HN Explorer

retrovrv

↗ HN profile [ 74.2 ms ] full profile

No user record in our sample, but retrovrv has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.

  1. Show HN: Prompt Engineering Studio – Toolkit for deploying AI prompts at scale

    Hey HN! Long-time reader, occasional commenter here. I wanted to share something my team and I have been building to solve our own frustrations. We've all seen the explosion of prompt engineering tools lately. While…

    2 points 4
  2. OpenAI Model Deprecation Guide – GPT3 is shutting down (portkey.ai)
    2 points 0
  3. GPT-4 is Getting Faster (portkey.ai)
    3 points 0
  4. Open Source AI Gateway (github.com)
    2 points 0
  5. 1 points 0
  6. Ask HN: Where to Host Llama 2?

    There's ollama/ggml etc for local setup, but other than Replicate, what are the other options for hosting Llama 2?

    3 points 2
  7. Overcoming Challenges with LLM APIs

    Once we accept that LLMs can sometimes hallucinate, we're left with other integration hurdles when incorporating them into apps: - Inconsistent APIs across different LLMs - Not entirely reliable - Higher latencies - The…

    1 points 0
  8. 1 points 1
  9. Neat implementation of semantic cache for GPT4 (portkey.ai)
    1 points 0
  10. Implementing Semantic Cache to Reduce LLM Cost and Latency (portkey.ai)
    2 points 0