Manchester United manager Ruben Amorim questions the "choices" of people close to forward Marcus Rashford after he said he was ready for a "new challenge".
from BBC News https://ift.tt/wNunyih
from BBC News https://ift.tt/wNunyih
Monday, 23 December 2024
Sunday, 22 December 2024
Ange Postecoglou accuses Match of the Day's Steve Wilson of discounting the impact of Tottenham's defensive injuries after their 6-3 defeat by Liverpool.
from BBC News https://ift.tt/xTJLZ70
from BBC News https://ift.tt/xTJLZ70
Saturday, 21 December 2024
Former Manchester United defender Phil Jones and football analyst Statman Dave discuss why January is huge for Arsenal in this season’s title race.
from BBC News https://ift.tt/rqWwhC0
from BBC News https://ift.tt/rqWwhC0
Friday, 20 December 2024
LATEST NEWS
New top story on Hacker News: We're about to fly a spacecraft into the Sun for the first time
We're about to fly a spacecraft into the Sun for the first time
38 by pseudolus | 13 comments on Hacker News.
38 by pseudolus | 13 comments on Hacker News.
Last Christmas tops the festive chart for a second year running, but Band Aid misses the top 10.
from BBC News https://ift.tt/O4eXuwB
from BBC News https://ift.tt/O4eXuwB
Thursday, 19 December 2024
Wednesday, 18 December 2024
Tuesday, 17 December 2024
Monday, 16 December 2024
Sunday, 15 December 2024
Saturday, 14 December 2024
Friday, 13 December 2024
Thursday, 12 December 2024
LATEST NEWS
New top story on Hacker News: Show HN: Gentrace – connect to your LLM app code and run/eval it from a UI
Show HN: Gentrace – connect to your LLM app code and run/eval it from a UI
10 by dsaffy | 0 comments on Hacker News.
Hey HN - Doug from Gentrace here. We originally launched via Show HN in August of 2023 as evaluation and observability for generative AI: https://ift.tt/5KnQNxi Since then, everyone from the model providers to LLM ops companies built a prompt playground. We had one too, until we realized this was totally the wrong approach: - It's not connected to your application code - They don't support all models - You have to rebuild evals for just this one prompt (can't use your end-to-end evals) In other words, it was a ton of work and time to use these to actually make your app better. So, we built a new experience and are relaunching around this idea: Gentrace is a collaborative LLM app testing and experimentation platform that brings together engineers, PMs, subject matter experts, and more to run and test your actual end-to-end app. To do this, use our SDK to: - connect your app to Gentrace as a live runner over websocket (local) / via webhook (staging, prod) - wrap your parameters (eg prompt, model, top-k) so they become tunable knobs in the front end - edit the parameters and then run / evaluate the actual app code with datasets and evals in Gentrace We think it's great for tuning retrieval systems, upgrading models, and iterating on prompts. It's free to trial. Would love to hear your feedback / what you think!
10 by dsaffy | 0 comments on Hacker News.
Hey HN - Doug from Gentrace here. We originally launched via Show HN in August of 2023 as evaluation and observability for generative AI: https://ift.tt/5KnQNxi Since then, everyone from the model providers to LLM ops companies built a prompt playground. We had one too, until we realized this was totally the wrong approach: - It's not connected to your application code - They don't support all models - You have to rebuild evals for just this one prompt (can't use your end-to-end evals) In other words, it was a ton of work and time to use these to actually make your app better. So, we built a new experience and are relaunching around this idea: Gentrace is a collaborative LLM app testing and experimentation platform that brings together engineers, PMs, subject matter experts, and more to run and test your actual end-to-end app. To do this, use our SDK to: - connect your app to Gentrace as a live runner over websocket (local) / via webhook (staging, prod) - wrap your parameters (eg prompt, model, top-k) so they become tunable knobs in the front end - edit the parameters and then run / evaluate the actual app code with datasets and evals in Gentrace We think it's great for tuning retrieval systems, upgrading models, and iterating on prompts. It's free to trial. Would love to hear your feedback / what you think!
Wednesday, 11 December 2024
Tuesday, 10 December 2024
Monday, 9 December 2024
Crowds gather at notorious Damascus prison, as Assad flees to Russia.
from BBC News https://ift.tt/KPlVi3H
from BBC News https://ift.tt/KPlVi3H
Sunday, 8 December 2024
Saturday, 7 December 2024
Northampton Saints kick-start their Investec Champions Cup campaign with a comfortable bonus-point victory over Castres at a blustery Franklin's Gardens.
from BBC News https://ift.tt/Ilrx1np
from BBC News https://ift.tt/Ilrx1np
Friday, 6 December 2024
Thursday, 5 December 2024
Wednesday, 4 December 2024
Tuesday, 3 December 2024
Monday, 2 December 2024
Sunday, 1 December 2024
Red Bull’s Max Verstappen wins a dramatic Qatar Grand Prix that was brought to life by two mid-race safety cars and a penalty for McLaren’s Lando Norris.
from BBC News https://ift.tt/ZlS5x3f
from BBC News https://ift.tt/ZlS5x3f
LATEST NEWS
New top story on Hacker News: Show HN: Vicinity – Fast, Lightweight Nearest Neighbors with Flexible Back Ends
Show HN: Vicinity – Fast, Lightweight Nearest Neighbors with Flexible Back Ends
9 by Pringled | 0 comments on Hacker News.
We’ve just open-sourced Vicinity, a lightweight approximate nearest neighbors (ANN) search package that allows for fast experimentation and comparison of a larger number of well known algorithms. Main features: - Lightweight: the base package only uses Numpy - Unified interface: use any of the supported algorithms and backends with a single interface: HNSW, Annoy, FAISS, and many more algorithms and libraries are supported - Easy evaluation: evaluate the performance of your backend with a simple function to measure queries per second vs recall - Serialization: save and load your index for persistence After working with a large number of ANN libraries over the years, we found it increasingly cumbersome to learn the interface, features, quirks, and limitations of every library. After writing custom evaluation code to measure the speed and performance for the 100th time to compare libraries, we decided to build this as a way to easily use a large number of algorithms and libraries with a unified, simple interface that allows for quick comparison and evaluation. We are curious to hear your feedback! Are there any algorithms that are missing that you use? Any extra evaluation metrics that are useful?
9 by Pringled | 0 comments on Hacker News.
We’ve just open-sourced Vicinity, a lightweight approximate nearest neighbors (ANN) search package that allows for fast experimentation and comparison of a larger number of well known algorithms. Main features: - Lightweight: the base package only uses Numpy - Unified interface: use any of the supported algorithms and backends with a single interface: HNSW, Annoy, FAISS, and many more algorithms and libraries are supported - Easy evaluation: evaluate the performance of your backend with a simple function to measure queries per second vs recall - Serialization: save and load your index for persistence After working with a large number of ANN libraries over the years, we found it increasingly cumbersome to learn the interface, features, quirks, and limitations of every library. After writing custom evaluation code to measure the speed and performance for the 100th time to compare libraries, we decided to build this as a way to easily use a large number of algorithms and libraries with a unified, simple interface that allows for quick comparison and evaluation. We are curious to hear your feedback! Are there any algorithms that are missing that you use? Any extra evaluation metrics that are useful?