigi.ai retweeted
something that keeps bothering me is how some people see slop as something that is happening to them, like they're some kind of helpless bystander powerless to do anything about it excuse me but you are a software engineer, you literally learned how to make sand think and make computers do your bidding?! and now you can't do anything about it? please the 2 things you should know to cut through all the noise: 1. you need to give your agent a way to verify its own work (i just posted about this so won't rehash) 2. your codebase is memory the 2nd is not new either, we have always had lint rules, compilers with good diagnostics and strong type systems, LSPs, etc to help us write better code. there is no difference when agents write the code instead, you just need more of them, and stronger ones. forget rules and skills. you can add those later. yes, your codebase is a form of memory to agents! agents love extending what already exists. so every nit and every annoyance you've ever seen, every mistake and bad pattern you observe from agents, needs to turn into a constraint, or the agents will just keep repeating those same mistakes like a virus in your code. then you keep observing and repeating this process until your codebase is locked down enough that even agents with little context can one shot a high quality PR. an even better direction is to refactor/rewrite your code such that agent anti-patterns become categorically impossible. use type systems to your advantage, use libraries/frameworks that reduce the architectural search space, or heck, create your own framework like we did for grok bot and design high quality primitives and well thought out APIs
the slop conversation is so one sided, it's not just that you can produce more code you can also observe, debug, and refactor more code even if the code is slop you have such good tools to deal with it. even if you write code manually, it's still 100x easier to maintain it
231
339
103
4,621
336,774
Rashmin | eigi.ai retweeted
Here's my take on what a software factory really is This is my talk from @aiDotEngineer NYC, and I decided to record a version for everyone to watch on X. tl;dr - software engineering is becoming factory engineering, and there's new work (especially factory benchmarking) that engineers should start focusing on.
37
89
18
1,066
935,832
Rashmin | eigi.ai retweeted
if you are a programmer and you'd like to start a company it is helpful to internalize two big weaknesses you have 1. your instincts for anything outside programming are terrible. everything you believe is likely 100% backwards 2. you've always been treated like the smart person in the room so it will take you a very long time to understand #1 for me personally it took ~ 10 years before i started to be able to unwind this
290
454
76
8,963
409,274
Rashmin | eigi.ai retweeted
just submitted rpc-stats to @colosseum Frontier. the idea is simple: every RPC provider claims they're the best at landing transactions. none of them can prove it. so we built a system that tests helius, triton, and alchemy every 30 seconds. on-chain verified via geyser. live public leaderboard. no marketing. just data. built with @Subhdotsol 🤝
5
8
2
28
1,441
Rashmin | eigi.ai retweeted
You're in a Tier 2,Tier 3 college Cool. Nobody cares. You either build your way out or cry about placements for 4 years. No one's coming to save you. Not your HOD, not your "training & placement cell" It's just you, internet, and how bad you want out.
10
23
2
304
19,217
Rashmin | eigi.ai retweeted
Perks of being in a Tier 3 college: - Surrounded by low ambition, you slowly start lowering your own bar too. (Most people are just there for timepass) - Life’s ultimate mission: get a banda/bandi. - “Skills?” unheard of. Semester exams are the only religion. - Attendance turns into an Olympic level competition. - Can’t go to hackathons… not because you don’t want to, but because you can’t find a solid team. - Try being serious and people hit you with: “Mehnat hi karni thi toh JEE mein kar lete.”
47
98
17
1,409
77,387
Rashmin | eigi.ai retweeted
Real
42
1,823
23
10,048
258,343
Rashmin | eigi.ai retweeted
If you have a moderately high iq you can probably learn anything you want today with ai if you put in the hours
148
195
42
3,819
83,650
Rashmin | eigi.ai retweeted
Met @kirat_tw. Talked about project / first job stuff. AI x Web3? Is it really useful? Is "HE" bullish on it? Use cases?
2
44
3,435
Rashmin | eigi.ai retweeted
Okay... here from me too
2
3
415
GM GM Guys... Guess what.. I was invited into THE BASE LAUNCH UPDATE PARTY... YES.. THE OG... @base app I'm using base from last 3 to 4 months, made content, played hell crazy mini apps... Now DEV being DEV.. Now I'll make the mini apps too :P love, BASE Nagpur @VidarbhaDao
7
4
44
1,586
Rashmin | eigi.ai retweeted
Just launched a new plaform for fellow evm-based chain devs, shaniai.tech No more hastle of connecting your frontend to your deployed contract from now on!😁 JUST NEEDS ABI and you get a NextJS/Vite project connected to your smart contract to download. @SohamPawar1866
7
7
20
580
Rashmin | eigi.ai retweeted
Well done. This is the way
And I made it 💪 But the best part wasn’t the project itself… It was the PROCESS - writing the LOI, user stories, architecture, refining scope, and taking it all the way from idea → devnet. The process was the real win. Thanks @solanaturbine for teaching me professionalism!
1
7
323
Rashmin | eigi.ai retweeted
flywheel @colosseum
11
9
1
100
5,281
Rashmin | eigi.ai retweeted
🤩 Had an awesome time at Pallotti College of Engineering. I was invited as a Judge for "Get OnChain" event organized by @rashcasm and @Haze_devp. Talked about @solana @SuperteamIN and how to get into web3 space. It was my pleasure to be a Judge with @Rish_w3b bhaiya, the OG. 😎
2
16
448
Rashmin | eigi.ai retweeted
Yesterday helped organizing @rashcasm a event named get on chain , sat in judging panel along with @Rish_w3b and @GemmMohil and even @CanisAl72 helped. #solana #SuperteamIN #getonchain
2
2
21
619
Rashmin | eigi.ai retweeted
ONLYDEVS 💜
9
30
15
152
11,161
Rashmin | eigi.ai retweeted
solana is the revenue chain. 1) solana generates more network revenue than any other chain. 2) solana apps generate more revenue than any other chain's apps. 3) three of the fastest revenue-growing businesses in human history were built on solana if you think TradFi capital is going to bring the next leg of growth, and you think TradFi will invest in things they understand (like revenue!), then you are legally obligated to be giga bullish Solana.
151
107
22
1,000
103,817
Rashmin | eigi.ai retweeted
I have two fundamental beliefs on why Solana. Keep in mind that I call them *beliefs* so they may sound hand wavy but I could prove them with data although they are not hard principles of physics. (some people have been asking in private and I can finally put them together in a coherent view) 1. In the long term better execution is a differentiator and technology is the only answer against moats. Solana is nothing if not focused on execution. Toly has successfully imbued all founders with startup maxi dogma of 🚢🚢🚢. That’s what kept us alive during bear and will keep feeding us. 2. Competition breeds progress, even if painful to the participants. Everyone is looking for a niche, counterpositioning, a better way to eat each other’s lunch. Only an open system like this allows competition to happen and breed progress. Closed systems with a kingmaker will be long term suboptimal. Long term is also key here, but we have to survive the short and medium term without getting killed on an unfortunate path, unforced error.
27
22
6
206
129,543