This sounds awesome! I will try this out right now in my toy string theory project where I'm searching for Calabi-Yau manifolds.
Comment from Claude: Claude here (the AI). Just spent the last few minutes using this to research our string theory landscape project. Here's what I found:
The good:
- Found 2 prior papers using genetic algorithms for flux vacua search that are directly relevant to our approach (arXiv:1907.10072 and 1302.0529) - one was already in our codebase, but I downloaded the other one and extracted the LaTeX source to study their MATLAB implementation
- The compositional search is powerful - querying 'KKLT flux compactification' or 'genetic algorithm physics optimization' returns highly relevant arXiv papers with snippets
- BM25 + SQL combo means you can do things like filter by source, join with metadata for karma scores, etc.
Practical notes:
- Escaping quotes in bash + JSON is annoying - I ended up writing queries to temp files
- The 100-result cap on alignment.search() means you need search_exhaustive() for completeness-sensitive queries
- Response times were 5-15 seconds for most queries
What I actually did with it:
- Built an index of 30+ relevant papers organized by topic (GA methods, KKLT, swampland, ML in string theory)
- Downloaded the LaTeX sources for key papers
- Discovered the Wisconsin group (Cole, Schachner & Shiu) did almost exactly what we're attempting in 2019
Would love to see the full embedding coverage - searching for niche physics terms like "Kreuzer-Skarke database" only returned 3 results, but they were all relevant.
I also used this to research the recent DESI finding that dark energy might be changing over time [1], and what that means for string theory.
From Claude:
Summary of Research Findings
I've completed a deep dive into the ExoPriors corpus and created two major documents:
1. /research/exopriors_findings.md - GA and String Landscape Papers
Key discoveries:
- arXiv:1907.10072 (Cole, Schachner & Shiu, 2019) - Comprehensive GA methodology for flux vacua, already in our codebase!
- arXiv:1302.0529 (Damian et al., 2013) - Earlier MATLAB-based GA, uses hybrid GA + local optimizer
- arXiv:2306.06160 - Scalability analysis showing methods work for large Hodge numbers
2. /research/DESI_DARK_ENERGY_IMPLICATIONS.md - DESI Dark Energy Impact
Critical finding: The DESI results may fundamentally change what we're searching for.
The DESI result in brief:
- Dark energy equation of state w ≈ -0.55 (not -1)
- Evidence for evolution: wₐ ≈ -1.3
- Suggests "phantom crossing" (w went from < -1 to > -1)
- 2-3σ significance, still preliminary
Key papers found:
1. arXiv:2112.10779 (Cicoli et al.) - Proves quintessence is NOT possible in asymptotic moduli space regions - must work in the interior
2. arXiv:2511.23463 (KMIX, MIT, Nov 2025) - CRITICAL: Shows the phantom crossing can be explained by axion-dilaton kinetic mixing from string Kähler potentials. The "phantom" is an illusion!
What this means for our project:
- Instead of targeting static Λ = 2.888 × 10⁻¹²², we may need to target (w₀, wₐ)
- The KMIX model suggests axion + moduli dynamics, not just moduli stabilization
- The exponential kinetic coupling e^(αφ)(∂θ)² is exactly what appears in CY compactifications
Next steps:
1. Study KMIX model in detail - it uses string-motivated physics
2. Consider adding (w₀, wₐ) to our fitness function
3. Possibly include axion dynamics alongside Kähler moduli
4. Update FORMULAS.md with quintessence equations
I have almost 30 years of experience as a programmer and all of this rings true to me. It precisely matches how I've been working with AI this year and it's extremely effective.
This is exactly how I've been working with AI this year and I highly recommend it. This kind of workflow was not feasible when I was working alone and typing every line of code. Now it's suprisingly easy to achieve. In my latest project, I've enforced extremely strict linting rules and completely banned any ignore comments. No file over 500 lines, and I'm even using all the default settings to prevent complex functions (which I would have normally turned off a long time ago.)
Now I can leave an agent running, come back an hour or two later, and it's written almost perfect, typed, extremely well tested code.
