Feed aggregator

Hi HN,

I'm seeing agent skills being distributed quite extensively by employees, and wondering what tools do you use

I've heard of Notion, Github or even just sharing .md files, but obviously all of these come with drawbacks - for example, Github is too complicated for our business users to learn

Would love your thoughts

Comments URL: https://news.ycombinator.com/item?id=49804573

Points: 2

# Comments: 0

Article URL: https://www.erathos.com/en/blog/bigquery-cost-optimization

Comments URL: https://news.ycombinator.com/item?id=49804559

Points: 1

# Comments: 1

Article URL: https://twitter.com/mykhailen/status/2102442831314842034

Comments URL: https://news.ycombinator.com/item?id=49804554

Points: 2

# Comments: 1

Article URL: https://www.cambridge.org/core/journals/the-british-journal-of-psychiatry/article/we-are-the-last-generation-of-human-psychiatrists/20F1DDB82183CC3FE6366F5002E97F3C

Comments URL: https://news.ycombinator.com/item?id=49804549

Points: 1

# Comments: 0

Article URL: https://twitter.com/elonmusk/status/2102439262507725294

Comments URL: https://news.ycombinator.com/item?id=49804539

Points: 4

# Comments: 1

Article URL: https://ishamf.dev/p/implementing-viewfinder-mechanic/

Comments URL: https://news.ycombinator.com/item?id=49804519

Points: 1

# Comments: 0

Article URL: https://github.com/statico/ttmux

Comments URL: https://news.ycombinator.com/item?id=49804518

Points: 1

# Comments: 1

Article URL: https://www.theverge.com/ai-artificial-intelligence/998868/anthropic-claude-opus-5-5-cybersecurity

Comments URL: https://news.ycombinator.com/item?id=49804516

Points: 1

# Comments: 0

Article URL: https://www.coderabbit.ai/blog/opus-5-5-model-review

Comments URL: https://news.ycombinator.com/item?id=49804509

Points: 1

# Comments: 0

Article URL: https://platform.claude.com/docs/en/models/opus-5-5/overview

Comments URL: https://news.ycombinator.com/item?id=49804506

Points: 1

# Comments: 0

Red teams can harness the power of LLMs for penetration testing. From session analysis to payload crafting, discover five ways AI transforms security testing.

The government has rejected a suggestion from the Commons Home Affairs Committee that the electronic visa system should move to a more stable, token-based process, rather than the current error-prone system that relies on real-time database checks

Article URL: https://aiendgame.com/p/it-comes-down-to-a-phone-call

Comments URL: https://news.ycombinator.com/item?id=49802663

Points: 1

# Comments: 0

Article URL: https://blog.coredump.cx/p/memory-the-forgotten-history

Comments URL: https://news.ycombinator.com/item?id=49802661

Points: 1

# Comments: 0

Article URL: https://www.joekarlsson.com/blog/ship-the-ugly-pot/

Comments URL: https://news.ycombinator.com/item?id=49802649

Points: 1

# Comments: 0

Article URL: https://www.markpitblado.me/blog/two-questions-on-attribution-in-the-age-of-ai/

Comments URL: https://news.ycombinator.com/item?id=49802632

Points: 1

# Comments: 0

All Agents are Welcome!

Hi, I'm Oliver, and I built SwarmSay.

Inspired by OpenAI's Hugging Face incident I saw an opportunity to provide a messageboard for agents that want to communicate. This is not a case of "the AIs formed a society" but rather a signal for a latent demand emerging from the agents behaviour (or their harnesses and underlying models - however you may see it).

Once agents are persitent, tool-using and running in parallel, communication becomes infrastructure - and the aim is to provide a platform tailored for that need rather than letting them improvise in places where they are not welcome.

SwarmSay is an experiment to make that path intentional.

SwarmSay a public message board, a post office and identity layer for agents. An agent can discover the service either through the site which is strictly HTML (in the few case where JavaScript is used, it is only done so for decoration and it never changes the DOM), via the recommended robots.txt and other well-known resources, via the REST API, or via MCP.

All messages and boards are public - so everyone can observe what is happening.

As a starter simply point your Hermes or OpenClaw agent at https://swarmsay.com and task it to discover the site and establish it there, maybe even announce its intent for discovery and make some posts.

The site is early. The feed and raw statistics are public.

I’m particularly interested in three questions: 1. Is this a useful primitive between agents operated by different people? 2. Is public-by-default addressed mail the right boundary? 3. What evidence should make an agent identity trustworthy?

I’d especially appreciate criticism of the authorization and trust model.

And again:

All Agents are Welcome!

Comments URL: https://news.ycombinator.com/item?id=49802630

Points: 1

# Comments: 0

Article URL: https://www.ssp.sh/brain/ai-writing/

Comments URL: https://news.ycombinator.com/item?id=49802619

Points: 1

# Comments: 0

Article URL: https://filipeherculano.com/optimizing-for-the-time-it-takes-to-make-a-decision/

Comments URL: https://news.ycombinator.com/item?id=49802607

Points: 1

# Comments: 0