Pierre Zemb
Home
Blog
Tags
Talks
Podcasts
Contact
⊕ dark
root@pierrezemb.fr
:
~/blog
$
./read --quorum tags/llm
✓
quorum 2/3 · 4 documents · committed
read: quorum
ls ./tags/llm
2026-05-05
BugBash 2026, or how the correctness decade has started
A retrospective on BugBash 2026, and why software engineering looks brighter than ever.
#software-engineering
#testing
#simulation
#correctness
#llm
2026-01-15
What I Tell Colleagues About Using LLMs for Engineering
LLMs amplify expertise, they don't replace it. Here's what works: planning, context, feedback loops, and building systems that let AI discover bugs.
#llm
#software-engineering
#rust
#testing
2025-12-19
Specs Are Back, But We're Missing the Tools
LLMs revived specifications. Model checkers like Fizzbee work for algorithms. But for APIs and business logic? The tooling doesn't exist yet.
#software-engineering
#llm
#specifications
#formal-methods
#model-checking
#fizzbee
2025-09-08
Testing: prevention vs discovery
Most testing prevents old bugs from returning. But what if we built systems where LLMs could actively discover new bugs instead?
#testing
#simulation
#deterministic
#llm
#foundationdb
revision history
© 2026 Pierre Zemb · last rev. 2026-06-09
contact
github
twitter
bluesky
rss