Suj

Cricket 🏏 enthusiast,Code

[Suj @imsujaypatil]

Very humble & starts in Kannada to speak about Karnataka flag displayed on @BurjKhalifa #VikrantRonaOnBurjKhalifa
#VikrantRona @KicchaSudeep

[Morty @0xMortyx]

Anthropic Engineer Andrej Karpathy dropped a full 6-hour course on how to build LLMs from scratch and use it:

• 00:00 - Deep dive into LLMs
• 03:31:23 - Building ChatGPT from scratch
• 05:27:43 - How to use LLMs (Karpathy method)

This course can replace a $150K Stanford LLM senior degree.

Start watching today, then read article below

[Morlex @0xMorlex]

Andrew Ng at Stanford:

“Stop waiting for the perfect model. Build the iteration "loop" and "graphs" around it.”

move from prompt → loop → graph → self-improving system

• 00:05 - why every AI project needs an iteration loop
• 04:08 - the full cycle: data → model → deploy → monitor
• 16:02 - why faster iteration can decide who wins
• 26:09 - using error analysis to improve the right data
• 39:39 - why shipping a simple system beats waiting for perfection
• 54:26 - monitoring drift and improving models after deployment

67-minute Stanford lecture, and it’s one of the clearest playbooks on why experienced AI engineers optimize the loop around the model, not just the model itself.

It's watch today, then read the full step by step roadmap in the article below

[Lunar @LunarResearcher]

Andrew Ng just released a 2-hour course on full Graph Engineering.

How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you:

09:14 - Build your first AI agent
33:11 - Run agents with loop engineering
1:02:46 - Turn agent loops into graphs
1:30:15 - Build agents that rewrite themselves
1:49:05 - Run the full graph system without you

Most people are still building one agent and calling it done.

Andrew Ng is already teaching everything after:

Prompt → Agents → Loops → Graphs → Self-Improving Systems

Single agents are the old workflow.

Systems that improve and run without you are the new one.

This 2-hour watch is worth more than most $500 agent engineering courses.

Bookmark and watch it before everyone catches up.

Then read how to run 1,000 agents from one prompt below ↓

[Morlex @0xMorlex]

Andrew Ng at Stanford:

“Stop trying to write the perfect prompt.”

Andrew Ng just showed why AI engineers are moving to "loops" and "graphs" that improve the system for you

• 00:05 - why some AI teams move 10X faster than others
• 07:12 - choosing an architecture and shipping the first version fast
• 30:12 - the 97% accuracy trap and why AI evals lie
• 48:12 - the build → error analysis → retrain loop
• 57:55 - how LLM deep-research agents are actually built
• 1:06:30 - finding the bottleneck inside an agent pipeline

75-minute Stanford lecture, and it’s one of the clearest playbooks on why experienced AI engineers are moving beyond prompts and building loops, graphs and systems that improve themselves.

Watch it today, then read the full roadmap in the article below

[codila @0xCodila]

Andrew Ng just released 2-hour course on 100% Graph engineering: 1 prompt → 100 agents → loops → graphs from scratch:

10% → 9:14 - build your first agent from scratch
30% → 33:11 - Loop engineering
55% → 1:02:46 - Graph engineering
75% → 1:30:15 - agents that rewrite themselves
100% → 1:49:05 - full graph system that work without you

most graph tutorials stop at the diagram - this one has you running one in the first 20 minutes

watch this brilliant course, build the graph - then read the full architecture below ↓

[Lunar @LunarResearcher]

Andrej Karpathy just explained the full stack behind why LLMs hallucinate, use tools, and need memory.

How to go from raw internet text to systems like ChatGPT:

00:00 - Hallucinations, tools, and working memory
16:28 - Turn a base model into ChatGPT
27:35 - Train and run GPT-2
39:18 - Turn tokens into predictions
50:52 - Turn the internet into training data

Most people only see the symptoms:

It hallucinates. It forgets. It reaches for tools.

Karpathy shows the full stack underneath:

Internet → Tokens → Training → Post-Training → Tools → Memory

Prompting the model is the surface layer.

Understanding what happens underneath is the real advantage.

This 59-minute watch explains more about LLMs than most paid AI courses.

Bookmark and watch it today.

Then read the full breakdown below ↓

[Suj @imsujaypatil]

@Manisshasingh Did you watch latest episode as well

[Suj @imsujaypatil]

Finally @ProteasMenCSA win the final
#WtcFinal2025 #SouthAfrica
Most happiest person @ABdeVilliers17 since couple of weeks
#savas #WTCFinal #AUSvsSA

[Suj @imsujaypatil]

Crucial last hour for #SouthAfrica to end the day without loosing this wicket
#WtcFinal2025 #savas
#tembabavuma

[Suj @imsujaypatil]

@geeksforgeeks From enjoying building Swing applets to debugging the Null pointer exceptions.

[ℏεsam @Hesamation]

Andrej Karpathy explains Tensor Cores and TF32 precision

[Suj @imsujaypatil]

@crazy_techgirl @RVCJ_FB Change that to boy !

[Suj @imsujaypatil]

@SumitM_X Using holdsLock(obj) for the running thread or have to check thread dumps.

[Suj @imsujaypatil]

@AskPerplexity can you check my above tweet

[Suj @imsujaypatil]

@AskPerplexity why isn't there a scroll to bottom in perplexity app?

[Suj @imsujaypatil]

@mehaktwts @NoobCoderVibe Yes

[Suj @imsujaypatil]

@mehaktwts Is it @NoobCoderVibe

[Suj @imsujaypatil]

@paarlroyals Yes

[Sebastian Raschka @rasbt]

A reader recently shared a resource on training tokenizers for new languages which reminded me I originally wrote a BPE Tokenizer for my “LLMs from Scratch” book but never shared it!

If you are looking a weekend project, here you go: https://t.co/sDAjxSkUuf