Here is a typical Russian milblogger channel. Note ”owning the libs” type naming.
Are you still surprised MAGA supports Russia?
I think they actually look up to Russia, honestly, and would love nothing more than the USA to become more like Russia.
Russian brashness and embracing being the bully excites them. Maybe even makes them jealous.
I’m excited to share my newest blog post, "Don't sure cosine similarity carelessly"
https://p.migdal.pl/blog/2025/01/dont-use-cosine-similarity
We often rely on cosine similarity to compare embeddings—it's like “duct tape” for vector comparisons. But just like duct tape, it can quietly mask deeper problems. Sometimes, embeddings pick up a “wrong kind” of similarity, matching questions to questions instead of questions to answers or getting thrown off by formatting quirks and typos rather than the text's real meaning.
In my post, I discuss what can go wrong with off-the-shelf cosine similarity and share practical alternatives. If you’ve ever wondered why your retrieval system returns oddly matched items or how to refine your embeddings for more meaningful results, this is for you!
`
I want to thank Max Salamonowicz and Grzegorz Kossakowski for their feedback after my flash talk at the Warsaw AI Breakfast, Rafał Małanij for inviting me to give a talk at the Python Summit, and for all the curious questions at the conference, and LinkedIn.
Efficient #Deep Pre-trained Sentence #Embedding Model for #Similarity Search #by Khushboo Taneja, Jyoti Vashishtha and Saroj Ratnoo
Similarity and continuity are manifestations of difference. Just specific types of differences repeatedly constructed over a certain period of time-space.
Plutarch notes that friendship arises out of and is sustained by similarities of habits, character, outlooks, feelings, & other matters. Flatterers know this, and for that reason imitate similarity with their targets
https://youtu.be/uTw_6PBnOW4
#Video #Plutarch #Friendship #Flattery #Imitation #Similarity
We were not accepted into Google Summer of Code. So, we started our own
https://qdrant.tech/blog/qdrant-summer-of-code-24/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant
PS If they only had a slightly invested #phylogeneticist at hand; they easily could have learned a lot about the strengths and weaknesses of their data and preferred tree (a Bayesian MRC, by the way, is a summary tree of various competing topologies sampled in the MCMC chain, not a phylogenetic tree)
Here's a quick #NeighbourNet based on their "toutes" matrix (inferred in less than a minute), annotated.
Overall #similarity makes #clades, surprise, surprise.
Qdrant, the Vector Search Database, raised $28M in a Series A round
https://qdrant.tech/blog/series-a-funding-round/
#ycombinator #vector_search_engine #neural_network #matching #SaaS #approximate_nearest_neighbor_search #image_search #recommender_system #vectors #knn_algorithm #hnsw #vector_search #embeddings #similarity #simaes_networks #BERT #transformer #word2vec #fasttext #qdrant
Ist euch eigentlich mal aufgefallen, dass "Alle meine Entchen" in moll gesungen
die israelische Nationalhymne ergibt?
'Quantifying Network Similarity using Graph Cumulants', by Gecia Bravo-Hermsdorff, Lee M. Gunderson, Pierre-André Maugis, Carey E. Priebe.
http://jmlr.org/papers/v24/21-082.html
#subgraph #graph #similarity
$f$-MICL: Understanding and Generalizing InfoNCE-based Contrastive Learning
The Vendi Score: A Diversity Evaluation Metric for Machine Learning
Dan Friedman, Adji Bousso Dieng
Action editor: Antonio Vergari.
ContraSim – Analyzing Neural Representations Based on Contrastive Learning
The Vendi Score: A Diversity Evaluation Metric for Machine Learning
Hacker News 
