That was a major concern of mine.
That was a major concern of mine. You can set the Research mode to "Off" by default and check URLs on a case-by-case basis and still do custom searches. Admittedly, it takes some of the serendipity out of it, but it addresses your concern. I considered (and was planning on) adding a "block URL" feature - but the issue of how to store those sensitive URLs (to block) came up. Because localStorage and sync storage in Chrome is not sandboxed or encrypted, the blocked list would be "in the open" to other extensions. Yes, you could hash the urls you'd hope to block, but then there would be no way to read that list back to the user at a later point in time, and slight mismatches in URL schemes would lead to an imperfect system. So simply toggling Research Mode and researching pages of interest is the best option, IMO. I don't cache any personal info in localStorage or sync storage (which at least Chrome does not encrypt :< ). The api results are stored in a local variable within the scope of the extension. And the "history" is a hashed and padded blob. This is also why I released it for both Chrome and FF, since some people assign different use cases to different browsers. The code is also public/open-source.
Posted by spenvo on Aug 2, 2015, 11:07 PM
Tags
Related issues
- The biggest problem with having an LLM do this, from what I've observed of at least frontier models, is that the way they are trained...
- The biggest problem with MOND is that it was hand-crafted with additional parameters simply to fit the data.
- (My comment is about detached houses).
- The biggest problem with this is that I can't run my company's own internal benchmarks against this API, because they will be trained int...
- > steer Claude away from over-engineering parts of the system in response to hypothetical concerns.
- Why is there no comparison with FLUX 3 Image?
Raise real-world problems, find people facing the same issue, and discuss solutions.5,000 issues0 comments
hackernews (Other)
The biggest problem with having an LLM do this, from what I've observed of at least frontier models, is that the way they are trained...
NewThe biggest problem with MOND is that it was hand-crafted with additional parameters simply to fit the data.
(My comment is about detached houses).
The biggest problem with this is that I can't run my company's own internal benchmarks against this API, because they will be trained int...
> steer Claude away from over-engineering parts of the system in response to hypothetical concerns.
Why is there no comparison with FLUX 3 Image?
> our Git monorepo was developing an annoying problem Sentences like this are so common from people using monorepos that I am convinced ...
Why is there no contact form?
That was a major concern of mine.
That was a major concern of mine. You can set the Research mode to "Off" by default and check URLs on a case-by-case basis and still do custom searches. Admittedly, it takes some of the serendipity out of it, but it addresses your concern. I considered (and was planning on) adding a "block URL" feature - but the issue of how to store those sensitive URLs (to block) came up. Because localStorage and sync storage in Chrome is not sandboxed or encrypted, the blocked list would be "in the open" to other extensions. Yes, you could hash the urls you'd hope to block, but then there would be no way to read that list back to the user at a later point in time, and slight mismatches in URL schemes would lead to an imperfect system. So simply toggling Research Mode and researching pages of interest is the best option, IMO. I don't cache any personal info in localStorage or sync storage (which at least Chrome does not encrypt :< ). The api results are stored in a local variable within the scope of the extension. And the "history" is a hashed and padded blob. This is also why I released it for both Chrome and FF, since some people assign different use cases to different browsers. The code is also public/open-source.
Comments (0)
No comments yet. Start the discussion.