Hacker News

HTTP Message Signatures Sandbox

Hacker News - 12 min 30 sec ago

Article URL: https://httpsig.org/

Comments URL: https://news.ycombinator.com/item?id=40237654

Points: 1

# Comments: 0

Categories: Hacker News

Where do you get your B2B news?

Hacker News - 13 min 14 sec ago

Comments URL: https://news.ycombinator.com/item?id=40237646

Points: 1

# Comments: 0

Categories: Hacker News

Ask HN: How Spam are removed from large datasets of web crawls for AI training

Hacker News - 13 min 24 sec ago

Large crawls for example commoncrawl or companies that have in house web scrapers/crawlers to collect data / scrape from the web to train ai . 1. How are blogspams / regular spams are cleaned from such huge data ? 2. Is it possible to teach ai to clean datasets with small human annotated datasets to clean large datasets for ai training ? 3. How misinfo/disinfo in cleaned ?

Comments URL: https://news.ycombinator.com/item?id=40237641

Points: 1

# Comments: 0

Categories: Hacker News

Show HN: Local GLaDOS

Hacker News - 18 min 5 sec ago

I built GLaDOS's brain, with a low-latency chat interface. Sub 600ms voice-to-voice response, running on Llama-3 70B.

Comments URL: https://news.ycombinator.com/item?id=40237586

Points: 3

# Comments: 0

Categories: Hacker News

Show HN: SpRAG – Open-source RAG implementation for challenging real-world tasks

Hacker News - 21 min 37 sec ago

Hey HN, I’m Zach from Superpowered AI (YC S22). We’ve been working in the RAG space for a little over a year now, and we’ve recently decided to open-source all of our core retrieval tech.

spRAG is a retrieval system that’s designed to handle complex real-world queries over dense text, like legal documents and financial reports. As far as we know, it produces the most accurate and reliable results of any RAG system for these kinds of tasks. For example, on FinanceBench, which is an especially challenging open-book financial question answering benchmark, spRAG gets 83% of questions correct, compared to 19% for the vanilla RAG baseline (which uses Chroma + OpenAI Ada embeddings + LangChain).

You can find more info about how it works and how to use it in the project’s README. We’re also very open to contributions. We especially need contributions around integrations (i.e. adding support for more vector DBs, embedding models, etc.) and around evaluation.

Comments URL: https://news.ycombinator.com/item?id=40237546

Points: 3

# Comments: 0

Categories: Hacker News

Pages