sks-website/src/content/codeindex/ at main · russ.fugl.dev/sks-website · Tangled

russ.fugl.dev / sks-website

0

build smart knowledge-sharing systems that combine the best of human expertise with smart technology

0

sks-website / src / content / codeindex /

at main 4 files

Russ T. Fugal feat(codeindex): update benchmarks with 19-repo multi-language eval results 4mo ago

feat(codeindex): update benchmarks with 19-repo multi-language eval results Replace self-eval test fixture benchmarks with real public repo results: - 330 queries across 19 public repos (17 GitHub, 2 tangled.org), 16 languages - Per-language data now from representative repos (e.g. Kong/kong for Lua, kubernetes for Go, elasticsearch for Java) - Lua jumps from "broken/17%" to "excellent/82%" on real-world Kong codebase - Update multipliers from 3.1x (naive grep) to 1.4x (vs LLM-crafted expert grep patterns) — more rigorous baseline - Update cost from $0.17 to $0.70, file count to 100k+ - Add services section anchor, language tags on repo cards - Qualify commit-boost signal contribution (25.8% on self-eval, varies on broader corpus — investigating) - Update all marketing copy, metadata, and OG images to match Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

4 months ago

feat(codeindex): add services section, update CTA footer, and fix claims Implements unified strategy content changes: - Fix unvalidated claims: 14→18 languages, soften blast-radius and cost-reduction stats, replace "Onboard 5x faster" with grounded copy - Add servicesSection: Agent Ready Workshop ($5K) and CodeReady Pilot ($15K) with deliverables, pricing, risk reversal, and proof point - Update ctaFooter from 3 to 4 tiers: self-serve install, cidx-cloud waitlist, workshop booking, and pilot booking - Add cidx-cloud waitlist page content (cloud.ts) Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

4 months ago

feat(codeindex): update benchmarks with 19-repo multi-language eval results Replace self-eval test fixture benchmarks with real public repo results: - 330 queries across 19 public repos (17 GitHub, 2 tangled.org), 16 languages - Per-language data now from representative repos (e.g. Kong/kong for Lua, kubernetes for Go, elasticsearch for Java) - Lua jumps from "broken/17%" to "excellent/82%" on real-world Kong codebase - Update multipliers from 3.1x (naive grep) to 1.4x (vs LLM-crafted expert grep patterns) — more rigorous baseline - Update cost from $0.17 to $0.70, file count to 100k+ - Add services section anchor, language tags on repo cards - Qualify commit-boost signal contribution (25.8% on self-eval, varies on broader corpus — investigating) - Update all marketing copy, metadata, and OG images to match Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

4 months ago

feat(codeindex): update benchmarks with 19-repo multi-language eval results Replace self-eval test fixture benchmarks with real public repo results: - 330 queries across 19 public repos (17 GitHub, 2 tangled.org), 16 languages - Per-language data now from representative repos (e.g. Kong/kong for Lua, kubernetes for Go, elasticsearch for Java) - Lua jumps from "broken/17%" to "excellent/82%" on real-world Kong codebase - Update multipliers from 3.1x (naive grep) to 1.4x (vs LLM-crafted expert grep patterns) — more rigorous baseline - Update cost from $0.17 to $0.70, file count to 100k+ - Add services section anchor, language tags on repo cards - Qualify commit-boost signal contribution (25.8% on self-eval, varies on broader corpus — investigating) - Update all marketing copy, metadata, and OG images to match Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

4 months ago