惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

U
Unit 42
F
Fortinet All Blogs
Martin Fowler
Martin Fowler
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
IT之家
IT之家
Blog — PlanetScale
Blog — PlanetScale
罗磊的独立博客
V
V2EX
Vercel News
Vercel News
Apple Machine Learning Research
Apple Machine Learning Research
J
Java Code Geeks
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
T
Tailwind CSS Blog
I
InfoQ
Engineering at Meta
Engineering at Meta
WordPress大学
WordPress大学
S
SegmentFault 最新的问题
H
Help Net Security
腾讯CDC
D
Docker
P
Proofpoint News Feed
GbyAI
GbyAI
博客园 - 三生石上(FineUI控件)
aimingoo的专栏
aimingoo的专栏

Show HN

Show HN: AI agents for UK GDAD PCF roles and their skills The Two Pillars: Mixer Mode and Meta-Software in the Reorganization of Software Work After AI GitHub - JaiCode08/teleport-env What 1,000+ Harness Experiments Taught Me About Self-Improving Agents Show HN: Liiists, a Markdown-first, iOS and CLI list app SwiperTab – Get this Extension for 🦊 Firefox (en-US) GitHub - kouhxp/fftext: Summarize, explain, fact-check, or translate any text, URL, or file. No GPU. No cloud. One command GitHub - sweetpad-dev/sweetpad: Develop Swift/iOS projects using VSCode GitHub - dogmaticdev/IRON: IRON a.k.a. Intermediate Representation Object Notation is a Interpreter/Database that is used to create Programming Languages. GitHub - sjhalani7/vaen: Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets. Show HN: Gandalf the Grader Show HN: Citadeld – replay any CI failure locally from a single file GitHub - tdortman/cuSBF: High-Performance GPU Super Bloom Filter coral-ai/claude-code-token-xray at main · Coral-Bricks-AI/coral-ai GitHub - ulyssestenn/funes: Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge base, and uses it to produce cited reports, analyses, and other outputs. GitHub - ThatXliner/gah: Git Add Hunk, built for agents to use GitHub - harmont-dev/harmont-cli: Command-line client for the Harmont CI platform GitHub - brooksmcmillin/mcp-authflow: OAuth 2.0 Authorization Server framework for MCP servers GitHub - javaid-codes/audit-supply-chain-agents GitHub - amorey/gochan: A small library of common channel architectures for Go, inspired by Rust GitHub - arifozgun/OpenGem: Free, Open-Source AI API Gateway with Gemini, OpenAI & Anthropic Compatibility in 1 file GitHub - Pranesh950/BioPetals: 🌸 Run BIOxAI models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading GitHub - cnguyen14/bounty-doctor: Diagnose a GitHub bounty issue before you waste hours: detects honeypot scam repos, AI-bot attempt swarms, and stale contests. Show HN: CoreMCP – MCP Server for On-Prem DBs Show HN: KittyHTML – Render HTML/CSS as an inline image in your terminal GitHub - bingud/filemat: Web-based file manager Show HN: TruthLens – Free multi-signal deepfake image detector GitHub - apexlocal-jz/claude-usage-tray: Windows system-tray app showing your Claude Code rate-limit usage at a glance. Zero deps, ~300 lines of PowerShell. Cross-IDE (works regardless of VS Code, Cursor, plain terminal). Release v0.1.2.1 · kouhxp/yapsnap GitHub - noopolis/moltnet: Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code.
Sonic AI, Audio Intelligence
Rob Diorio · 2026-06-23 · via Show HN

The best ideas are buried in audio

The best investors, founders, and policymakers say things on podcasts, earnings calls, and conference stages they'd never put in writing. Sonic pulls every claim out of the audio, attributes it to the person who said it, and turns hours of listening into cited research briefs in seconds.

tech

Anthropic's CEO set a goal for 90% of the company's code to be written by its AI system, Claude, by the end of 2025.

Ezra KleinAnthropic

tech

Martin Shkreli believes the most valuable use of AI in pharma would be an LLM that reads all 38 million papers in the PubMed database to identify novel drug targets.

Martin ShkreliPubMed

Type a question. Get a research brief.

Every answer links back to the exact moment someone said it on the record, so you can see where experts actually agree, disagree, or quietly change their mind.

Skip the listening. Keep the signal.

Cited Research Briefs

Ask any question. Get a synthesized brief with inline citations back to the exact source.

Contradiction Detection

See where experts agree and disagree on the same topic, with links to both sides.

Project Tracking

Define a research question. Sonic auto-finds supporting and contradicting evidence over time.

Entity Intelligence

Auto-generated profiles for every company and person, with sentiment and mention tracking.

Explore the database →

No signup needed · See it before you create an account

The highest-signal primary source nobody indexes

Podcasts, earnings calls, conferences, and interviews have become the most information-dense sources in the market. Almost none of it is searchable.

  • Fund managers disclose portfolio conviction on podcasts before public filings
  • Executives reveal guidance and competitive strategy on earnings calls and conference stages
  • Policymakers signal regulatory intent in interviews that never makes written testimony

Start a project. Let evidence come to you.

Define a research question and Sonic automatically surfaces supporting and contradicting evidence every time new audio comes in.

  • Auto-classifies every claim as supporting or opposing
  • Tracks the entities, domains, and questions you care about
  • Updates quietly in the background. A daily brief, not a feed

Making expert knowledge accessible and accountable

Expert insight is increasingly shared in conversations, not documents. The best-informed people are the ones with the most hours to listen.

  • Every claim is extracted, attributed, and searchable
  • Every source is linked and verifiable
  • Every finding synthesized with citations back to the original audio

If an expert said it out loud, you should be able to find it in seconds.

Built by professionals who spent years relying on expert conversations to inform high-stakes decisions. Our background in management consulting and institutional finance means we understand how research professionals actually consume, synthesize, and act on qualitative intelligence.

Built by alumni of

BCG

JPMorganChase

Stop listening. Start searching.

Search 400+ hours of expert conversations. Free during early access.