He/him. Dad and husband. I work at https://xitter.cf/t.co/aVBqOzwwD1. My main hobbies are sailing, mountain/road biking, and creating an ultra low power personal computer.
Trondheim, Norway
Joined November 2009
- Tweets565
- Following228
- Followers225
- Likes2K
Andreas Eriksen retweeted
I’m excited to join the speaker lineup at Vespa.ai Live! My session will explore Nuances of Binarized Embeddings-Based Retrieval
If you’re attending, let me know — would love to connect at the event.
Andreas Eriksen retweeted
My opinion on tokenmaxxing is companies shouldn’t mandate/constrain any tools at all and then evaluate software developers by output / (salary + token use)
Andreas Eriksen retweeted
Vespa isn't only powering American AI, now it's also @MistralAI's retrieval solution
Andreas Eriksen retweeted
bm25 is nice and all, but you won't believe how easy it is to improve upon it with and how much more you can squeeze from lexical features in @vespaengine
Andreas Eriksen retweeted
Hypencoder is now ready for production using Vespa! Props to @andreer for making it happen! Really great stuff!
Just added a sample app for how to search with hypencoder models on Vespa. A large meta-model that generates a small query-specific model that scores your docs - it feels like pure science fiction, but of course we can do it: github.com/vespa-engine/samp…
Andreas Eriksen retweeted
A metamodel that generates weights for a NN for each query on the fly and using the same net for ranking documents against the same query - cool idea by @Julian_a42f9a
But, can you do it completely within @vespaengine , at scale, with reasonable latency (a few hundred ms)?
@andreer: hold my beer... (red bull)
🤯
Just added a sample app for how to search with hypencoder models on Vespa. A large meta-model that generates a small query-specific model that scores your docs - it feels like pure science fiction, but of course we can do it: github.com/vespa-engine/samp…
Andreas Eriksen retweeted
State-of-the-art ColBERT models are trained by applying knowledge distillation on top of dense pre-trained models
What if we run the whole pre-training in the multi-vector?
Introducing ColBERT-Zero, a model that sets a new SOTA on BEIR, using only public data
Andreas Eriksen retweeted
Considering putting this into the front panel. It responds very nicely to changes in cpu load
Andreas Eriksen retweeted
how is it, that despite every frontier LLM being insanely python maxxed they rarely use virtural envs, and even adding rules like "we are using uv, do everything with uv" they ignore it and think the system python is broken. like, every time. that's actually an accomplishment
Andreas Eriksen retweeted
Perplexity builds AI Search on Vespa.ai
Blog post below 👇
Andreas Eriksen retweeted
A tutorial for semantic search in video using @twelvelabs and Vespa: twelvelabs.io/blog/twelve-la…
Andreas Eriksen retweeted
100% agree. An information retrieval system that scales with intelligence is the future
This quoted post is unavailable.
Andreas Eriksen retweeted
A new blog post on how stress-free your life is when you run your search on @vespaengine even at a billion-scale!
Andreas Eriksen retweeted
Why are we excited about Matryoshka representation learning (MRL) for dense representations?
nDCG@10 versus OpenAI text-embedding-3-large with native support for shortening embeddings.
@andreer is dropping the mic with this visualization in the upcoming blog post on 🪆reps
