TechPulseTechPulse
Back to News
Advertisement
Advertisement

⚡ Community Insights

Discussion Sentiment

100% Positive

Analyzed from 186 words in the discussion.

Trending Topics

#skills#loop#ironbee#figure#testing#took#opus#thing#verification#method

Discussion (7 Comments)Read Original on HackerNews

bel8•about 2 hours ago
From what I understood, the gist of it is that uses a bunch of skills in a loop to help LLMs solve the tasks better via browser-testing, debugging, visual-testing, etc..

The skills can be found here:

https://github.com/ironbee-ai/ironbee-devtools-skills/tree/m...

Question that was left unanswered:

How much longer does a 4x DeepSkeep loop took compared to Opus?

_aavaa_•about 3 hours ago
Seems interesting, but buried under a mountain of written slop.
rightbyte•about 2 hours ago
It is marketing for some SaaS thing. However, I think something like this, "verification loops with some sort of tricks", is what Anthropic and "OpenAI" do behind the scene with their interfaces.
sozal•about 3 hours ago
Fair on the length. The verification loop took DeepSeek from ~20 to ~80 on Web-Bench, matching Opus at ~7x less cost. Curious if the method holds up for you.
_aavaa_•about 2 hours ago
Well I don’t know what the method is, there’s a mention of ironbee, but I’m not willing to spend the time digging through this to figure out what’s needed and how to set it up.
alexgoodhart•about 2 hours ago
You could literally send it to an ai
scotty79•about 2 hours ago
> I’m not willing to spend the time digging through this to figure out what’s needed

That's the neat part. You don't... need to do this yourself nowadays. AI agent is perfectly capable to figure out any new open source thing that pops up daily now. You can just give it the link to the repo and say "Set this up for me. I wanna play with it."