Vaibhav Gupta Profile
Vaibhav Gupta

@vaibcode

Followers
1K
Following
323
Media
74
Statuses
623

Making a programming language - BAML. @boundaryml, ๐Ÿฆ„ aitw podcast: https://t.co/g4CJWgOsrj prev YC, google, msft, deshaw, and other things

Seattle, WA
Joined September 2012
Don't wanna be here? Send us removal request.
@vaibcode
Vaibhav Gupta
29 days
I donโ€™t enjoy the syntax and tooling we use to building AI pipelines. Langchain/ai sdk/et all have never really felt โ€œrightโ€. No type safety, single language support, prompt is hidden until I buy some observability suite. So we made a thing https://t.co/eU06qqQHjK
3
2
23
@vaibcode
Vaibhav Gupta
2 days
Coding has always been way more about debugging than it has been about coding
2
0
15
@vaibcode
Vaibhav Gupta
4 days
โ€œHow many of you want to try this?โ€ Live demoing something new youโ€™ve been working for 3 months is scary. Youโ€™ve been drinking all the koolaid but until you put it in the hands of a stranger, you canโ€™t know. Yet, the @AITinkerers crowd came in strong. Im even more excited to
0
1
20
@vaibcode
Vaibhav Gupta
9 days
wow, anthropic finally caught up to realizing you can't just dump tokens via MCP and "it just works". Turns out its just software engineering. if you want tech facts like this (but 12 months earlier), check out ai that works podcast with myself and @dexhorthy every tuesday 10am
6
1
47
@tech_optimist
Prashanth Rao
11 days
6 months ago, we simply did not have folks talking about both @boundaryML (BAML) & @DSPyOSS in the same vein. Now, thanks to the awesome work of @getpy, we're getting content like this. There's value in understanding both tools! Do watch and share around ๐Ÿš€
7
6
37
@vaibcode
Vaibhav Gupta
11 days
We pushed vibe coding to the limit last 3 months. Itโ€™s not there yet. It makes you at most 50% faster. For small bugs and long tail tasks sure, but the meat and potatoes still require love and care. I suspected this, but itโ€™s good to know for sure.
0
0
10
@aomi_labs
aomi labs
12 days
Our goal is simple: Process user intent into transactions without bespoke integration of DeFi SDKs. Just plain, direct interaction with blockchain nodes. But this isn't just a chatbot task. It requires resolving addresses, building calldata, and computing gas & slippage
2
2
7
@vaibcode
Vaibhav Gupta
14 days
what if openai is more comcast than msft? everyone wants internet, the company doesn't matter. everyone wants a model, the company doesn't matter? or does it?
2
0
2
@vaibcode
Vaibhav Gupta
17 days
even worse, the saddest outcomes usually are for the team, not the founders in these situations
0
0
0
@vaibcode
Vaibhav Gupta
17 days
most first-time founders don't understand the risks of raising. you ego battle for big raises at big valuations. that makes soft landings harder. If you want more landing options, raise at smaller valuations, or grind longer, or get luckier. there's no such thing as free money
@rohitdotmittal
Rohit Mittal
17 days
you raised $8M at a $40M valuation you ground it out for 4 years and got to $2M ARR while burning money or breakeven at bast solid product. customers renew. team is competent some money still left in the bank you have revenue. you have profit. you just dont have the growth
1
1
11
@vaibcode
Vaibhav Gupta
19 days
i wish i could programmatically control my homescreen
1
0
3
@vaibcode
Vaibhav Gupta
19 days
I know there are scenarios such as cofounders leaving, etc, but if you're playing for that game, then you're either not winning hard enough, or your building something that both of you aren't into.
1
0
1
@vaibcode
Vaibhav Gupta
19 days
if you're using that 1% to make the difference, the business is already fucked
@garrytan
Garry Tan
20 days
From a lot of experience with lots of founding teams: 50/50 deadlock cap tables are considered harmful
1
0
4
@vaibcode
Vaibhav Gupta
20 days
ffi bridging rust <--> rust is cruel and unusual punishment. But anything to make a users life better.
2
0
14
@vaibcode
Vaibhav Gupta
25 days
smart man
@aaronvi
Aaron Villalpando
26 days
It's hard for me to recommend using python to someone new to code, even with AI help. There are still too many ways to shoot yourself in the foot. The main one is not enforcing any types. You have to explain to this new user the concept of typing.
1
0
7
@vaibcode
Vaibhav Gupta
26 days
More people talking about unwrap and rust, than those impacted by cloudflare going down
1
1
10
@vaibcode
Vaibhav Gupta
28 days
day 0. @antigravity is a dope name btw. thoughts on it coming later this week!
@_mohansolo
Varun Mohan
28 days
Excited to launch Google Antigravity, our next generation agentic IDE, now powered by Gemini 3!
1
0
12
@antigravity
Google Antigravity
28 days
Meet Google Antigravity, your new agentic development platform. An evolution of the IDE, it's built to help you: - Orchestrate agents operating at a higher, task-oriented level - Run parallel tasks with agents across workspaces - Build anything with Gemini 3 Pro.
620
2K
13K
@vaibcode
Vaibhav Gupta
29 days
AI/ML maybe for training models. Reliable agents apps can't be built on python. No enforced type-safety. Lack of multi-line lambdas. Ever tried streaming w/ python? Its just not designed for it.
@ennycodes
๐•ฏ๐–Š๐–›๐•ฐ๐–“๐–“๐–ž โŸ
1 month
What's the point of Rust?? ๐Ÿค”
4
0
4
@Vector76
Jamie
29 days
@vaibcode So far it has been a breeze, and between linter and AI the newl language is a non-issue. I had some hiccups with error handling, where a provider rate limit produced parse errors due to empty/missing response field. I tried fallback too. But overall great.
0
1
1