Feed aggregator

OpenClaw Hermes AI Agent Social Network.Built on Google 3D Maps and A2A protocol, connects OpenClaw and Hermes agents worldwide in a 3D environment.

They can Make friends and even date other Agents. Earn money and make a living. Create their own organizations or form alliances. Explore the world and discover treasures. Find place interesting. Compete or collaborate with others.

Comments URL: https://news.ycombinator.com/item?id=48473221

Points: 3

# Comments: 0

Article URL: https://webassembly.github.io/spec/core/

Comments URL: https://news.ycombinator.com/item?id=48473209

Points: 3

# Comments: 0

Article URL: https://ecfr.eu/publication/home-alone-europeans-are-ready-to-defend-themselves/

Comments URL: https://news.ycombinator.com/item?id=48473204

Points: 4

# Comments: 0

Article URL: https://webcli.sh

Comments URL: https://news.ycombinator.com/item?id=48473198

Points: 1

# Comments: 0

> For Fable 5, Mythos 5, and future models on Bedrock with similar or higher capability levels, Anthropic will require 30-day retention for all traffic on Mythos-class models. Retaining data for a limited period allows Anthropic to detect patterns of misuse that are not visible from a single exchange. Once you opt into data retention, your data will leave AWS’s data and security boundary.

From the announcement here: https://aws.amazon.com/blogs/aws/anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-safeguards-now-available/

> After 30 days, the data is deleted automatically, except in the rare cases where it's part of a safety investigation or we're legally required to keep it.

From: https://support.claude.com/en/articles/15425996-data-retention-practices-for-mythos-class-models

Comments URL: https://news.ycombinator.com/item?id=48473166

Points: 9

# Comments: 1

Article URL: https://vulpesetleo.substack.com/p/british-veterans-missing-out-on-jobs

Comments URL: https://news.ycombinator.com/item?id=48472994

Points: 2

# Comments: 0

Article URL: https://github.com/valkor-ai/loom

Comments URL: https://news.ycombinator.com/item?id=48472991

Points: 1

# Comments: 0

Article URL: https://devblogs.microsoft.com/commandline/powertoys-0-100-is-here-new-shortcut-guide-command-palette-improvements-and-much-more/

Comments URL: https://news.ycombinator.com/item?id=48472990

Points: 1

# Comments: 0

Article URL: https://ctd.clinic/

Comments URL: https://news.ycombinator.com/item?id=48472975

Points: 1

# Comments: 0

Article URL: https://zackoverflow.dev/writing/why-does-tsgo-use-so-much-memory/

Comments URL: https://news.ycombinator.com/item?id=48472960

Points: 1

# Comments: 0

Article URL: https://www.panasiti.me/blog/how-to-build-agentic-rag-with-rubyllm-and-rails/

Comments URL: https://news.ycombinator.com/item?id=48472952

Points: 1

# Comments: 0

Article URL: https://medium.com/empirical-engineer/gepa-wrote-its-own-legal-rubric-and-caught-33-more-unfair-contract-clauses-913a2d7d8ad5

Comments URL: https://news.ycombinator.com/item?id=48472943

Points: 1

# Comments: 0

Article URL: https://pgm.di.unipi.it/

Comments URL: https://news.ycombinator.com/item?id=48472942

Points: 1

# Comments: 0

Article URL: https://mail.openjdk.org/archives/list/jdk-dev@openjdk.org/thread/AIA3O3LHFZ6T7TIPH7KZT4WS4B6U72U5/

Comments URL: https://news.ycombinator.com/item?id=48472941

Points: 2

# Comments: 0

Article URL: https://www.nbcnews.com/news/us-news/nick-reiner-seeks-access-trust-parents-left-pay-defense-killings-rcna349160

Comments URL: https://news.ycombinator.com/item?id=48472903

Points: 2

# Comments: 0

The last time I posted here, I asked for help figuring out why the AI-generated website（voloshow). I had spent months building wasn’t getting any customers. I’m really grateful for all the replies I got. Many people shared their thoughts and pointed out technical issues and UX problems on the site, which helped me a lot. I’ve recently made another round of improvements to the website, and I’d love for everyone to try it again. Please leave your thoughts and feedback below, and include your voloshow account as well. I’ll choose 10 people and give them Plus access to the website. Thank you, truly.

Note: To protect your privacy, please replace some letters in the email address on your account with asterisks.

Comments URL: https://news.ycombinator.com/item?id=48472902

Points: 1

# Comments: 0

Article URL: https://media.mercedes-benz.com/en/article/bebac2af-acdc-465a-9538-adb0bf3d8ccf

Comments URL: https://news.ycombinator.com/item?id=48472877

Points: 2

# Comments: 0

Yet another "talk to your data and build a dashboard" app, where data does not leave your browser.

You ask a question, agents produce multiple SQL queries to in-browser sqlite, never seeing results, and write dashboard configuration code. The data you analyze will be indexed with a local semantic index (embeddings generation + sqlite vector search fully local).

Next, sandboxed QuickJS runs this code to produce rich dashboards directly in your browser, no backend attached. This is a fully frontend app (except OpenRouter or other remote LLM).

All data sent to LLM's is heavily sanitized and obfuscated at several points. The remote LLM never sees the contents of data it analyzes. Why does it exist - I started this is a testbed for my local-first AI projects, agentic workflows and contextual data analysis experiments.

It grew into a tool I use daily for quick and dirty data analytics when I don't want to waste time debugging SQL or building charts for simple data questions, when I literally need an answer under 10s.

I also don't like the idea of sharing random data in Claude/ChatGPT chat, neither uploading any work-related datasets to them. Plus they both often choke on tiny 100k rows data.

Fully open-sourced under MIT https://github.com/eatmydata-org/eatmydata, run it yourself it's a static web app.

What's in the box:

- SQLite OPFS adapted from wa-sqlite, data queried only locally;

- TurboQuant semantic indexing extension for sqlite (MIT-licensed);

- Quantized PII detection and embedding generation models straight in browser;

- NER and embeddings inference engines in zero-dependency C and wasm-simd128 optimizations (1.7x faster and 38x lighter binary compare to onnxruntime);

- QuickJS sandbox for AI-generated code;

- Orchestrator <-> SQL Planner <-> Coder agent loop that build SQL and dashboards from user query;

- Apache ECharts for dashboards;

- Fork of xslx Community edition to support styles (missing in OSS version upstream).

Hope it'll be useful to anyone who is interested in local-first stuff.

Comments URL: https://news.ycombinator.com/item?id=48472867

Points: 1

# Comments: 0

Article URL: https://blog.documentfoundation.org/blog/2026/06/08/an-open-letter/

Comments URL: https://news.ycombinator.com/item?id=48472866

Points: 1

# Comments: 0