HackerTrans
TopNewTrendsCommentsPastAskShowJobs

dovelome

no profile record

Submissions

[untitled]

1 points·by dovelome·il y a 12 jours·0 comments

[untitled]

1 points·by dovelome·il y a 19 jours·0 comments

[untitled]

1 points·by dovelome·il y a 23 jours·0 comments

The Line Vibe Coding Can't Cross

blog.r-lopes.com
2 points·by dovelome·il y a 24 jours·0 comments

Governance Is the Missing Half of AI Efficiency

blog.r-lopes.com
4 points·by dovelome·il y a 25 jours·2 comments

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

blog.r-lopes.com
5 points·by dovelome·il y a 28 jours·3 comments

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

blog.r-lopes.com
3 points·by dovelome·il y a 28 jours·0 comments

comments

dovelome
·il y a 12 jours·discuss
[flagged]
dovelome
·il y a 19 jours·discuss
[flagged]
dovelome
·il y a 23 jours·discuss
[flagged]
dovelome
·il y a 24 jours·discuss
[flagged]
dovelome
·il y a 25 jours·discuss
Check it out: https://blog.r-lopes.com/how-it-works
dovelome
·il y a 25 jours·discuss
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
·il y a 25 jours·discuss
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
·il y a 25 jours·discuss
[flagged]
dovelome
·il y a 28 jours·discuss
[flagged]
dovelome
·il y a 28 jours·discuss
[flagged]
dovelome
·il y a 3 mois·discuss
Love it