aloka

Trying to be an orginal in a sea of artificials...
Petrolhead | Techie | Melophile | Productivity

[aloka @TheThrottleBit]

@ConnectBhawna Well, a good one... Hope it bought out clarity... I wonder, what did you normally think of or picture then when you meditate? And what did you do when your attention shifts from focusing on your senses?

[Nekt0 @Nekt_0]

Andrej Karpathy just said your kids should ignore most of school.

"80% of education should be math, physics, CS."
Not because it's useful - because it carves grooves in the brain.
Grooves that get harder to carve the older you get.

In a pre-AGI world: it gets you a job.
In a post-AGI world: it makes you a functioning, empowered human.

Everything else? Tack it on later.

The cognitive foundation is the only foundation that survives the transition.

[unicode @unicodef1wn]

A senior Anthropic engineer leaked his internal PDF on giving multi-agent systems permanent memory.

Your agent forgets everything the second its context window closes. His fix: a knowledge graph that survives past any single run.

Extract → Resolve → Assemble → Query → Repeat:

Extract: Haiku pulls entities and triples, one call per doc
Resolve: Sonnet matches "Edwin Aldrin" to "Buzz Aldrin" with zero string overlap, just context
Assemble: canonical nodes, typed edges, provenance on every triple
Query: Sonnet reasons over the graph, every answer points to a specific edge

Wire it in as shared memory: workers write to it, evaluators check claims against it, loops run overnight without losing state.

Save this before it gets taken down 👇

[Hasan Toor @hasantoxr]

Claude Code Project Structure: The Complete Map

[Raytar @Raytar]

Andrej Karpathy joined Anthropic five weeks ago.

Yesterday my friend on his team sent me the Claude.md file he actually uses.

It completely changed how I work with Claude.
From the very first message, the difference was obvious.

With this file, Claude finally stops fighting me and starts working exactly the way I need it to.

Bookmark it before it gets taken down.

Read it now, then check the article below.

[Hasan Toor @hasantoxr]

Loop Engineering is the next step after prompt engineering.

Most people still use Claude Code, Codex, Cursor, or Grok like a chat box:

Prompt.
Wait.
Copy.
Fix.
Prompt again.

This repo shows the next step:

You stop prompting the agent.

You design the loop that prompts the agent for you.

Inside:

→ Daily triage loops
→ PR babysitter loops
→ CI sweeper loops
→ Dependency sweeper loops
→ Changelog drafter loops
→ Post-merge cleanup loops
→ Issue triage loops

It also gives you CLIs to:

• Scaffold a loop
• Estimate token cost
• Audit if your repo is ready
• Add memory/state
• Add human handoff
• Add verification gates
• Run agents safely through GitHub Actions

The wild part is the shift in thinking.

Prompt engineering was about writing better instructions.

Loop engineering is about building a system where agents keep working, checking, fixing, and escalating without you babysitting every step.

This is what AI coding looks like when it stops being a chat session and starts becoming an operating system for software teams.

Repo: https://t.co/2USzC6KHUt

[ℏεsam @Hesamation]

this PhD student had 47 interviews and 4 offers before she was hired at OpenAI.

she practiced with her “notes on LLMs” and math and they’re a goldmine. super concise and organic and shared to everyone for free. you can use her notes or her topic list to study on your own.

[aloka @TheThrottleBit]

Jun 11,12 - Days 5,6

1. Worked on 2 more subsections of the paper, specifically knowledge distillation, peft, QLoRA
2. Analyzed the working of my report generator agent and started fixing bugs..

Doing small amount of things in a large amount manner

Discipline's Quintessential!

[aloka @TheThrottleBit]

June 8:10 - Days 2:4

1. Worked on my survey paper. Composed a few sections. Made a few diagrams. The only concern now is the sheer length of it....
2. Applied for ML summer school, a few other internships and more...

Learnt in the meantime....

Discipline & Consistency!!

[aloka @TheThrottleBit]

June 8:10 - Days 2:4

1. Worked on my survey paper. Composed a few sections. Made a few diagrams. The only concern now is the sheer length of it....
2. Applied for ML summer school, a few other internships and more...

Learnt in the meantime....

Discipline & Consistency!!

[aloka @TheThrottleBit]

June 7 - Day 1/100

1. Worked on my survey paper, composing 2 sections of it and vetting a few papers.
2. Started Learning Framer, explored around, started off with a small button animation.

