HackerTrans
トップ新着トレンドコメント過去質問紹介求人

dovelome

no profile record

投稿

[untitled]

1 ポイント·投稿者 dovelome·11 日前·0 コメント

[untitled]

1 ポイント·投稿者 dovelome·18 日前·0 コメント

[untitled]

1 ポイント·投稿者 dovelome·22 日前·0 コメント

The Line Vibe Coding Can't Cross

blog.r-lopes.com
2 ポイント·投稿者 dovelome·23 日前·0 コメント

Governance Is the Missing Half of AI Efficiency

blog.r-lopes.com
4 ポイント·投稿者 dovelome·24 日前·2 コメント

Why Agents Don't Scale: It's an Engineering Problem, Not an AI Problem

blog.r-lopes.com
5 ポイント·投稿者 dovelome·27 日前·3 コメント

The AI supply chain is a software supply chain with new failure modes

blog.r-lopes.com
3 ポイント·投稿者 dovelome·28 日前·0 コメント

コメント

dovelome
·11 日前·議論
[flagged]
dovelome
·18 日前·議論
[flagged]
dovelome
·22 日前·議論
[flagged]
dovelome
·23 日前·議論
[flagged]
dovelome
·24 日前·議論
Check it out: https://blog.r-lopes.com/how-it-works
dovelome
·24 日前·議論
I like what you are doing! I suggest you create a proxy service that will route the traffic to the AI provider.

You can cache questions and answers heavily and use a B25 search with a vector embedded to retrieve the best results for you.

   RAG pipeline
   ├── BM25 + TF-IDF + RRF retrieval
   ├── cross-encoder reranking
   ├── knowledge-graph entity linking
   └── multi-angle intent detection
        │
        ▼
   LLM synthesis  (Claude / local models)
dovelome
·24 日前·議論
I believe this future is happening now! I see a lot of movement in the industry to understand what AI efficiency is and how to properly quantify it. The industry is eager to know the ROI of the ratio of token usage, Mr merges, and value delivered.
dovelome
·24 日前·議論
[flagged]
dovelome
·27 日前·議論
[flagged]
dovelome
·28 日前·議論
[flagged]
dovelome
·3 か月前·議論
Love it