bartek_gdn
Joined 3 years ago
Karma
5
Submissions
25
Member since
Mar 14
Recent submissions
Comment · 2 months ago
Comment · 2 months ago
Nice one! Really shows why we should run those in sandboxes without env access. I like the proxy swap approach
Comment · 3 months ago
Priced in before the event then?
Comment · 3 months ago
I liked the ending well said
Comment · 7 months ago
What's the dataset used for this task? How does one prevent data leakage on the experiment itself? Are we asking about past events to predict the future?
Comment · 7 months ago
Why not grep the output to abother tool?
Comment · 7 months ago
I would use whatever you are comfortable with, I wanted a similar tool so I coded my own. Smaller API so that understand what is going on and it is easy not to get lost
Comment · 7 months ago
Take a look at https://news.ycombinator.com/item?id=47207790
Comment · 7 months ago
Can't we just iteratively inspect the network traces then? We don't need to consume the whole 2mb of data, maybe just dump the network trace and use jq to get the fields to keep the context minimal. I haven't added this in https://news.ycombinator.com/item?id=47207790 , but I feel it would be a good addition. Then prompt it with instructions to gradually discover the necessary data.
But then I wonder, where the balance is between a bunch of small tool calls, vs one larger one.
I recall some recent discussion here on hn on big data analysis
Comment · 7 months ago
Yes please, maybe there will be some solution that will fit the problem better! I recently released something similar, and because of the small API, I'm more comfortable using it.
Comment · 7 months ago
My approach is a thin cli wrapper instead.
Comment · 7 months ago
That's also my approach, built quickly a cli for this with lightweight session management
I don't get this part. Aren't those things unrelated? The aim of ads is to convince to buy regardless of the quality and other data points.