Chamroque

bitcoin

[Elon Musk @elonmusk]

Murderous migrants beheading innocent people in their home town is what’s making people angry, not “social media”!

[John Cleese @JohnCleese]

Absolutely disgraceful

I hope Labour are decimated at the election

[Rupert Lowe MP @RupertLowe10]

How many more young British men and women are going to die? Bleeding in the street, alone and terrified. Cuffed, in a pool of their own blood. Begging for help.

How many more parents are going to stand there, and say that they couldn’t help their children in their dying moments? Apologising to their dead children because they couldn’t stop it from happening?

How many more?

This is going to happen again, and again, and again.

It’s happening right now, in every city across the country.

Rape. Sexual torture. Even worse. Mass industrial abuse of British children.

Henry Nowak is one of thousands and thousands and thousands.

Innocent young men and women put through the most unimaginable pain, because our country has failed to do what needs to be done.

Because children have been sacrificed to death in order to appease foreign cultures that have no place in our country.

I have had enough - of all of it.

I am going to look back in anger.

I urge you all to do the same.

[Ahmad @TheAhmadOsman]

Top 26 Essential Papers for Mastering LLMs and Transformers

Implement those and you’ve captured ~90% of the alpha behind modern LLMs.

Everything else is garnish.

This list bridges the Transformer foundations
with the reasoning, MoE, and agentic shift

Recommended Reading Order
1. Attention Is All You Need (Vaswani et al., 2017)
> The original Transformer paper. Covers self-attention,
> multi-head attention, and the encoder-decoder structure
> (even though most modern LLMs are decoder-only.)

2. The Illustrated Transformer (Jay Alammar, 2018)
> Great intuition builder for understanding
> attention and tensor flow before diving into implementations

3. BERT: Pre-training of Deep Bidirectional Transformers (Devlin et al., 2018)
> Encoder-side fundamentals, masked language modeling,
> and representation learning that still shape modern architectures

4. Language Models are Few-Shot Learners (GPT-3) (Brown et al., 2020)
> Established in-context learning as a real
> capability and shifted how prompting is understood

5. Scaling Laws for Neural Language Models (Kaplan et al., 2020)
> First clean empirical scaling framework for parameters, data, and compute
> Read alongside Chinchilla to understand why most models were undertrained

6. Training Compute-Optimal Large Language Models (Chinchilla) (Hoffmann et al., 2022)
> Demonstrated that token count matters more than
> parameter count for a fixed compute budget

7. LLaMA: Open and Efficient Foundation Language Models (Touvron et al., 2023)
> The paper that triggered the open-weight era
> Introduced architectural defaults like RMSNorm, SwiGLU
> and RoPE as standard practice

8. RoFormer: Rotary Position Embedding (Su et al., 2021)
> Positional encoding that became the modern default for long-context LLMs

9. FlashAttention (Dao et al., 2022)
> Memory-efficient attention that enabled long context windows
> and high-throughput inference by optimizing GPU memory access.

10. Retrieval-Augmented Generation (RAG) (Lewis et al., 2020)
> Combines parametric models with external knowledge sources
> Foundational for grounded and enterprise systems

11. Training Language Models to Follow Instructions with Human Feedback (InstructGPT) (Ouyang et al., 2022)
> The modern post-training and alignment blueprint
> that instruction-tuned models follow

12. Direct Preference Optimization (DPO) (Rafailov et al., 2023)
> A simpler and more stable alternative to PPO-based RLHF
> Preference alignment via the loss function

13. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (Wei et al., 2022)
> Demonstrated that reasoning can be elicited through prompting
> alone and laid the groundwork for later reasoning-focused training

14. ReAct: Reasoning and Acting (Yao et al., 2022 / ICLR 2023)
> The foundation of agentic systems
> Combines reasoning traces with tool use and environment interaction

15. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning (Guo et al., 2025)
> The R1 paper. Proved that large-scale reinforcement learning without
> supervised data can induce self-verification and structured reasoning behavior

16. Qwen3 Technical Report (Yang et al., 2025)
> A modern architecture lightweight overview
> Introduced unified MoE with Thinking Mode and Non-Thinking
> Mode to dynamically trade off cost and reasoning depth

17. Outrageously Large Neural Networks: Sparsely-Gated Mixture of Experts (Shazeer et al., 2017)
> The modern MoE ignition point
> Conditional computation at scale

18. Switch Transformers (Fedus et al., 2021)
> Simplified MoE routing using single-expert activation
> Key to stabilizing trillion-parameter training

19. Mixtral of Experts (Mistral AI, 2024)
> Open-weight MoE that proved sparse models can match dense quality
> while running at small-model inference cost

20. Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints (Komatsuzaki et al., 2022 / ICLR 2023)
> Practical technique for converting dense checkpoints into MoE models
> Critical for compute reuse and iterative scaling

21. The Platonic Representation Hypothesis (Huh et al., 2024)
> Evidence that scaled models converge toward shared
> internal representations across modalities

22. Textbooks Are All You Need (Gunasekar et al., 2023)
> Demonstrated that high-quality synthetic data allows
> small models to outperform much larger ones

23. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet (Templeton et al., 2024)
> The biggest leap in mechanistic interpretability
> Decomposes neural networks into millions of interpretable features

24. PaLM: Scaling Language Modeling with Pathways (Chowdhery et al., 2022)
> A masterclass in large-scale training
> orchestration across thousands of accelerators

25. GLaM: Generalist Language Model (Du et al., 2022)
> Validated MoE scaling economics with massive
> total parameters but small active parameter counts

26. The Smol Training Playbook (Hugging Face, 2025)
> Practical end-to-end handbook for efficiently training language models

Bonus Material
> T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (Raffel et al., 2019)
> Toolformer (Schick et al., 2023)
> GShard (Lepikhin et al., 2020)
> Adaptive Mixtures of Local Experts (Jacobs et al., 1991)
> Hierarchical Mixtures of Experts (Jordan and Jacobs, 1994)

If you deeply understand these fundamentals; Transformer core, scaling laws, FlashAttention, instruction tuning, R1-style reasoning, and MoE upcycling, you already understand LLMs better than most

Time to lock-in, good luck!

[John Cleese @JohnCleese]

Sorry to have to say this...

The British do not like the kind of diversity that intends to take over Britain and kill any infidel that does not convert to Islam

Is that hard to understand, silly little man ?

[Rupert Lowe MP @RupertLowe10]

I do not want these men in our country.

[unusual_whales @unusual_whales]

BREAKING: We just gave Claude access to the entire options and stock market and it's not a demo.

It's the Unusual Whales MCP Server. It plugs directly into any AI assistant and gives it live, structured market data on demand.

Build a trading bot. Build a finance dashboard. Build a screener. Build whatever you want.

A thread:

[John Cleese @JohnCleese]

This is complete rubbish

To criticise a religion is not racist.

It's culturalist

The difference ? you can choose one, not the other other

Now, many of us prefer some cultures to others

For example, I prefer a culture that does not permit Female Genital Mutilation, Child Marriage, Animal Torture, Total Humiliation of Women, and Execution
of People from other Belief Systems, and which is not intent on World Domination

Call me old-fashioned...

[Chamroque @goodishpile]

@JasonPLowery what happens when AI agents own more of the supply than humans?

[Rupert Lowe MP @RupertLowe10]

Restore Britain will put the safety and wellbeing of British women ahead of third world sex pests who have broken into our country and now freely roam our streets.

We do not give a shit about their human rights.

They will all be deported, immediately.

[Chamroque @goodishpile]

@RestoreBritain_ exactly. nothing to do with the state.

[Rupert Lowe MP @RupertLowe10]

Today marks the end of the survivor participation for our rape gang inquiry hearings. I simply have no words that describe the bravery and courage of these women who have come forward.

No words.

What they have been through is indescribable.

It has been a life-changing experience for me. I never thought such evil was possible. Never. Not here, in Britain. In our towns, in our communities. It is pure evil. These men are so utterly depraved.

If it were up to me, thousands of them would receive the death penalty.

To do what they did, on such an industrial scale, to innocent young girls - many of whom were already in such an incredibly vulnerable place? There is no redemption possible. The world is a better place without them in it.

I started this inquiry because so many others failed.

Speaking honestly, I did not understand how deep this evil is rooted in our society.

Police, politicians, council officials, the NHS, social workers, children’s homes - it is everywhere.

IS everywhere. Not was. IS.

Meeting these women, and men, listening to how severely they were failed by those tasked to protect them? My views have changed forever. I knew it was bad. I never knew how bad it was.

Every single one who has come forward is a hero in my view.

The courage and grace in how they have conducted themselves is unlike anything I have seen in my life. All because they don’t want others to suffer the same fate. That is an extraordinary sacrifice. They could have just moved on with their lives. Tried to forget. But no, they chose to do this. I am in awe of all of them.

Our hearings will finish tomorrow, following the contribution of three more expert witnesses.

Then the next stage begins. We will produce a report, and then we will seek to put people in prison. There are FAR more testimonies and evidence to release - this will keep coming and coming and coming.

Even with a media blackout, we have reached tens of millions. We have made real progress.

And following such immense demand, we will reopen the portal so that more women can tell their stories.

This is just the beginning.

Politicians from all parties have failed these girls, again and again and again.

I do not intend to join that list.

To everyone who donated, thank you. To our team, thank you. And especially to the survivors, thank you.

I believe that together we can start to make Britain understand what is happening, and then finally do something about it.

[Chamroque @goodishpile]

@RupertLowe10 bravo Rupert

[Rupert Lowe MP @RupertLowe10]

I am today launching Restore Britain as a national political party.

Join us.

https://t.co/RMtEuHopgV

[Quality Learing Center @qualitylearnc]

For England

[𝓢𝓪𝓶 @samofsamshire]

Add a floor and give them bigger windows.

Two additions that immediately improve aesthetics and quality of life.

[Chamroque @goodishpile]

@Giovann35084111 awesome post sir

[Chamroque @goodishpile]

@BitcoinPierre “founder of bitcoin” 🙄

[Chamroque @goodishpile]

@Excellion Make Energy Money Again

[Chamroque @goodishpile]

@NutriDetect very telling that wanting to know the cause of your condition is a “frustration” for these doctors