Mukesh Firoda

Tech

[Annatar.md @AnnatarXBT]

this is pure f*cking gold

andrej karpathy landed at anthropic 14 weeks ago

about that "two anthropic seniors made his loop 1000x better with graph engineering" line - i can't find a source for it anywhere, so i'm not passing it off as fact

what is public and checkable:

anthropic's own cookbook on building knowledge graphs, plus karpathy's autoresearch loop that ran 700 experiments in 2 days and surfaced 20 optimizations on its own

i wired the graph approach into my own setup

the difference showed up on the very first reply

claude skipped the stock answer and actually reasoned through the problem

start with the cookbook, the full write-up is below

[Mukesh Firoda @Luckylobster886]

We’re getting dangerously close to the point where “AI can code” is the least interesting part of the story
#AI #Coding #AIEngineering #GenerativeAI #SoftwareDevelopment #Developers #Tech

[Simon Willison @simonw]

New TIL on using Blender with coding agents on macOS: https://t.co/GvMDfD926E

GPT-6 Astra (medium):

> Use the already install /Applications/Blender to render a scene of a pelican riding a bicycle

> OK add a background and a lot of flair

> OK make it a whole lot better

[Mukesh Firoda @Luckylobster886]

AI can now fix your PR until CI passes.
At what point does “code review” become “AI reviewing AI”?

[Mukesh Firoda @Luckylobster886]

If your entire development environment can run AI locally,
what happens to the "you need the cloud" argument?
Microsoft is now pushing a developer-focused Windows setup around high-memory machines and local AI workloads

[Mukesh Firoda @Luckylobster886]

Your AI writes 1,000 lines of code overnight.
Tomorrow morning:
Do you review it
or
just run the tests?

[Hacking Articles @hackinarticles]

Pic of the Day

#infosec #cybersecurity #cybersecuritytips #pentesting #cybersecurityawareness

[Mukesh Firoda @Luckylobster886]

The better AI gets at writing software,
the less valuable writing software becomes.
So what becomes the real engineering skill?

[Mukesh Firoda @Luckylobster886]

I was thinking about it

[Priy @alwayspriyesh]

Everyone is celebrating GPT-6 Astra

But as a software engineer, when u see:

- Better code
- Better reasoning
- Better agents
- Better security

4 major models. 3 days.

AI progress is accelerating
AGI feels closer

And software engineers? You should be worried

[Mukesh Firoda @Luckylobster886]

Thanks for letting us know @PawelHuryn

[Paweł Huryn @PawelHuryn]

So, I finally tested GPT-6 Astra.

2 real repos, 105 bugs, find and fix what you can. Max effort:

GPT-6 Astra: 48/105
Fable 5.1: 43/105
GPT-5.6 Sol: 42/105
Gemini 3.8 Flash: 20/105

And it's crazy efficient. Look at the time and cost 🧵

[Mukesh Firoda @Luckylobster886]

Looks good to me
@simonw

[Simon Willison @simonw]

Got access to GPT-6 Astra. Want to see some pelicans? Yeah you want to see some pelicans... here's a grid comparing Astra to GPT-5.6 Sol, Terra, and Luna https://t.co/LJi3XOpYpJ

[Mukesh Firoda @Luckylobster886]

You can choose one:
A model that writes perfect code
or
a model that tells you exactly why its code works.
Which one do you want?

[Clara Bennett @CodeswithClara]

Sam Altman (CEO of Open AI):

"You no longer need to write prompts."

In just 38 minutes, he explains how to use ChatGpt at a level that most people can't even imagine.

It's talk he gave to stanford students. A friend sent me the recording last night.

After watching it, I realized I was only taking advantage of about 15% of what this tool can really do.

Watch it in full and then read the guide l leave below on how to create a system that prompts itself.

[Mukesh Firoda @Luckylobster886]

@Taniyatweets_ Yes

[Mukesh Firoda @Luckylobster886]

@sama Uhhh can you do it for free users also😅😅

[Mukesh Firoda @Luckylobster886]

I guess it is very useful

[Amit Shekhar @amitiitbhu]

Research papers every LLM engineer must read:

- Attention Is All You Need
- BERT
- GPT-3: Language Models are Few-Shot Learners
- Scaling Laws for Neural Language Models
- Chinchilla
- InstructGPT
- Chain-of-Thought Prompting
- Retrieval-Augmented Generation
- LoRA: Low-Rank Adaptation
- LLaMA
- FlashAttention
- DPO: Direct Preference Optimization

[Shahzamann 💤 @ShazXcode]

Evolution of GenZ kids