LLM-written Rust library bbtree verified: speed claims hold, memory savings reverse
lmoroney · x · 2026-10-27
Xiangpeng Hao, designer of Bf-Tree (said to run in production at Microsoft), released bbtree, a Rust ordered map whose implementation he says was written entirely by LLMs with cross-provider cross-checking — he made the design decisions and owns accountability. This sparked debate on Hacker News.
An independent benchmark by @superdoccimo on an 8 vCPU Linux box confirmed the speed claims (several times faster than std BTreeMap on lookups), but the "30% memory reduction" reversed under default glibc malloc: bbtree actually used 1.8x the memory. Takeaway: LLM-written systems code can be serious, but performance claims need per-metric verification.
More from coding & agent
- Reticle builds a verification layer that lets AI coding agents check their own generated code — Scobleizer · 2026-10-27
- Trust your agent, but read its logs: Claude managed agents tips — brada · 2026-10-27
- Dev training a guard model to block prompt injection, tool and memory poisoning — gnukeith · 2026-10-27
- Dev trains a ~4GB-VRAM sentinel model to guard against prompt injection and poisoned memory — gnukeith · 2026-10-27
- Superset rebrands as Paradev, raises $11.5M seed led by USV — massimosgrelli · 2026-10-27
- Ex-Big Tech managers may thrive in the AI era: manage agents like you managed teams — lxfater · 2026-10-27