Hacker News Reader

che_shr_caton DeepConf: Scaling LLM reasoning with confidence, not just compute

I'm the author of this blog. That's correct, the texts are generated and then validated manually by me.

I also do manual reviews (https://gonzoml.substack.com/), but there are many more papers for which I don't have time to write a review. So I created a multi-agentic system to help me, and I'm constantly iterating to improve it. And I like the result. It was also validated by the paper authors a couple of times, they agree the reviews are correct. So, if you see something is definitely wrong, please let me know.

Regarding myself, I became at least x10 more productive in reading papers and understanding what's happening. Hope, it will also help some of you.

che_shr_caton Deep Learning with Jax

Thank you for the feedback! I'm the author of the book :)

che_shr_caton Big Post About Big Context

I updated the post a bit, added a few clarifications

che_shr_caton Big Post About Big Context

the close example is Machine translation quality estimation (MTQE)

che_shr_caton Big Post About Big Context

That means the models still confabulate and make other errors, and for many cases it's a problem, so there should be solutions to control model output quality

che_shr_caton Hardware for Deep Learning, Part 3: GPU

The original plan was this:

https://blog.inten.to/hardware-for-deep-learning-current-sta...

che_shr_caton Hardware for Deep Learning, Part 3: GPU

Thanks!

che_shr_caton Hardware for Deep Learning, Part 3: GPU

Many companies designed or designing their own chips. The most prominent example is Google TPU.

There will be another articles in this series on FPGAs, ASICs and so on.

che_shr_caton 19 Machine Translation engines compared for 48 language pairs

Cool report! No single best provider :)

che_shr_caton Cloud Sentiment Analysis – Vendor Overview (April 2018)

It seems to be so inefficient market!..