k
keynews.ai
keynews.ai
AI newsThe story, in brief

Show HN: Postgres extension for BM25 relevance-ranked full-text search

Not a pilot. Tiger Data just shipped a Postgres extension that outperforms ParadeDB by 4.7x—using Claude AI to cut development time from 12 months to 6.

Reporting by Hacker News 1 min brief
Illustration of a transparent lens revealing connected networks across layers of paper.
Exploring the next frontier of AI research.AI illustration by KeyNews
The KeyNews take

Why it matters

Open-source tooling is collapsing development timelines for AI infrastructure. Tiger Data's pg_textsearch demonstrates how AI-assisted coding (Claude) enabled a solo engineer to build production-grade database search in half the estimated time, disrupting the competitive moat of established vendors like ParadeDB.

The key facts

7 to know

  1. 4.7x query throughput advantage over ParadeDB/Tantivy at scale

  2. Development timeline: estimated 6-12 months reduced to ~6 months actual (2 quarters) with AI-boosted development

  3. pg_textsearch released open-source under Postgres license

  4. Built by Tiger Data, a Postgres cloud vendor specializing in timeseries data

  5. BM25 relevance-ranked full-text search for hybrid search stacks

  6. Benchmarked on MS-MARCO dataset with publicly available methodology

  7. Addresses Postgres native gap: no built-in ranked keyword search; alternative (ParadeDB) uses restrictive AGPL license

Go to the source

Hacker Newsgithub.com

Publisher excerpt: Last summer we faced a conundrum at my company, Tiger Data, a Postgres cloud vendor whose main business is in timeseries data. We were trying to grow our business towards emerging AI-centric workloads and wanted to provide a state-of-the-art hybrid search stack in Postgres. We'd already built…
Read original report
Back to today's editionMore AI news

The wider picture

View all
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Agents01

Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation

Anthropic disclosed a major defensive win against coordinated model distillation attacks targeting Claude's reasoning tokens. The scale and attribution matter: this confirms a known threat vector is operationalized at industrial volume by named Chinese labs, and Anthropic's countermeasures—account bans and technical hardening—are measurable. Practitioners running Claude in enterprise environments need to understand the attack surface; the distillation risk affects cost and model-moat strategy.

The Decoder
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work02

Why process excellence will become the competitive advantage in the AI economy

As AI models become commoditized, enterprise differentiation will shift from technology access to operational maturity — the clarity, governance, and end-to-end process design that allow agents to execute autonomously at scale. This is a strategic reframing for enterprises: AI success is now a process and governance problem, not primarily a model problem.

CIO
Illustration of two anonymous hands arranging task cards around an amber tool on a shared desk.
AI illustration by KeyNews
Work03

Wikipedians Believed AI Would Come and Go. They Were Wrong

As AI systems increasingly use search aggregation and direct answers over source links, Wikipedia's role as a foundational knowledge layer for both humans and machines faces structural erosion—a shift that affects how enterprises think about data grounding, source attribution, and the long-term viability of community-maintained knowledge bases in an agentic AI era.

Wired AI