Hacker News: tristenharr

The AI may have a spot in it's Jacobian representing YOU

tristenharr — Fri, 17 Jul 2026 12:28:31 +0000

Article URL: https://author2vec.com/jlens

Comments URL: https://news.ycombinator.com/item?id=48946554

Points: 1

# Comments: 0

Guide to help people Transplant to the Bay from the Midwest

tristenharr — Fri, 17 Jul 2026 12:26:06 +0000

Article URL: https://transplantfrommissouri.com/

Comments URL: https://news.ycombinator.com/item?id=48946536

Points: 1

# Comments: 1

New comment by tristenharr in "Ask HN: What Are You Working On? (July 2026)"

tristenharr — Mon, 13 Jul 2026 05:55:13 +0000

I'm still working on Logos Language. Just launched v0.10.0 :)

https://logicaffeine.com/benchmarks

Ask HN: Do your tests clear "If the tests pass, you cannot break the code" bar?

tristenharr — Sun, 12 Jul 2026 05:08:40 +0000

Why or why not?

This is how I have found AI to be very powerful. If my tests pass, I know my code won't break. I spend more time on tests than any other part of the code-base. I am curious who else is building in this manner? I use the statement in the title because I feel that is the bar you have to meet to get the AI to work well, but once you meet that bar lately it has been working pretty flawlessly for me.

Comments URL: https://news.ycombinator.com/item?id=48878448

Points: 1

# Comments: 1

New comment by tristenharr in "After 7 years in production, Scarf has reluctantly moved away from Haskell"

tristenharr — Fri, 10 Jul 2026 19:01:53 +0000

This is the silliest take I’ve ever read. Strong type systems are an AI’s best friend.

Show HN: Jacobian Fingerprinting in LLM's

tristenharr — Thu, 09 Jul 2026 10:16:11 +0000

Article URL: https://author2vec.com/jlens

Comments URL: https://news.ycombinator.com/item?id=48843521

Points: 2

# Comments: 0

New comment by tristenharr in "Verbalizable Representations Form a Global Workspace in Language Models"

tristenharr — Wed, 08 Jul 2026 22:55:37 +0000

Feels related to research I've been doing with Author2Vec! https://author2vec.com/

I truly believe that now with all the post-training these AI models know some of us not just as fuzzy vectors but as individuals with a specific location within the Jacobian workspace that they tend to work from.

This thesis is why I keep separate Claude accounts, some for letting them train on my data, and another for work that must stay private. The more that it seems Claude will come to know you based on your fingerprint defined by your word choices and the fingerprint making up basically a mathematical representation of the way your brain is wired to do language.

If you want a model to do good work I hypothesize it is better to make sure that your project has a representation to work from within it's jacobian workspace!

Verbalizable Representations Form a Global Workspace in Language Models

tristenharr — Wed, 08 Jul 2026 22:51:06 +0000

Article URL: https://transformer-circuits.pub/2026/workspace/index.html

Comments URL: https://news.ycombinator.com/item?id=48838426

Points: 5

# Comments: 1

Adiabatic Circuit

tristenharr — Wed, 08 Jul 2026 08:30:58 +0000

Article URL: https://en.wikipedia.org/wiki/Adiabatic_circuit

Comments URL: https://news.ycombinator.com/item?id=48829192

Points: 1

# Comments: 0

Zero Copy

tristenharr — Wed, 08 Jul 2026 08:29:41 +0000

Article URL: https://en.wikipedia.org/wiki/Zero-copy

Comments URL: https://news.ycombinator.com/item?id=48829186

Points: 2

# Comments: 0

New comment by tristenharr in "The LLVM Compiler Infrastructure"

tristenharr — Wed, 08 Jul 2026 08:24:51 +0000

Yes that's the language, the v0.10.0 benchmarks are coming very soon and with it some major updates. We've added supercompilation and symmetry breaking to the optimizer pipeline. Sneak peeks available on a branch currently named stream1. https://github.com/Brahmastra-Labs/logicaffeine/tree/stream1

New comment by tristenharr in "The revenge of the philosophy majors"

tristenharr — Tue, 07 Jul 2026 22:22:37 +0000

I wanted to major in Philosophy but was worried I wouldn’t make enough money to support the lifestyle I wanted so majored in Computer Science instead. What irony.

Someday I hope to go back to school to get a PhD in philosophy with a focus on logic. :)

Reversible Computing

tristenharr — Tue, 07 Jul 2026 15:49:43 +0000

Article URL: https://en.wikipedia.org/wiki/Reversible_computing

Comments URL: https://news.ycombinator.com/item?id=48819466

Points: 1

# Comments: 0

Landauer's Principle

tristenharr — Tue, 07 Jul 2026 15:44:55 +0000

Article URL: https://en.wikipedia.org/wiki/Landauer%27s_principle

Comments URL: https://news.ycombinator.com/item?id=48819398

Points: 2

# Comments: 0

New comment by tristenharr in "The LLVM Compiler Infrastructure"

tristenharr — Tue, 07 Jul 2026 15:37:35 +0000

I’ve been shocked by how much LLVM leaves on the table while designing Logos language! Some very exciting benchmarks coming soon that we’ve been working on for over 6 months, but LLVM misses a LOT of potential optimizations when you have a strong type system!

New comment by tristenharr in "Connections in Math: the two kinds of random"

tristenharr — Mon, 06 Jul 2026 00:13:41 +0000

Lately I’ve felt Kolmogorov complexity is an unfair measurement because it takes for granted your underlying programming language as treats it as zero cost. In theory you could create a custom language and embed the program as data and “compress” a large random sequence with a better Kolmogorov complexity for that specific language than Pi, simply by not exposing the ability in the language to even work with Pi. I think what’s maybe more interesting is when you take into account the work of Dr. Futamura and the idea of Jones Optimality and view things through that lens.

New comment by tristenharr in "Proving Claude Knows You by Your Code Style: Author2Vec"

tristenharr — Fri, 03 Jul 2026 03:05:05 +0000

Hey all, I didn't actually use Claude for the embeddings on this (bc they don't offer embeddings), but I think we can extrapolate that if a tiny open source model has this level of recognition, surely the SOTA models do. Very interesting to me that we can predict things like gender and college from a sample of writing for authors. Also interesting how much stronger the correlation may be between Coders and their Code to authors and their books. Seems code has a more "unique" fingerprint than your typical book perhaps. (Although actually looking at it again perhaps that's sample size. Would need to research more to know for sure.)

Proving Claude Knows You by Your Code Style: Author2Vec

tristenharr — Fri, 03 Jul 2026 03:02:58 +0000

Article URL: https://author2vec.com/

Comments URL: https://news.ycombinator.com/item?id=48770217

Points: 4

# Comments: 1

Gaussian Function

tristenharr — Thu, 02 Jul 2026 21:28:33 +0000

Article URL: https://en.wikipedia.org/wiki/Gaussian_function

Comments URL: https://news.ycombinator.com/item?id=48767597

Points: 3

# Comments: 0

The Three Projections of Doctor Futamura

tristenharr — Thu, 02 Jul 2026 05:55:01 +0000

Article URL: http://blog.sigfpe.com/2009/05/three-projections-of-doctor-futamura.html

Comments URL: https://news.ycombinator.com/item?id=48757071

Points: 1

# Comments: 0