HN Explorer

eskibars

↗ HN profile [ 86.3 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Show HN: DriftTrip – A Virtual Road Trip (drifttrip.connelly.casa)

    I've always loved the idea of taking a "virtual road trip" between 2 cities. You get to experience the tourism ads or other short-form videos at each "stop" along the way. I hope others enjoy it as well :)

    1 points 0
  2. Evaluating different LLMs for their security research capabilities (zeroquarry.com)
    2 points 0
  3. Obsidian plugins are (mostly) dangerous (zeroquarry.com)
    5 points 2
  4. Critical RCE found in Obsidian Tasks plugin (zeroquarry.com)
    5 points 1
  5. Show HN: Free security scanning for OSS projects

    Hi HN, I've spent a lot of my career working in open source and I want to give back. Recently, I launched https://zeroquarry.com, which is a tool that helps you find 0-days in your software by through AI by tracing…

    2 points 0
  6. Show HN: Scan your OSS projects for vulnerabilities (console.zeroquarry.com)

    Hi all, I've had a feeling for a while that there was going to be a war on software based on LLMs controlled by "bad actors." LLMs have gotten really good at finding security vulnerabilities and in the hands of bad…

    1 points 1
  7. Heads up: Backblaze is using AI SDRs

    I received a call from a Backblaze sales person asking for "27 seconds of my time" to my personal cellphone. My cell is on the US "do not call" list, but was dialed anyway. The conversation sounded very strange, and I…

    5 points 2
  8. Show HN: New and more powerful OSS hallucination detection (vectara.com)

    Hi HN! At Vectara (https://vectara.com) were hyper focused on providing best in class retrieval-augmented-generation (RAG). We've just released a new open source hallucination detection model (available on HuggingFace…

    2 points 0
  9. Show HN: Mockingbird is an LLM that outperforms GPT4 on RAG (vectara.com)

    Hi HN! I lead product at Vectara and we've just released a new LLM in our platform that outperforms GPT4 and Gemini 1.5 Pro on RAG tasks. Vectara is a Retrieval Augmented Generation (RAG) platform primarily deployed as…

    9 points 1
  10. Vectara raises $25M for enterprise RAG and releases its own generative LLM (venturebeat.com)
    3 points 0
  11. Ask HN: Does your business prefer token-based pricing?

    Currently, my product offers retrieval augmented generation as a service. Anyone doing LLM-based apps has probably noticed that the usage costs are typically on a per-token basis, which seems very "fair" in that each…

    1 points 0
  12. 1 points 0
  13. Show HN: AI Kids Book Generator (kidsbook.connelly.casa)

    Fun little weekend project over the past month or so. Our kids ask for a story every night, and I wanted to see how far I could get AI to generating it with corresponding images. The text comes from gpt-4-turbo. Images…

    2 points 0
  14. 1 points 1
  15. Show HN: Chat-focused RAG with automated memory management (docs.vectara.com)
    4 points 3
  16. Show HN: Sankofa – Browser extension to semantically search your history (vectara.com)

    Hey there HN! I lead Product at Vectara. Some of us read a lot of articles on the web (like those on HN) and we were desperately trying to recall the text we read -- using semantic search because we might not have…

    19 points 1
  17. Ask HN: Do you like to use REST verbs

    Interested in thoughts here: we're considering rolling out a new REST API, and curious about your preferred way of interacting with REST APIs: in particular, HTTP verbs (mostly interested in POST vs PUT vs PATCH). I’m…

    2 points 1
  18. Show HN: Open-source model and scorecard for measuring hallucinations in LLMs (vectara.com)

    Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple"…

    65 points 14
  19. Show HN: Quepid now works with vector search (quepid.com)

    Hi HN! I lead product for Vectara (https://vectara.com) and we recently worked with OpenSource connections to both evaluate our new home-grown embedding model (Boomerang) as well as to help users start more…

    2 points 0
  20. Show HN: Launching a new home-grown embedding LLM for RAG (vectara.com)

    Hi HN! Vectara is a "batteries included" retrieval augmented generation platform. You can upload your rich text documents like PDFs, HTML pages, word docs, etc, or semi-structured JSON and Vectara handles the text and…

    12 points 1
  21. Show HN: Live Train Webcams (train.api.connelly.casa)

    Our son is really into trains. He was home sick a few weeks ago and we found that there are several YouTube channels that have live video feeds from various train stations or railway clubs around the US. He really liked…

    15 points 4
  22. You don't need a vector database. You need a GenAI Platform (vectara.com)
    5 points 0
  23. Ask HN: Developer opinions on SaaS in-product walkthroughs

    Hi HN! We recently launched our company/product (https://vectara.com) a few weeks ago. Just as background is a new neural search SaaS product (think a bit like Elasticsearch or Algolia I guess, but with natural language…

    1 points 1
  24. Show HN: Where SF public transit breaks rules (oddball.eskibars.com)
    2 points 2