Interesting choice with telegram. I see it requires to get user's own Gmail api credentials?
I too recently launched AI automations for Gmail. I am a heavy email user, so connecting chatgpt to my inbox was obvious to me. When gpt-4 was released it passed my tests with 90% accuracy, so I've decided to release it at inboxchat.ai
But while I enjoy AI sorting my emails, the most useful feature for meturned out to be screener, inspired by this post: https://blog.nawaz.org/posts/2018/Sep/solving-my-email-probl.... It sends all emails from first-time or unknown senders into a separate Review Later label. If email is moved to Inbox, then that sender becomes trusted and is allowed into Inbox in the future. It's simple, dumb feature but so effective
I would use something like inboxchat.ai, sort of. What I want is to get proposed labels based on my usual labeling activity, and then I want to periodically login and review recommended labels for the activity (unlabeled unread pending email) in my inbox, where I would either speed edit some of the suggestions or accept the recommended labels.
While I have hundreds of auto-label filters already setup, there's always constantly more activity to consider. So having label recommendations could save a lot of time. Or proposed new filters based on common obvious labeling activity already occurring in my inbox.
Trello is great, I actually use it for this project:). The main difference (for now) is tracking documents. When I am job searching I usually have several versions of CVs and many versions of cover letters. Managing and tracking those isn't always the easiest thing. Hence, ConvertJob.
In great country of Kazakhstan, horse gallop to own final supper! .. seriously though, see the proto Sino-Caucasian reconstructed phoneme I posted above.
Yes-yes I understand that. There could be two networks: bitcoin and bitcoinxt. And people could choose between the two. So why is that bad? I am asking genuinely
This is an interesting article but very one sided. To really assess "the wisdom of HN community" the author should have assessed all four cells: Successful companies with positive comments, Successful companies with negative comments (which the author did), Unsuccessful companies with positive comments and Unsuccessful companies with negative comments. This would provide a broader and more objective picture of HN community
It's okay to give them half a billion dollars in loans because others got billions? Why not be outraged at everyone involved? The industry is colossally inefficient.
Inefficient when it comes to innovating, yes. In any industry dominated by powerful incumbents and where the startup capital costs are extremely high, you do need outside intervention (I.e. a subsidy in the form of a loan) to help newcomers.
So any startup that competes in the pharmaceutical sector or biotechnology industry should be given hundreds of millions of dollars in taxpayer-funded loans?
I am not outraged at anyone, except previous commenter. But to your point, yes it is okay to give them half a billion. I don't see why government should not have supported them. And as time has shown it was a right decision, since they have paid off that loan, which I think is incredible for an only electric cars company.
I too recently launched AI automations for Gmail. I am a heavy email user, so connecting chatgpt to my inbox was obvious to me. When gpt-4 was released it passed my tests with 90% accuracy, so I've decided to release it at inboxchat.ai
But while I enjoy AI sorting my emails, the most useful feature for meturned out to be screener, inspired by this post: https://blog.nawaz.org/posts/2018/Sep/solving-my-email-probl.... It sends all emails from first-time or unknown senders into a separate Review Later label. If email is moved to Inbox, then that sender becomes trusted and is allowed into Inbox in the future. It's simple, dumb feature but so effective
reply