TrainLoop

32 posts

TrainLoop

TrainLoop

@TrainLoop_ai

Reasoning fine-tuning.

san francisco, ca 参加日 Ocak 2025
23 フォロー中402 フォロワー
TrainLoop がリツイート
Joan Cabezas
Joan Cabezas@josancamon19·
🧵 Labs and VC's are throwing cash at RL environments, especially for computer and browser use. Yet, with just 4 customers and over 30+ vendors, is cloning every website in the world really the path to scale? of course not. Introducing TRACE: Trajectory Recording and Capture of Environments.
English
6
10
77
9.5K
TrainLoop がリツイート
Avi Peltz
Avi Peltz@avimakesrobots·
Only the best companies use @superset_sh had a lot of fun onboarding @TrainLoop_ai. If you are a cracked MLE and want to jump on a rocket ship with crazy high talent density hit them up 🚀
Kiet@FlyaKiet

@TrainLoop_ai is one of those companies in our group office hour that has something special. They're hitting an exponential curve and are now hiring more cracked engineer! Had a great time onboarding @jackson_stokes and @mlpierce22 to Superset yesterday with @avimakesrobots

English
2
2
11
1.6K
Kiet
Kiet@FlyaKiet·
@TrainLoop_ai is one of those companies in our group office hour that has something special. They're hitting an exponential curve and are now hiring more cracked engineer! Had a great time onboarding @jackson_stokes and @mlpierce22 to Superset yesterday with @avimakesrobots
Kiet tweet mediaKiet tweet mediaKiet tweet media
English
2
1
10
3.7K
TrainLoop
TrainLoop@TrainLoop_ai·
New on the TrainLoop blog: MAE, MSE & R² — Making Sense of Model Errors We break down Mean Absolute Error (MAE), Mean Square Error (MSE), and R-Squared -- three core metrics that shape how we judge model performance. Link to blog -- trainloop.ai/blogs/simple-e…
TrainLoop tweet media
English
0
0
2
453
TrainLoop
TrainLoop@TrainLoop_ai·
A bite-sized explainer on how LLMs learn - end to end. Core ideas without the math. Follow @TrainLoop_ai for our plain-language blog series that dives deeper into each concept.
English
0
0
3
325
TrainLoop
TrainLoop@TrainLoop_ai·
Cut through the AI model post-training confusion with @TrainLoop_ai.
English
0
0
3
256
TrainLoop
TrainLoop@TrainLoop_ai·
With @TrainLoop_ai , AI model training outcomes are predictable, repeatable, and sustained --- not blind trial-and-error.
English
0
0
2
223
TrainLoop
TrainLoop@TrainLoop_ai·
Precision vs. Recall 🤔 Always confused between the two? You’re not alone. We broke it down in plain English + a 2-min “Wild Fire” game 🔥 After this, you’ll never mix them up again : 👉 trainloop.ai/blogs/importin…
English
0
0
5
225
TrainLoop
TrainLoop@TrainLoop_ai·
AI model training isn’t about getting lucky -- your competitive advantage depends on it. With TrainLoop fine-tuning, you trade chance for control.
English
0
0
5
176
TrainLoop
TrainLoop@TrainLoop_ai·
Have you ever spotted a four-leaf clover? 🍀 We’d love to hear your story if you have!
English
0
1
4
182
TrainLoop
TrainLoop@TrainLoop_ai·
How accurate is your model? Before you think about it, Here's another one - what is 'accuracy', really?
English
0
0
3
157
TrainLoop
TrainLoop@TrainLoop_ai·
The coffee machine is in the house! And we have started running some experiments. We are a Research Lab after all!
TrainLoop tweet media
English
1
0
6
478
TrainLoop
TrainLoop@TrainLoop_ai·
Model evaluation is the broccoli of Machine Learning. 🥦🥦 At least we made it simpler -- our evals framework is now open-source → github.com/TrainLoop/evals
English
0
1
2
166
TrainLoop
TrainLoop@TrainLoop_ai·
So many good-looking things in one frame. Also, here’s our new office in North Beach. If you’re around, come say hello.
TrainLoop tweet media
English
4
1
16
2.4K
TrainLoop
TrainLoop@TrainLoop_ai·
When you fine-tune your AI model without a “map”, it will wander. Random tweaks = random outcomes. TrainLoop gives your fine-tuning process structure, direction, and control - so you land where you intend, not where the currents take you
English
0
0
6
211
TrainLoop がリツイート
Mason Pierce
Mason Pierce@mlpierce22·
Love this explanation on why AI models always generate outputs that seem good but don’t get anybody excited. This is the main reason why custom models are the future. A one-size-fits-all solution actually fits nobody
Mason Pierce tweet media
Ethan@torchcompiled

Every single RL paper for image-gen I've seen honestly the outputs look like SLOP. my gut is that the mean aesthetic preference, whats optimized for, is not a good preference, its kitsch. Is there a way we can sample individual aesthetic targets?

English
1
2
9
2K

ディスカバー

@superset_sh @FlyaKiet @jackson_stokes @mlpierce22 @avimakesrobots @elonmusk @BarackObama @taylorswift13