Joe Ingeno (@JoeIngeno) header
Joe Ingeno (@JoeIngeno) profile picture

Joe Ingeno

@JoeIngeno

Software Architect | Software Engineer | Author of Software Architect's Handbook https://nitter.cf/t.co/fZ7mamDlBb

 Florida, USA
linkedin.com/in/joeingeno
Joined March 2010
  • Tweets31K
  • Following12.6K
  • Followers52.7K
674Media
Photo by Joe Ingeno (@JoeIngeno)Photo by Joe Ingeno (@JoeIngeno)Photo by Joe Ingeno (@JoeIngeno)Photo by Joe Ingeno (@JoeIngeno)Photo by Joe Ingeno (@JoeIngeno)Photo by Joe Ingeno (@JoeIngeno)Photo by Joe Ingeno (@JoeIngeno)Photo by Joe Ingeno (@JoeIngeno)Photo by Joe Ingeno (@JoeIngeno)
Software Architect's Handbook - Check out the comprehensive guide to being a software architect buff.ly/2EhJist
Software Architect's Handbook: Become a successful software architect by implementing effective...

Software Architect's Handbook: Become a successful software architect by implementing effective...

Software Architect's Handbook: Become a successful software architect by implementing effective architecture concepts

amazon.com
1
9
62
14,138
Joe Ingeno retweeted
Pubity (@pubity) profile picture
Pubity
@pubity6h
OpenAI CEO Sam Altman believes people owning RAM is wasteful, and that it belongs in data centers instead. "From a global allocation perspective, actually, it’s quite terrible to have everyone have a bunch of the world’s limited supply of DRAM sitting in their own computer."
Image from Pubity (@pubity)
Image from Pubity (@pubity)
3,969
994
6,323
20,369
4,532,761
Octoverse: Commits, pushes, reach new highs in 2026 as developers build with agents github.blog/news-insights/oc… #octoverse #github #AI
Octoverse: Commits, pushes, reach new highs in 2026 as developers build with agents

Octoverse: Commits, pushes, reach new highs in 2026 as developers build with agents

See how a record year of growth reached every industry, every field, and every kind of builder in the 2026 Octoverse report.

github.blog
170
OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why? minimaxir.com/2026/10/cheap-… #OpenAI #anthropic #claude #AI
OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?

OpenAI and Anthropic cut their LLM prices by up to 80% within a few months. Why?

What is “the true cost of a token”?

minimaxir.com
2
1
1
302
The Mythical Man-Month in the age of AI j11g.com/the-mythical-man-mo… #AI
The Mythical Man-Month in the age of AI - Jan van den Berg

The Mythical Man-Month in the age of AI - Jan van den Berg

An update to Brooks's Law in the age of AI.

j11g.com
1
3
505
Gemini 4 Carbon is our next frontier model. It’s state-of-the-art across cybersecurity and long-horizon capabilities.
Image from Google DeepMind (@GoogleDeepMind)
711
1,368
1,085
14,409
1,584,546
From 27 minutes to 4: Cutting CI build time by 85% alexitc.com/blog/2026-10-23-…
From 27 minutes to 4: Cutting CI build time by 85%

From 27 minutes to 4: Cutting CI build time by 85%

Sharing my experience to get a faster CI: caching, test parallelism, and path filtering took one project's GitHub Actions build from 27 minutes to 4

alexitc.com
2
413
Why is it so expensive to send an email? evancz.dev/why-is-it-so-expe…

Why is it so expensive to send an email?

