31–40 of 55 posts
the need for more web search indices is indeed dire given landscape with agents and providers turning into walled gardens means that independent ones are definitely going to be needed, but just seems insurmountable when building actual index is so costly. Maybe just purely pareto efficient of serving 80% of requests or something is good enough.
The latency of 5s for the basic tier search request is very confusing to me. Is that 5s per request or 5s per 1k requests? If it is indeed 5s per request that seems like a deal breaker
This is a search agent available in the cloud. The site mentions that they doesn't optimize for being "done in milliseconds and as cheaply as possible", and that they do a lot more work like extracting relevant paragraphs and "Single-call resolution for complex queries that normally require multiple search hops" and more. Geared to be consumed by other agents, hence the latency may be tolerable. They have the advanta…
The fact that GPT-4.1 was the judge does not convince of the validity of the bench.
it's an odd choice. I'd be curious why they picked that. it's not the cheapest, most expensive, best, or worst. It does have a relatively large context window, and ime is very good at format adherence
I agree there is a need for such APIs. Using Google or Bing isn't enough, and Exa and Brave haven't clearly solved this yet.
I've been saying for quite some time now that AI is going to kill the traditional (free) search engine. This is just another nail in the coffin. When an AI searches google.com for you, the ads never get shown to the user. Search engines like kagi.com are the future. You'll give the AI your Kagi API key and that'll be it. You won't even need cloud-based AI for that kind of thing! Tiny, local models trained for perform…
if you say it for long enough, i'm sure you will be right!
> Traditional search engines were built for humans. They rank URLs, assuming someone will click through and navigate to a page. The search engine's job ends at the link. The system optimizes for keywords searches, click-through rates, and page layouts designed for browsing - done in milliseconds and as cheaply as possible.
> ... AI search has to solve a different problem: what tokens should go in an agent's context window to help it complete the task? We’re not ranking URLs for humans to click— we’re optimizing context and tokens for models to reason over.
I pay for a lot of tools, but patterns like this leave me with a really bad impression.
I get that everyone wants to piggyback on the common-ness of words, but it'd be a lot cooler if they _didn't_.