AI is changing the world. Don't stay behind. Clear summaries, community insight, delivered without the noise. Subscribe to never miss a beat.

Privacy

Contact

Back to all news

code-generation ai-agents developer-tools educational-technology

Old and new apps, via modern coding agents by Terry Tao

terrytao.wordpress.com

July 12, 2026

3 min read

🔥🔥🔥🔥🔥

64/100

Summary

Machine-assisted methods for teaching mathematics have been explored since 1999, with early applets coded in Java 1.0 for complex analysis and linear algebra courses. The transition away from Java 1.0 due to web standards rendered these applets obsolete.

Key Takeaways

The author successfully migrated old Java applets to modern JavaScript using AI assistance, restoring functionality and improving graphics.
The AI agent identified two bugs in the original code while porting the applets, resulting in a net improvement in code quality.
The author created a new visualization tool for special relativity with the help of an AI agent, realizing a long-held vision from 1999.
The author plans to use AI-generated interactive visualizations as supplements for future papers, assessing the risk of potential bugs as acceptable.

Read original article

Community Sentiment

Mixed

Positives

Terry Tao's excitement over coding agents feels like a major leap, as even top-tier mathematicians are now exploring AI to enhance their work.
Using LLMs for visualizations has been a game changer for many educators, allowing them to create complex teaching aids they previously lacked time for.
Commenters see LLMs as fantastic tools for iterating on projects, making it easier to produce visual outputs without worrying about perfect code.

Concerns

Skeptics argue that many AI projects, including Tao's, remain hobbyist endeavors rather than serious applications within academia.
There's a strong sentiment that LLMs generate code that's often atrocious and unreliable, making them unsuitable for high-stakes programming tasks.
Despite the excitement, some commenters emphasize the need for caution, noting that AI tools shouldn't be blindly trusted.