←back to thread

Building Effective AI Agents

(www.anthropic.com)
543 points Anon84 | 6 comments | 17 Jun 25 17:50 UTC | HN request time: 0.872s | source | bottom
1. chaosprint ◴[17 Jun 25 21:15 UTC] No.44304050[source]▶
Half a year has passed, and it feels like a long time in the field of AI. I read this article repeatedly a few months ago, but now I think the development of Agent has obviously reached a bottleneck. Even the latest gemini seems to have regressed.
replies(3): >>44304076 #>>44304162 #>>44304346 #
2. m3kw9 ◴[17 Jun 25 21:18 UTC] No.44304076[source]▶
They have hard time solving prompt issues injection and that’s a one of the bottle necks
3. EGreg ◴[17 Jun 25 21:29 UTC] No.44304162[source]▶
What exactly makes them regress?

Why can’t they just fork swarms of themselves, work 24/7 in parallel, check work and keep advancing?

replies(1): >>44304168 #
4. amelius ◴[17 Jun 25 21:31 UTC] No.44304168[source]▶
Because they are not intelligent. (And this is a good definition of it).
replies(1): >>44310028 #
5. jsemrau ◴[17 Jun 25 21:51 UTC] No.44304346[source]▶
(1) Running multiple agents is expensive, decreasing RoI. My DeepSearch agent for stocks uses 6 agents, and each query costs about 2 USD.

(2) Multi-agent orchestration is difficult to control.

(3) The more capable the model, the lower the need for multi-agents.

(4) The less capable the model, the higher the business case for narrow AI.

6. vonneumannstan ◴[18 Jun 25 14:06 UTC] No.44310028{3}[source]▶
How is that a regression?