Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Agent2Agent Protocol (A2A)

developers.googleblog.com

Post reply on HN
Print view View original

181–190 of 293 posts

Re: The Agent2Agent Protocol (A2A)

#181

Post by IanCal »

simonw wrote: post #144
abshkbh wrote: post #138

Earlier quoted context omitted.

Morden software consists of separation of responsibilities between services and a higher plane orchestrating the data flow for business logic. If you believe there is value in fuzzy tasks being done by LLMs then from that it follows that having separate "agent" services with a higher order orchestrator would be required. Each calling LLMs on their own inside.

I don't buy it. Why would I want my LLM to talk to some other LLM and introduce even more space for weird, non-deterministic bugs when I could have my LLM call a deterministic API to achieve the same thing?

Why do you assume there's a deterministic API doing the same thing?

Re: The Agent2Agent Protocol (A2A)

#184

Post by low_tech_punk »

low_tech_punk wrote: post #183

But, why do they launch Firebase Studio ( https://firebase.blog/posts/2025/04/introducing-firebase-stu... ) on the same day? I wonder if this is a timed.

Of course, there is Ironwood announce too: https://blog.google/products/google-cloud/ironwood-tpu-age-o...

Re: The Agent2Agent Protocol (A2A)

#185

Post by rukuu001 »

What’s really interesting about this is the broad support Google has drummed up among platforms.

So it’s actually looks like a strategic focus, rather than just announcement for interest, relevance or whatever

Re: The Agent2Agent Protocol (A2A)

#186

Post by lta »

darepublic wrote: post #158

Langchain is a technology partner? People just love bloat and abstraction for its own sake huh. Screw google and screw this protocol

Would have made a similar comment if I hadn't found yours. Google starts to inspire the same bloaty feeling as MS. I feel sad

Re: The Agent2Agent Protocol (A2A)

#187

Post by daxfohl »

So we have MCP for USB, A2A for network. Next we'll need a protocol for nonvolatile storage, one for volatile storage that can be paged into context, interrupts or something for debugging. Definition of kernel/userland or rings. What else before an AI model can serve as a fuzzy CPU?

Re: The Agent2Agent Protocol (A2A)

#188

Post by HumanOstrich »

TeMPOraL wrote: post #156
qwertox wrote: post #91

Earlier quoted context omitted.

Should security be part of the protocol? Both the host and the client should make sure to sanitize the data. How else would you trust a model to be passing "safe" data to the client and the host to pass "safe" data to the LLM?

There is no such thing as "safe" data in context of a general system, not in a black-or-white sense. There's only degrees of safety, and a question how much we're willing to spend - in terms of effort, money, or sacrifices in system capabilities - on securing the system, before it stops being worth it, vs. how much an attacker might be willing to spend to compromise it. That is, it turns into regular, physical world…

Are you generating these replies with an LLM?

Edit: My apologies then.

Re: The Agent2Agent Protocol (A2A)

#189

Post by sneak »

fragmede wrote: post #165
delusional wrote: post #105

Earlier quoted context omitted.

At some level everything has to go in a single band. I don't have separate network connections to my house, I don't send separate TCP SYN packets for each "band". I don't have separate storage devices for each file on my harddrive. We multiplex the data somewhere. Yhe trick to it is that the multiplexer has to be a component, and not a distributed set of ad-hoc regexes.

at some level, sure, but I can no longer put +++ATH0 into my comment and have it hang up your connection, so it's worth some effort to prevent the problem.

Strictly speaking, that only works with a three second delay between the third + (at which you receive “OK”, indicating a mode switch from data mode back to command mode) and the AT command (which is then interpreted as a command and not data).

Anything that would hang up on seeing that string as a monolith was operating out of Hayes spec.

Re: The Agent2Agent Protocol (A2A)

#190

Post by simonw »

IanCal wrote: post #181
simonw wrote: post #144

Earlier quoted context omitted.

I don't buy it. Why would I want my LLM to talk to some other LLM and introduce even more space for weird, non-deterministic bugs when I could have my LLM call a deterministic API to achieve the same thing?

Why do you assume there's a deterministic API doing the same thing?

Because if a company built an LLM that can perform actions, they almost certainly did that by building an API first for it to use as a tool.
Post reply on HN