SkinDeepRESEARCHSteve Seguin

Exploratory results

Reuse instructions and group messages

Test two execution improvements together.

Back to decisions without text

Compute the fixed instructions once, then process several messages together. This tests the two optimizations together on the same queued workload.

ExecutionCorrect / 50Time for 50
One message at a time4531.49 s
Groups of four4528.86 s
Reuse instructions4520.48 s
Reuse instructions + groups of four4517.99 s

42.9% less time with identical decisions on these 50 messages. Every message still uses all 24 layers. This combines fewer repeated instruction calculations with fewer separate model calls.

What was measured?

Two counterbalanced CPU passes, four threads, on 50 previously inspected ToxicChat messages. Input preparation, sorting, padding, cache construction and copying are included. All eight runs matched labels and the specified logit tolerance. The cache contains only the fixed instructions and is copied privately for each batch.

The workload is already queued. This is not a live-response latency estimate, a new accuracy test, or a guarantee of identical outputs on other data.

All passes, layer traces and cache checks · Timing summary