docs: add multi-step training curves to README + BLOG_POST

BLOG_POST: clarify ambiguous "80% of 94-token human-prompt accuracy" in hook

BLOG_POST: stronger 3-paragraph hook, move Prior Work above the fold, escape unsafe single tildes

docs: refresh BLOG_POST stale 87-task numbers; finish README ~ cleanup

docs: add Prior Work section + replace Training/thinking-mode A/B with multi-step setup

docs: surface multi-turn in How-it-works, defer training-process notes

docs: consolidate Results section — single master table + per-category + examples

docs: add multi-step variant section to README + BLOG_POST

Update BLOG_POST.md

BLOG_POST: drop 37× MSN policy compression callout

BLOG_POST: drop policy-tasks-as-headline-workload framing

BLOG_POST: integrate user revisions

BLOG_POST: drop 37× compression claims

BLOG_POST: full rewrite — research framing, 10 sections, citations, image placeholders

docs: drop the misleading 37× compression anecdote (0-accuracy task)

README + BLOG: drop multi-step + Llama-self mentions (in-progress runs)

Add BLOG_POST.md (HF blog draft, hackathon framing)