Deep Gains
Subscribe
Sign in
Home
Notes
Archive
About
Wharton’s vs MIT - Understanding the contrasting findings from recent AI studies
95% Fail vs 75% Win - why such a big difference in findings ?
Nov 12
•
Arun S
1
2
Most Popular
View all
Jailbreaking the censorship of DeepSeek R1 - detailed steps with video
Jan 31
•
Arun S
3
1
3
On the Biology of a Large Language Model - Anthropic Research
Mar 31
•
Arun S
3
5
Running DeepSeek locally for free and without restrictions
Jan 29
•
Arun S
3
3
Using Claude's new GitHub integration to visualize code 🔥🔥
Feb 26
•
Arun S
3
1
Recent posts
View all
1:55
Conquering the Browser: Why This Is the Cheat Code for getting to AGI with LLMs
Mastering the digital world’s most universal tool could finally help us define what truly useful AGI looks like.
Jul 19
•
Arun S
1
3
Context Engineering - Unlocking Agentic AI’s True Potential
The art and science of giving the right information to LLMs. As AI systems become more complex and sophisticated, prompt engg is not enough to convey…
Jul 5
•
Arun S
1
2
Context Bloat in Large Language Models
Context makes or breaks large language model implementations.
Jun 18
•
Arun S
3
1
Analysis of Claude 4's System prompt and what changed from Claude 3.7
There are major changes in how Claude 4's character has been modeled. This also gives a glimpse into how models have improved, and how Anthropic's world…
May 24
•
Arun S
1
Meta AI's full system prompt and analysis - LLAMA 4
I was able to extract and analyze the full system prompt of the newly released Meta AI app which is powered by LLAMA 4. A very detailed prompt that…
Apr 30
•
Arun S
1
2
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
