Reza 😈

Software Engineer | I'm your favorite persons favorite person | Best Mario Kart player of all time

[Reza 😈 @ImRxza]

@realPigboy Too much healing tbh

[Reza 😈 @ImRxza]

@DyIanNova @PotNoodleOW @Duck_Formeal Leave lean pig alone

[Reza 😈 @ImRxza]

@twomundane Never forget your Chikorita hate arc

[The Random Recruiter @randomrecruiter]

POV: Your manager just asked you to hop on a "quick call" in the middle of your mid day nap

[Python Programming @PythonPr]

Layers of AI

[Inferam @InferamAI]

Study methods guide

[Python Programming @PythonPr]

Evolution of AI Agents
Image Credit- Brij Kishore Pandey

[The Random Recruiter @randomrecruiter]

Remote workers when they hear a Microsoft Teams notification during their mid day nap

[Avi Chawla @_avichawla]

RAG vs. CAG, clearly explained!

RAG is great, but it has a major problem:

Every query hits the vector database. Even for static information that hasn't changed in months.

This is expensive, slow, and unnecessary.

Cache-Augmented Generation (CAG) addresses this issue by enabling the model to "remember" static information directly in its key-value (KV) memory.

Even better? You can combine RAG and CAG for the best of both worlds.

Here's how it works:

RAG + CAG splits your knowledge into two layers:

↳ Static data (policies, documentation) gets cached once in the model's KV memory

↳ Dynamic data (recent updates, live documents) gets fetched via retrieval

The result? Faster inference, lower costs, less redundancy.

The trick is being selective about what you cache.

Only cache static, high-value knowledge that rarely changes. If you cache everything, you'll hit context limits. Separating "cold" (cacheable) and "hot" (retrievable) data keeps this system reliable.

You can start today. OpenAI and Anthropic already support prompt caching in their APIs.

I have shared a link to OpenAI's prompt caching guide in the replies.

Have you tried CAG in production yet?

[ℏεsam @Hesamation]

bro packaged math and programming into a game and 1000s of people are playing it on steam.

this looks so cool 🤯

[Reza 😈 @ImRxza]

@santosplays7 Old man 🤣 (happy bday)

[Dmitrii Kovanikov @ChShersh]

Nothing beats debugging for 2 hours just to discover there was a typo

[Pallav | RAG Expert @vibingmonk]

Your resume:
Git
SSL
Vue
CSS
PHP
Sass
Node
DOM
React
HTML
CRUD
MERN
MEVN
MEAN
Netlify
Mongo
MySQL
Python
Docker
Angular
Fortnite
GraphQL
Full Stack
JAMstack
JavaScript
TypeScript
Kubernetes
PostgreSQL

Interview decision:
Sorry we need someone who knows AWS.

[Reza 😈 @ImRxza]

@GithubProjects Segfault

[Alex Veremeyenko @alex_verem]

RIP prompt engineering ☠️

This new Stanford paper just made it irrelevant with a single technique.

It's called Verbalized Sampling and it proves aligned AI models aren't broken we've just been prompting them wrong this whole time.

Here's the problem: Post-training alignment causes mode collapse. Ask ChatGPT "tell me a joke about coffee" 5 times and you'll get the SAME joke. Every. Single. Time.

Everyone blamed the algorithms. Turns out, it's deeper than that.

The real culprit? 'Typicality bias' in human preference data. Annotators systematically favor familiar, conventional responses. This bias gets baked into reward models, and aligned models collapse to the most "typical" output.

The math is brutal: when you have multiple valid answers (like creative writing), typicality becomes the tie-breaker. The model picks the safest, most stereotypical response every time.

But here's the kicker: the diversity is still there. It's just trapped.

Introducing "Verbalized Sampling."

Instead of asking "Tell me a joke," you ask: "Generate 5 jokes with their probabilities."

That's it. No retraining. No fine-tuning. Just a different prompt.

The results are insane:

- 1.6-2.1× diversity increase on creative writing
- 66.8% recovery of base model diversity
- Zero loss in factual accuracy or safety

Why does this work? Different prompts collapse to different modes.

When you ask for ONE response, you get the mode joke. When you ask for a DISTRIBUTION, you get the actual diverse distribution the model learned during pretraining.

They tested it everywhere:

✓ Creative writing (poems, stories, jokes)
✓ Dialogue simulation
✓ Open-ended QA
✓ Synthetic data generation

And here's the emergent trend: "larger models benefit MORE from this."

GPT-4 gains 2× the diversity improvement compared to GPT-4-mini.

The bigger the model, the more trapped diversity it has.

This flips everything we thought about alignment. Mode collapse isn't permanent damage it's a prompting problem.

The diversity was never lost. We just forgot how to access it.

100% training-free. Works on ANY aligned model. Available now.

Read the paper: arxiv. org/abs/2510.01171

The AI diversity bottleneck just got solved with 8 words.

[Mathieu @miniapeur]

Honestly mom what do you think?