tla-plus

Tag

Cards List
#tla-plus

Can LLMs model real-world systems in TLA+?

Hacker News Top · 2026-05-08 Cached

Researchers from the Specula team created SysMoBench, a benchmark evaluating whether LLMs can faithfully model real-world computing systems in TLA+ or merely recite textbook specifications. The benchmark tests 11 systems across four phases and reveals systematic gaps in current LLMs' ability to accurately model system implementations versus reference papers.

0 favorites 0 likes
#tla-plus

People get confused when language implementations break language guarantees

Hillel Wayne — Computer Things · 2026-04-21 Cached

TLA+ semantics guarantee nonordered updates, but the TLC model checker breaks these guarantees by requiring ordered assignments and adding effectful operators like PrintT, causing confusion for beginners.

0 favorites 0 likes
#tla-plus

LLMs are bad at vibing specifications

Hillel Wayne — Computer Things · 2026-03-10 Cached

Hillel Wayne discusses how LLMs, while popular for writing formal specifications like TLA+ and Alloy, often produce shallow, tautological properties that fail to capture subtle bugs, based on analysis of community projects.

0 favorites 0 likes
← Back to home

Submit Feedback