gauravsc

They're doing it for VCs because VCs consider it proof of traction. They're not doing it to impress you and they don't care whether you check stars or not.

I find this whole space of building tools for agents very interesting and fun. I am building similar software for agents e.g. agentreview.io and just posted about it on https://news.ycombinator.com/item?id=47488888

Apologies, the url went wrong while pasting, but I've reposted here: https://news.ycombinator.com/item?id=47072031

I am working on versanovatech.com. Its a learning layer for AI agents that lets them remember, share and learn from their experiences. I have built novasheets.com using the tech of versanovatech.com. It extract structured information from financial excel spreadsheets and is totally free to use.

well, I can't afford to analyse everyone's excel spreadsheets with my own money. But people can put a small amount of money in the account and restrict the money that can be spent with a given api key (if that's possible) and delete the api key after a while :)

Thanks. We think that while short term memory can be handled by LLMs directly and can be commoditised, it would be harder to do that natively for long term memory. We write about it in our article: https://medium.com/versanova/understanding-memory-in-ai-agen...

We have built something very close to it, a memory and learning layer called versanovatech.com and we posted about it here: https://news.ycombinator.com/from?site=versanovatech.com

thank you. we would love to provide you a demo and an api-key if you leave your contact on the website form.

I'm not sure how true that is for sectors other than software/AI, but in AI most academic researcher complain that all the moonshot research (often not even commercially applicable) is now solely coming from corporate research labs e.g. Deepmind, Facebook etc., as opposed to universities. They attribute this to poaching of faculty by companies, lack of resources in universities, lack of motivation in grad students to stay in academia.

https://jacobbuckman.com/2020-01-17-a-sober-look-at-bayesian...

"But in practice, BNNs do generalize to test points, and do seem to output reasonable uncertainty estimates. (Although it’s worth noting that simpler approaches, like ensembles, consistently outperform BNNs.)"

I think that it was Reliance Communications (Mukesh's brothers company) and not Reliance Jio that facebook hd tied up to deliver free basics. It is not the same company.

I guess going by the apple-samsung lawsuit, getting your patent validated in court seems to depend a lot on random chance as well.

Fadia is a piece of joke.

Why are you finding problems with app.net instead of focussing on it;s good parts and possibilities. You say and talk about some fundamental differences with companies facebook and apple, but why should anyone believe your assessment. Future can not be predicted in the world of technology and app.net has a good chance like any other company.

I eat my corn in spiral and I love analysis part of maths. I am doing my masters in data mining. I guess, it adds another data point to your findings.

Absolutely, things like these are the only hope for facebook's drowning fortune.

Everyone is sure that there will be an anti-congress wave in the next elections, but is that going to be divided between BJP and Anna party, is an important question.

This government is totally useless, ineffective, arrogant and insensitive.

Even Indians are not used to such large scale load shedding, where almost half of the country is without power.

The best part is that they have decided to promote the Power Minister Sushil Shinde as the Home Minister, now all the terrorist will die rolling on the floor laughing.

the rendered pages are not very accurate, they seem deformed.

India is good at producing cheaper technologies(PSLv is an example) and this will create a way for future tablet technologies to be cheaper and affordable.

lol, that's a funny comment!

thanks Colin, Can you please tell me the email ID on which to send the query? Thanks very much for your help, I can't find a contact us section here.

Yes, this post is visible but all my other posts(which are URL links) definitely are not visible. This "hell ban" phenomenon is something I am unsure of how I got, I didn't make any such comments in the past.

Exactly, I wish to know the algorithm that HN follows, it must be something really interesting.

We are using Dynamic programming and you are correct, knapsack is a problem but since the most common solution(and widely used) is using DP, we sometimes intermittently use the term Knapsack algorithm with DP algorithm to solve Knapsack problem.

Well as far as my knowledge goes, any sequence of steps to solve a problem is an algorithm(some are simple algorithms and some are complex). In our case we couldn't use fractional knapsack since we couldn't break images.

Plugin co-author: I have answered it in the above comments, see if that suffices.

Plugin co-author here: One more possible extension of this algo would be to use value of each image equal to the weight of each image. This would ensure best fit and would be one more way to make things look beautiful and arranged.