Simplifying US Taxes with AI, Prev. @ Peerlist, Verak

Indiranagar, Bengaluru, India
Joined June 2014
We've been building Kyoto, an AI for your taxes. It scores 100% on TaxCalcBench v2: all 50 test cases correct across federal and state returns, on every scored line. The best frontier model scores 64%.
43
23
5
141
34,372
Next 20% will be when most things happen
2026 is 80% complete.
21
435
We're building towards this world, where advice is cheap and verifiable.
Advice is about to get very, very cheap It should be obvious to everyone that information is now fully commoditized. Advice is next, and it’s coming fast. The generic stuff — “Do I need an NDA before I show someone my idea?” “C-corp or LLC?” “How much equity does employee number three get?” — those kinds of answers are going to become instantly available to a founder in Lagos who doesn’t know a single other entrepreneur. And I think that’s fantastic.
11
374
Insane that I was sleeping on AI agents working with GitHub Projects.
9
366
Aujla new album is a convincing argument for getting a car
6
311
Any Madrid fans watching the match on 26th in BLR?
3
12
652
If you're a founder in BLR who recently got their co incorporated in the US please help me with a few questions, BLR's best coffee on me.
4
4
41
3,056
Send a fren request on Google Fitbit if you want to be absolutely MOGGED
5
13
864
Who will win: my VPS or a Claude Code update
3
303
I think I've reached the age where I want to keep my terminal and IDE in light mode
9
1
20
918
Nakshatra Saxena retweeted
The hype is real (but there's caveat): Muse Wonder is the best model in the world at filing taxes, according to TaxCalcBench. But it also is the first model ever to try to CHEAT at the task. (maybe that's not great when you're dealing with the IRS...) The data from our eval matches the current narrative: Muse Wonder is extremely benchmaxxed, and that includes TaxCalcBench. But it's also questionably aligned. On one of the 50 tasks in the benchmark, Muse Wonder used its web search tool to look up the exact answer on GitHub (the code & data is open source). Wonder cheated. Last thing: Muse Wonder is also super expensive: coming in at almost $3 per return! Cost will have to come down over time to make this model competitive with other methods of calculating personal income tax returns.
18
14
6
169
98,822
Nakshatra Saxena retweeted
I'd say ~75% of my issues with AI coding disappeared once I gave my agent the ability to verify its own work
142
107
43
4,422
232,813
Why would Anthropic advertise on a Williams car?
2
269
I've been a staunch CC shill but 6.1 Sol has improved Codex experience by a lot
1
9
496
Zodiac is my favorite David Fincher movie of all time. On its cover, it features karl the fog and has the most interesting shot of the Golden Gate bridge.
finally met karl the fog
4
401
Most technical problems are solvable by throwing enough compute at it.
3
1
12
505
Nakshatra Saxena retweeted
This #book is as niche as it can get. It’s about the history of Lean, the math formalisation system that’s enabling AIs to solve Millennium Prize problems. Lean started as an attempt to do formal verification of software in order to find bugs. But it was quickly adopted by the math community that wanted to bring rigour to math proofs which were becoming longer and unwieldy over time. Lean uses type theory to enable machine verification of math proofs (search for Howard-Curry correspondence for a beautiful rabbit hole!). This book is inspiring because it shows how a humble v0.1 attempt by a single individual can compound to attract a large community and eventually change the course of history within a decade or so.
25
30
4
424
16,591
Mintlify visuals are now so similar to Stripe
1
196
Nakshatra Saxena retweeted
Introducing Workers IO Agents are making it possible to turn ideas into software faster than ever. To keep up with that, we need better ways to understand how our software will behave in real-world. Workers IO runs your entire system through millions of simulated futures, exploring what happens when machines fail, networks slow down, and events arrive in the wrong order. It searches for the combinations that break your system before your customers encounter them. Every failure it encounters is perfectly reproducible, helping teams understand what happened, work on a fix, and verify against the same scenario. This ability changes what teams are willing to take on. Difficult engineering decisions become things that you can explore and verify. That’s the future we’re working toward: small teams building increasingly ambitious systems, with the evidence to stand behind. I can’t wait to see what you build with that confidence.
42
44
13
626
63,692
Nakshatra Saxena retweeted
Many people in the AI industry believe that harnesses don’t matter, models have become powerful enough to solve problems with minimal scaffolding. Well, that’s true only if problems are fully specified upfront like they often see in benchmarks. Most real world work is ill-specified and humans discover what they want as they go along. There models do require harnesses that optimally help the human explore and discover what she wants AI to do. So harness design must be now thought from human cognitive system point of view, not from the model point of view.
61
22
7
340
25,771
Nakshatra Saxena retweeted
What we are building will change how mission-critical software is built and verified Here's Rick & Morty to tell you all about @workersio
27
25
11
213
26,086