HackerTrans
TopNewTrendsCommentsPastAskShowJobs

dovelome

no profile record

Submissions

[untitled]

1 points·by dovelome·vor 11 Tagen·0 comments

[untitled]

1 points·by dovelome·vor 19 Tagen·0 comments

[untitled]

1 points·by dovelome·vor 22 Tagen·0 comments

The Line Vibe Coding Can't Cross

blog.r-lopes.com
2 points·by dovelome·vor 23 Tagen·0 comments

Governance Is the Missing Half of AI Efficiency

blog.r-lopes.com
4 points·by dovelome·vor 25 Tagen·2 comments

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

blog.r-lopes.com
5 points·by dovelome·vor 27 Tagen·3 comments

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

blog.r-lopes.com
3 points·by dovelome·vor 28 Tagen·0 comments

comments

dovelome
·vor 11 Tagen·discuss
[flagged]
dovelome
·vor 19 Tagen·discuss
[flagged]
dovelome
·vor 22 Tagen·discuss
[flagged]
dovelome
·vor 23 Tagen·discuss
[flagged]
dovelome
·vor 24 Tagen·discuss
Check it out: https://blog.r-lopes.com/how-it-works
dovelome
·vor 24 Tagen·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
·vor 24 Tagen·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
·vor 25 Tagen·discuss
[flagged]
dovelome
·vor 27 Tagen·discuss
[flagged]
dovelome
·vor 28 Tagen·discuss
[flagged]
dovelome
·vor 3 Monaten·discuss
Love it