nkristoffersen

Joined 10 years ago

Karma
546
Submissions
287
Member since
Jan 11
[ my public key: https://keybase.io/nkristoffersen; my proof: https://keybase.io/nkristoffersen/sigs/-NgjNMRBLQhpM9gq4DMqUtAJX9LEfJfKFK8vxDqkLGg ]

https://[email protected]

View on Hacker News

Recent submissions

Comment · 1 year ago
Comment · 1 year ago
We are using over 50 billion LLM tokens for NLP/classification purposes per month. A mix of self hosted and cloud hosted models. But I have not attempted any fine tuning. Just prompt, (and perhaps more importantly) context “engineering”.
Comment · 1 year ago
We do a lot of things with podcast and other audio media at https://listenalert.com

But in general we found the best course of action is simply label everything. Because our customers will want those answers and rag won’t really work at the scale of “all podcasts the last 6 months. What is the trend of sentiment Hillary Clinton and what about the top topics and entities mentioned nearby”. So we take a more “brute force” approach :-)

Comment · 2 years ago
yes, definitely some skin deep similarities! We both transcribe podcasts, but what we do after that is very different ;-) (also, i'm a fan of his podcast).

There is also more generally Mention, Brand24, Meltwater, etc, in the media monitoring space. But all are generally weak in the audio media space.

When we stop looking at audio media like a newspaper article, things get more interesting.

Comment · 2 years ago
I'm working on a podcast and audio media monitoring and research platform. Easily the most complex thing I've built. But still so much more to do to make it truly useful. Testing PR and public affairs use cases at the moment.

https://listenalert.com

I used to work for a media monitoring company but was instantly struck by how old fashion everything was. And the total reliance on boolean searches meant only experts could find relevant information. This still appears to be the case for most players in the industry.

So I'm building a platform that finds what is important before you look for it. Novel entity linking, and sentiment analysis plus speaker tracking. It has come a long way from the proof of concept. Focused on audio media at the moment as it is the hardest to index compared to news articles in my opinion. And the hypothesis is audio media such as podcasts can contain so many juicy insights.

Next steps are converting pilot customers to paying customers, testing more markets (based in a tiny market now), raise a small pre-seed (bootstrapped at the moment), and quickly evolve the product based on feedback.

Comment · 2 years ago
You can actually create multiple widgets of the same type. So as many timezones or cities you want to track you can just keep adding timezone widgets.
Comment · 2 years ago
What kind of problems are you facing for entity extraction with 3.5? I am also currently working with 3.5 for entity extraction and entity linking. It is a fun pipeline but curious what issues you ran into?
Comment · 3 years ago
What makes you say that?

I can definitely argue that mirrorless is always better for most users! Thinner bodies, modern lens selection (so faster autofocus and wider aperture, etc), real-time image previews, better low-light preview (in both rear and viewfinder screens), video recording capabilities better match professional video cameras (by removing mirror complexity) which better matches the hybrid needs of the modern camera buyer.

Comment · 3 years ago
isn't "callback hell" a bit old fashioned now? With promises and async/await etc.
Comment · 3 years ago
Comment · 3 years ago
Even better when it says "[SPEAKS FOREIGN LANGUAGE]"
Comment · 4 years ago
Comment · 4 years ago
I’ve tried a few of these, and right now betteruptime gets my money :-)
Comment · 4 years ago
Try thinking outside your specific needs. The raw filesystem is an antiquated interface that, honestly, a vast majority of people do not need. In fact, if you observe average computer users, the filesystem is what really impedes their ability to get things done. In fact, the filesystem introduces a huge complexity when the application does not know where its files exist. Did the document you downloaded in the Downloads folder? The Desktop? Documents? Or is it in the last folder you downloaded? Users want to get things done, not hunt for files. The iPad paradigm solves a lot of regular user issues. It was never meant for "power programming users". The car vs. truck analogy.
Comment · 4 years ago
Best feature not really mentioned is Sidecar! Having a second high quality screen has been a game changer. So portable and so powerful. I will be upgrading my 2018 12.9 iPad Pro to the latest. Mostly for the better screen to match my M1 Max.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton