How to use Claude to check symbolic expressions
Claude Code helped build a SymPy evaluator for expressions using exp(x) - ln(y). The author shared matching symbolic and numeric results for the displayed examples.
news.ycombinator.com
Suggested prompt
Suggested prompt written by Agents In Use, not the source author. Replace bracketed inputs and review tool permissions first.
Build a SymPy evaluator for expressions using [binary operator definition]. Evaluate [constants and function expressions], compare symbolic simplification and numeric values with [expected results], and print a table identifying mismatches.
Reach people exploring AI agents
See placements →Evidence at a glance
Sourced account- Source poster / publisher
- pveierland
- Original account
- Read the source ↗
- Published
- Source link checked
- Reported result
- The displayed evaluator results matched expected values for the listed constants, unary functions and binary operations, with symbolic and numeric checks marked successful.
- Human involvement
- The author examined and shared the evaluator output, concluding that numeric and symbolic results appeared to agree.
A linked account supports attribution. It does not mean we independently reproduced its result.
Report an issue with this case
Open correction emailOpens your email app with the case link included. Nothing is sent automatically.
How the agent did it
- Use Claude Code to build a quick evaluator for the binary operator.
- Evaluate constants, unary functions and binary arithmetic examples.
- Compare computed values with expected numeric and symbolic results.
The author wanted to see whether SymPy could evaluate expressions built from a single binary operator. They used Claude Code to build a quick evaluator for eml(x, y) = exp(x) - ln(y), referencing the paper identified in the supplied output. They then shared a Nix command for running the project and a table of evaluation results.
The output covers constants, unary functions and binary operations. Constant checks include zero, negative values, fractions, the square root of two, the imaginary unit and pi. Unary checks use x = 7/3 and include exponentiation, logarithms, reciprocal, square and square root. Binary checks use x = 7/3 and y = 5/2 for addition, subtraction, multiplication, division and powers.
Each displayed row compares a computed value with an expected value and reports symbolic and numeric status. The author cautiously says the numeric and symbolic results appear to agree. This is a reported evaluator check, not a claim that every possible expression was validated. Who it's for: developers exploring mathematical representations who want an executable comparison between symbolic simplification and numerical evaluation.
Prompt
Suggested prompt (written by Agents In Use, not the author's)
Source: Hacker News · pveierland
Frequently asked questions
What operator did the evaluator implement?
The shared output defines eml(x, y) as exp(x) - ln(y). The author used Claude Code to build a quick evaluator involving SymPy.
What did the displayed checks show?
The displayed constants, unary functions and binary operations showed matching computed and expected values, with symbolic and numeric checks marked successful.
More details
Remaining steps
- Share the Nix execution command and the evaluation output.
About this account
Claude Code built the evaluator at the author's request; the source does not describe a longer autonomous development process.
Platform: Hacker News. Attribution: https://news.ycombinator.com/item?id=47749545. Prompt: Suggested (written by Agents In Use, not the author's). Sourced by the Agents In Use pipeline.
Credit: pveierland on Hacker News
Source published
Added to Agents In Use
Source checked
Tools and topics
Claude Code · SymPy · Nix
Mathematics · SymPy · Symbolic computation
Editorial completeness: 100/100. Measures documented fields, not agent performance or verified outcomes.