Supachai Jaturaprom

CCIE#65006, Solutions Consulting

[Dipanshu Kushwaha @Dipanshu_AI]

Anthropic just released a 4-hour course to getting a $500k AI engineering job:

00:15 - The right way to prompt Claude
33:21 - What makes Claude act dumber on your code
01:33:39 - How Anthropic use Claude every day
02:50:56 - The fix that makes Claude way smarter This

4-hour Anthropic free course replaces about 10 paid engineering courses.

Watch it today, then read the step-by-step guide on building loops below.

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Jacob King @JacobKinge]

Crypto is a rigged casino, and today’s events prove it beyond doubt.

A single colossal BTC whale shorted at the peak, then, just minutes before the market-shattering crash, piled on millions more in shorts.

At the very bottom of the drop, he closed 90% of his Bitcoin short and completely exited his Ethereum short, pocketing roughly $190–$200 million in a single day. That’s the only instance we can trace, but speculation is rampant that the scale was far larger and extended across other exchanges.

Don’t be naive, this wasn’t luck. Someone was either manipulating the market or front-running it. Either way, the collapse was engineered, and investors have every reason to be alarmed.

[Supachai Jaturaprom @SupachaiSu]

Migration is fine. #cisco

[Supachai Jaturaprom @SupachaiSu]

I think very happy. #cisco

[Devendra Chaplot @dchaplot]

Super excited to announce Mistral Large 2
- 123B params - fits on a single H100 node
- Natively Multilingual
- Strong code & reasoning
- SOTA function calling
- Open-weights for non-commercial usage

Blog: https://t.co/YPwJmtjSb6
Weights: https://t.co/Q2MSUcR7fm

1/N

[Zach Vorhies / Google Whistleblower @Perpetualmaniac]

@ianmiles C++ is hard. Maybe they have a DEI engineer that did this but for mission-critical software like this Crowdstrike should have set up automated testing using address sanitizer and thread sanitizer that runs on every code update.

https://t.co/Txz96hoFXy

https://t.co/cLHk9FfGea

[Zach Vorhies / Google Whistleblower @Perpetualmaniac]

Crowdstrike Analysis:

It was a NULL pointer from the memory unsafe C++ language.

Since I am a professional C++ programmer, let me decode this stack trace dump for you.

[Data Science Dojo @DataScienceDojo]

AI isn't just robots and sci-fi movies! It's a complex world with layers that are changing our reality.

Learn how to build your own AI project, like a chatbot here ➡️ https://t.co/QlEtKSWqi6

#GenerativeAI #ML #LLM

[Chief AI Officer @chiefaioffice]

New market maps covering the latest AI startups.

1. AI agents from Insight Partners

[DeepLearning.AI @DeepLearningAI]

The best way to learn about Generative AI is by building a project. We’re excited to introduce a new resource to help you get started!

Our guide to create a Retrieval Augmented Generation (RAG) application provides a detailed project description, a step-by-step outline of the RAG process, and a curated list of @DeepLearningAI short courses that offer both theoretical insights and practical example code.

Check out our guide and start your RAG project: https://t.co/i6jLoQ5QUZ

[Ronald van Loon @Ronald_vanLoon]

These systems allow farmers to handle sheep with ease
by @gigadgets_

#TechForGood #Tech #Technology #Innovation

cc: @ravikikan @pbalakrishnarao @bigdata

[NetworkChuck @NetworkChuck]

I built a private AI server for my kids… and it’s kind of epic

Check it out! ----➝ https://t.co/t2n51nSsnG

@ITproTV #AI #aiserver #ollama #llama3

[Chief AI Officer @chiefaioffice]

Big tech is all in on AI.

The number of deals to AI startups backed by US big tech companies & their venture arms jumped 57% YoY.

Big tech's AI investments in 2023:

[Chief AI Officer @chiefaioffice]

New market maps in AI

1. AI agents from E2B

[elvis @omarsar0]

Self-Evolution of LLMs

Provides a comprehensive survey on self-evolution approaches in LLMs.

I often get asked what's next for LLMs?

I think it might be self-evolution or something closely related to this emerging paradigm.

There is still a lot to solve if you look closely at the different phases such as experience acquisition and self-evaluation.

[Mumshad Mannambeth @mmumshad]

Docker Vs Podman Vs Containerd Vs CRI-O👇

Exploring the key roles of container runtimes in modern software deployment, this comparison navigates the unique features of four popular technologies

Check out our courses: https://t.co/rEi2BGNHwU

#kodekloud #devops #kubernetes

[DeepLearning.AI @DeepLearningAI]

In Quantization Fundamentals with @HuggingFace, you'll learn how to quantize open source models, to make them more accessible and efficient.

You’ll get hands-on and practice by quantizing open source multimodal and language models.

Start now! ➡️ https://t.co/VDQ2yC424N

[Sebastian Raschka @rasbt]

One of the best ways to understand LLMs is to code one from scratch!
Last summer, I started working on a new book, "Build a Large Language Model (from Scratch)": https://t.co/VbloA34M4I

I'm excited to share that the first chapters are now available via Manning's early access program if you are looking to read something over the holidays or pick up a new project in 2024!

In short, in this book, I'll guide you step by step through creating your own LLM, explaining each stage with clear text, diagrams, and examples.
This includes Implementing the data preparation, sampling, and tokenization pipeline:

1. Coding multi-head attention from the ground up
2. Building and pretraining a GPT-like model
3. Learning how to load pretrained weights
4. Finetuning the model for classification
5. Instruction-finetuning the model with direct preference optimization

PS: The code implementations are in PyTorch.

Don't hesitate to reach out if you have any questions!

[AK @_akhaliq]

ReNoise

Real Image Inversion Through Iterative Noising

Recent advancements in text-guided diffusion models have unlocked powerful image manipulation capabilities. However, applying these methods to real images necessitates the inversion of the images into the domain of the