/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 allenai.org
Tülu 3: The next era in open post-training | Ai2
| | bdtechtalks.com
Under the hood: The Innovations powering DeepSeek's AI breakthrough - TechTalks
4.5 parsecs away

Travel
| | Here is how DeepSeek models disrupted AI norms and revealed that outstanding performance and efficiency don't require secrecy
| | amatria.in
Beyond Token Prediction: the post-Pretraining journey of modern LLMs - AI, software, tech, and people. Not in that order. By X
2.9 parsecs away

Travel
| | (This blog post, as most of my recent ones, is written with GPT-4 assistance and augmentation)
| | ljvmiranda921.github.io
A lexical view of contrast pairs in preference datasets
5.4 parsecs away

Travel
| | Preference data is a staple in the final step of the LLM training pipeline. During RLHF, we train a reward model by showing pairs of chosen and rejected mode...
| | blog.adnansiddiqi.me
5 Application Security Best Practices for 2023 | Adnan's Random bytes
7.4 parsecs away

Travel
| Image Source What Is Application Security? Application security is the practice of protecting computer systems and applications from threats and vulnerabilities. This includes measures to prevent unauthorized access, modification, use, destruction, disruption, or disclosure of an application or its data Application security is important because applications are often the primary targets of cyber attacks. Hackers