Small Steps!

But these compound as major wins later...

[aloka @TheThrottleBit]

a journey of 100 days, that mainly covers:
1. DSA/CP
2. Agentic AI/ML
3. Framer

(And some occasional refreshers of some core CS concepts and languages)

[aloka @TheThrottleBit]

June 7 - Day 1/100

1. Worked on my survey paper, composing 2 sections of it and vetting a few papers.
2. Started Learning Framer, explored around, started off with a small button animation.

Small Steps!

But these compound as major wins later...

[aloka @TheThrottleBit]

Jun 1 to June 6

1. Gave my ML paper (pretty chill)

And that's all

Rested a bit. Talked to a few friends. Fixed up a few things. Mostly rest these days.

Anyhow, placement season is about to start and I dont wanna miss it out...

Daily posts (hopefully)

Daily DSA, Projects!!

[aloka @TheThrottleBit]

@tarunvats33 damn, just noticed it now!
so cool...

[aloka @TheThrottleBit]

Time to get back building....

Wish me luck! 🤞

[aloka @TheThrottleBit]

Jun 1 to June 6

1. Gave my ML paper (pretty chill)

And that's all

Rested a bit. Talked to a few friends. Fixed up a few things. Mostly rest these days.

Anyhow, placement season is about to start and I dont wanna miss it out...

Daily posts (hopefully)

Daily DSA, Projects!!

[aloka @TheThrottleBit]

May 26 to May 31

1. Gave my ADS, BDA papers (one went well, latter not so much)
2. Revised ML for sem ends.
3. Focused Majorly on sem ends itself.
4. Gave Amazon Hackon OA (pretty chill, except those prompt questions, my god took 1 minute to read those questions)

Discipline!!

[Menci 💖 @lcMenci]

Claude 教会了我，打不开的网站可以用 https://t.co/8WmWI2junp 突破限制（

[Tom Dörr @tom_doerr]

Turns any codebase into an interactive knowledge graph

https://t.co/rTSuMR94Ho

[Arjun Virk @virkvarjun]

I just spent months handwriting a 200 page guide on the entirety of ML foundations and math from scratch.

The guide features:
- Neural Nets (Backprop, Adam, SGD, Batch Norm)
- ML Algorithms (SVM, Grad Boosting, K-means, PCA)
- Hardware (Tensor Cores, Systolic Arrays, CUDA)
- Transformers (Multi-Head Attn, KV Cache, LoRA)
- Vision (ViT, Convolutions, MAE, IoU, NMS, VLM)
- Agents (OpenClaw, ReAct, Memory, Orchestration)

Everything I wish I had years ago, for free.

[Ahmad @TheAhmadOsman]

Step-By-Step LLM Engineering Projects Roadmap

- Build a tokenizer
- Learn embeddings
- Implement RoPE / ALiBi
- Hand-wire attention
- Build MHA
- Build a Transformer block
- Train a mini-former
- Compare objectives
- Build sampling
- Speculative decoding
- KV cache
- MQA / GQA / MLA
- Long context
- FlashAttention
- Hardware budgets
- Toy MoE
- Sparse model trade-offs
- State-space / linear attention
- Diffusion language models
- Data pipelines
- Synthetic data
- Scaling laws
- SFT / DPO / RLHF / GRPO
- Quantization
- Serving stacks
- Eval harnesses
- RAG
- Tool use / agents
- Vision-language adapters
- Interpretability
- Red-team suite
- Full capstone model system

One request:

Choose an Opensource AI lab when you make it

Opensource is where humanity gets to keep the tools

DM me when you've made it ;)

[a16z @a16z]

World Labs CEO Dr. Fei-Fei Li: "The world is not made of words."

"Language models have given machines an extraordinary command of concepts, vocabulary, and reasoning, but the physical world, virtual or real, runs on a different substrate."

"Where language models learn the statistical structure of text, world models learn the statistical structure of space and time: how light falls on a surface, how a garden looks from an angle no camera has captured, how objects respond to force and follow the laws of physics."

"Language gave machines a way to talk about that world. World models are how machines will finally come to understand, imagine, reason and interact with it."

Full piece: https://t.co/C9qOJg5wuc

[aloka @TheThrottleBit]

@getpeid OMG, such a cool way (and free that too :) to get peoples attention. Wow!