Lab
Small experiments. Each asks one question and reports the measured answer, whichever way it came out. Mostly Rust, mostly CPU-local on Apple Silicon.
toolfetch
Python · CPU-local
For LLM tool-calling, do you retrieve fewer tools or inject more into the context window?
The measured retrieve-vs-inject frontier on a CPU-local model: how many tools you can put in context before it stops picking the right one. Real ToolRet labels, exact-match scoring, no LLM judge.
prefixfair
Go · CPU-only
Prefix-cache routing raises your hit rate. What does it cost in cross-tenant fairness?
The cache-hit vs cross-tenant service-gap Pareto frontier across five routing policies, measured on real llama.cpp backends. Honest either way.
crosskv
Rust
KV-cache eviction and quantization get tuned separately. Does treating them as one budget win?
On a real 12B transformer, a coupled budget allocator beats separable allocation held-out at equal budget. The interaction is real and worth allocating for.
funnelscan
Rust · NEON / Apple M4
How hard can you load a hash table before p99.9 probe counts fall apart?
A NEON group-probe funnel table sustains 99.9% load with bounded p99.9 probes, in a smaller footprint than a SwissTable forced to resize.
circ-das
Rust · NEON / Apple M4
Do block-circulant local codes actually beat 2D Reed-Solomon for blockchain data-availability?
At high rate, block-circulant beats 2D-RS distance. First implementation and honest measurement, with a NEON GF(2^8) encoder and a coded-Merkle DAS sampler.
ribbonguard
Rust · NEON / Apple M4
Can an approximate-membership filter stay cheap under skew without ever returning a false negative?
Yes. A NEON blocked filter fused with a skew-adaptive false-positive suppressor holds the no-false-negative invariant, exhaustively checked, while cutting false positives where the skew concentrates.
calibann
Rust · NEON / Apple M4
A semantic cache decides what to serve on a similarity threshold. Is a static threshold safe?
It's silently unsafe. A calibrated, safety-gated gate on a binary-quantized ANN core turns served-error into a target you control instead of a number you hope about.
cdcneon
Rust · NEON / Apple M4
How fast can content-defined chunking run on Apple Silicon, and does the fast path cost you dedup?
SeqCDC on a NEON fast path hits ~19 GiB/s on an M4. Gear stays the default: it dedups better and degrades more gracefully. blake3 content-addressed store underneath.