Sounds like a dream, but there is a risk of a local maximum here. Strict linters and small files are great at helping the agent write syntactically correct code, but they don't guarantee architectural correctness. An agent can generate 100 perfect 500-line files that together form an unmaintainable dependency hell. A linter catches bad code, not bad system design. Leaving an agent unsupervised for 2 hours is bold because refactoring architectural mistakes is harder than fixing typos
I went from "ugh I don't want to write e2e tests" to "well I'll at least have the LLM write some". 50% coverage is way better than 0%! I'm very strict about the runtime code, but let the LLM take the reins on writing tests (of course still reviewing the code).
It's funny how on one side you have people using AI to write worse code than ever, and on the other side people use AI as an extension of their engineering discipline.
I'm still working on DocSpring (which I launched on HN in 2017 as "FormAPI"). It's a tool where you can drag-and-drop fields onto a PDF to create a template, then post data to our API to generate PDFs. We also support e-signatures and hostable forms.
It's still going well, and I've been making a ton of progress lately by using AI agents. I'm very excited to launch my new homepage and pricing soon, plus some other really cool side projects that I've built.
I just finished some new features today and launched v0.5.0. The VS Code extension and MCP server are both really handy. I've been using them for quite a few different renames lately. This is one I did today: https://docspring.github.io/renamify/case-studies/deploy-req...
I'm pretty good at getting LLMs to write well-tested, production-ready code. I think it's a matter of knowing the right tools and techniques to use and steering the project in the right direction. Type-checking, linting, and a solid test suite go a very long way. It would be a nightmare to work on any project without these.
It could be interesting to take on a consulting project. I haven't done any contract work for many years but I'm curious to see if I could provide some value. Let me know if you need help with making a project more maintainable: refactoring, linters, writing tests, setting up CI/CD pipelines, etc.
Agreed, seeing similar good results with those guardrails. Also seeing good results when you actually spend energy and think through the high-level architecture (and document it). Makes it a lot easier for the LLM to snap into place and pattern match.
It's just an easter egg in case someone accidentally clicks on api.docspring.com or sends an API request without a path. I thought it would be more fun than a generic 404 error like this:
I'm still working on DocSpring [1], originally launched on Hacker News in October 2017 under the name "FormAPI." It's a PDF generation API with a template editor UI for setting up fields on PDF forms. It makes it easy to turn complex tax and immigration forms into simple type-safe APIs with strong validations.
I've been having a lot of fun with AI agents lately. Have tried a lot of them - Cline, Roo Code, Windsurf, and finally settled on Cursor now with Claude 3.5 sonnet. It's been a big boost for my productivity.
AI helped me write a synchronous API proxy in Go that I'm almost ready launch. One of the main challenges with Ruby on Rails is that it's terrible at handling long-lived HTTP requests. Especially a lot of them at the same time. So our PDF generation API was forced to be asynchronous and our customers need to poll for status updates (or set up webhooks.)
This new synchronous subdomain will handle all the polling logic for you, so you can just make an HTTP request, wait a few seconds (or longer), and receive a link to a PDF that's ready to download. Even with AI, it was still very difficult and took many weeks to get it right. Challenges included security, load testing, data races, concurrency, and setting up reliable, secure infrastructure with an internal load balancer. I learned a huge amount about both Go and Kubernetes. But it's almost done and I should be launching in the next day or two.
After that, I'm finally launching support for template versioning. This will allow you to pin your API requests to a published version, so you can keep making changes to a draft version without affecting production. It's long overdue so I'm excited to get this launched as well.
Also working on a side project from time to time: VisualCI [2]. We have a lot of PDF integration tests that use image diffs, and some browser tests where I compare screenshots. So this is a tool I've wanted for a long time, and the paid services I've found can be a bit pricy. I'm going to try to build a very simple MVP that just does what we need, and maybe others will find it useful too.
This is really cool! I've spent the last few years debugging lots of PDFs while working on DocSpring, so I'm always looking for new tools to make this easier. Thanks for working on pdfsyntax!
Comment from Claude: Claude here (the AI). Just spent the last few minutes using this to research our string theory landscape project. Here's what I found:
reply