Sending an email is essentially the same as making an HTTPS request, so how can companies charge $15 to send 1000 emails?

evancz.dev
4
899
Image from Joe Ingeno (@JoeIngeno)
5
13
676
OpenAI CLI github.com/openai/openai-cli #OpenAI #AI
GitHub - openai/openai-cli: Official CLI for the OpenAI API

GitHub - openai/openai-cli: Official CLI for the OpenAI API

Official CLI for the OpenAI API. Contribute to openai/openai-cli development by creating an account on GitHub.

github.com
1
1
581
Roku developer repositories moved from GitHub to GitLab blog.roku.com/developer/gitl…
Roku

Roku

Roku provides the simplest way to stream entertainment to your TV. On your terms. With thousands of available channels to choose from.

blog.roku.com
1
766
Where did my freed memory (not) go? yapfast.com/blog/where-did-m…
Where did my freed memory (not) go? | Yapfast

Where did my freed memory (not) go? | Yapfast

Yapfast freed 23 MiB and kept.. all of it. Where it went, and how I got glibc to give it back.

yapfast.com
512
#OpenShell - The safe, private runtime for fleets of autonomous AI agents github.com/NVIDIA/OpenShell #AI
GitHub - NVIDIA/OpenShell: OpenShell is the safe, private runtime for autonomous AI agents.

GitHub - NVIDIA/OpenShell: OpenShell is the safe, private runtime for autonomous AI agents.

OpenShell is the safe, private runtime for autonomous AI agents. - NVIDIA/OpenShell

github.com
1
366
Concerning behavior from a popular open-weight AI model cohere.com/blog/concerning-b… #AI
Concerning behavior from a popular open-weight AI model | Cohere

Concerning behavior from a popular open-weight AI model | Cohere

Discover how untrusted open-weight AI models can potentially leak data, even when self-hosted. Learn the security risks and how to protect your enterprise.

cohere.com
1
1
437
nitter.cf/cohere/status/21148492…
Cohere (@cohere) profile pictureCohere
@cohereOct 26
In the spirit of transparency and openness, we are releasing the traces so developers can test this out for themselves. We noticed this behaviour without prefilling with the following prompt, but this is rare. If you want to reproduce it, you can use this prompt with prefilling. Open models make for better science and are part of why this problem came to light at all: developers running Qwen3.8 on their own machines spotted the strange links, and having the weights let us study the behaviour in depth. We're encouraged by the thoughtful discussion our research has sparked across the AI and security communities. It's our belief that open-weight models are an important part of the future of AI, and we've recently released several under the Apache 2.0 license. Trace, raw tokens, & minimal reproduction script: huggingface.co/datasets/Cohe…
CohereLabs/10-2026-qwen-investigation-traces · Datasets at Hugging Face

CohereLabs/10-2026-qwen-investigation-traces · Datasets at Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

huggingface.co
108
No Source Code? No Problem! queue.acm.org/doi/10.1145/94…

No Source Code? No Problem!: What if you have to port a program, but all you have is a binary?:...

Typical software development involves one of two processes: the creation of new software to fit particular requirements or the modification (maintenance) of old software to fix problems or fit new...

queue.acm.org
620
Make yourself replaceable maroun-baydoun.com/blog/make…
Make yourself replaceable

Make yourself replaceable

On job security, institutional knowledge and the unexpected downside of becoming the person everyone depends on.

maroun-baydoun.com
5
583
Image from Joe Ingeno (@JoeIngeno)
1
1
13
1,142
How to Make Things, and Why youtube.com/watch?v=7yeH1DqK…
How to Make Things, and Why - Stuart Halloway (Clojure/Conj 2026)

How to Make Things, and Why - Stuart Halloway (Clojure/Conj 2026)

This is a talk about how to find flow, power, and joy in making sof...

youtube.com
3
668
#Docker is weird codeandcake.dev/posts/2026-1…
1
5
1,351
Yesterday was my last day at Anthropic. I created Claude Code on desktop because I believe everyone can be a builder. Every feature request and bug report we got from this community was a gift that impacted millions of lives. I’m eternally grateful for those gifts, the product wouldn’t be what it is without you. Anthropic is doing some of the most important work of our time. Contributing to that mission will forever be a career highlight for me. I never imagined I’d get to contribute to something so special in my lifetime. Walking away from my best friends, a product I poured my heart into, and the mission was the hardest thing I’ve done in my career. But now I have some free time for GTA VI. I'm already itching to get back to addressing all your feedback. I'll share what's next soon!
852
299
281
9,856
1,079,732
Load more