HN Explorer

44za12

↗ HN profile [ 49.7 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Stop generating what you already have (aazar.me)
    2 points 0
  2. Horcrux – Distributed, Zero-Trust Secret Manager (github.com)
    3 points 2
  3. Lattice Deduction Transformers (arxiv.org)
    4 points 0
  4. δ-mem: Efficient Online Memory for Large Language Models (arxiv.org)
    240 points 23
  5. Beyond Semantic Similarity (arxiv.org)
    68 points 10
  6. In Defense of Boring Technology (aazar.me)
    1 points 0
  7. Show HN: RightSize CLI, Find the cheapest LLM that works for your prompt (github.com)

    RightSize runs your prompt against candidate models (Kimi, GLM, Qwen, Gemma etc.) in parallel via OpenRouter. Then it uses a stronger model as a Judge to score accuracy against a baseline model. Happy to answer…

    3 points 0
  8. Show HN: LLM Sanity Checks – A practical guide to not over-engineering AI (github.com)

    I keep seeing teams use frontier models for tasks a regex or a 4B model could do cheaper and faster. This repo is a collection of opinionated patterns and heuristics to help you rethink the architecture of your AI…

    1 points 0
  9. Stop using JSON for LLM structured output (nehmeailabs.com)
    2 points 1
  10. FlashCheck-270M: Open weights for fact verification (Apache 2.0, WASM Demo) (huggingface.co)
    2 points 0
  11. Show HN: Surf – open-source Web Access for LLMs (github.com)

    SURF (Search Utility & Reading Framework) is an open-source API that bridges LLMs with the web. It provides a standardized interface for web search and content processing that preserves formatting of tables, code, and…

    6 points 0