myzie
Joined 10 years ago
Karma
110
Submissions
69
Member since
Nov 22
Recent submissions
Comment · 28 days ago
Yeah, I was mainly thinking about how much cheaper Luna appeared to be in this case.
Comment · 28 days ago
Interesting that you have gpt-6-luna at $0.01 vs. claude-haiku-5-5 at $0.16 for this task. I see the score disparity though and I played them briefly. My takeaway from this is that the choice between Luna and Haiku 5.5 may remain nuanced. Luna may be a lot cheaper still and good enough for some jobs. Is that your read of the results?
Comment · 1 month ago
Looks like you can opt-out of having an environment via
`environment.type: "none"`
When there is an environment, my impression is it's a floor of 5 minutes at that 1 GB @ $0.03/20 min rate. So $0.0015/minute * 5 minutes = $0.0075 minimum charge per activated environment.
https://developers.openai.com/api/docs/guides/agents-api/ses... https://developers.openai.com/api/docs/pricing#built-in-tool...
Comment · 1 month ago
I built several harnesses in different products over the last two years. Fully agree with you that doing it right is a rabbit hole. Certain system properties that you almost always want in a harness used within a SaaS (for example) are non-obvious at the start and require certain architectural choices. It's easy to start down a path and then find a gap a couple days before launch.
Async tool calls, having the agent wait indefinitely for a human response, and showing a form or questions to the user via a tool call are a few common capabilities that come up that a product manager might miss at first.
This is why I've been building Nvoken. LLM agnostic, ergonomic SDKs, flexible tool call patterns, tenant and user-aware budget enforcement, etc.
I'd really appreciate any and all feedback on this! It gives you some free tokens on signup and it's super quick to try.
Comment · 1 year ago
The Chrome extension approach may shift some (most?) of the risk to the end user, since technically they are now the one scraping. Theoretically getdex would be relatively better off in this arrangement, while putting their customers into a legal gray area.
Comment · 1 year ago
Related research on past litigation in this area for anyone that wants to go deeper:
https://deepnoodle.ai/research/linkedin-legal-battles-tos-vi...
Comment · 1 year ago
Currently, yes. However it's quite early and I'm exploring whether this is the best option.
The reason I was posting here on HN is to see if anyone more technical may be interested in this as well. E.g. to leverage an API like this with AI agents or otherwise.
Comment · 1 year ago
https://github.com/diveagents/dive
Dive orchestrates multi agent workflows in Go. Take a look and let me know what you think.
Comment · 1 year ago
+1 to the article.
Along these lines, I'm building Dive:
https://github.com/diveagents/dive
When building a SaaS with a Go backend, it's nice to be able to have the option of the agents and workflows being in the same process. And being confident in the ability of that to scale well.
While it's true that Go lacks good ML libraries, for some this isn't too consequential if your app is primarily using Anthropic or OpenAI and a database that offers semantic or hybrid search for RAG. The ML is done elsewhere. Plus it could be that you can leverage MCP servers and at that point you're language agnostic.
Regarding the concurrency model approach with Go and agents, I initially baked a message based approach (a la the Actor model, with one goroutine per agent) into Dive Agents, but eventually found that this would be better implemented as another layer. So currently in Dive it's the user's choice on how to implement concurrency and whether to use messaging. But I anticipate building that back in as an optional layer.
Comment · 1 year ago
Risor is an embedded scripting library and CLI for Go. This release adds new modules for web crawling, background scheduling, and more. Happy scripting.