Brad

Dev stuff. Development manager during the day, indie builder at night.

[Brad @BradButner]

AI building apps fast isn't news in 2026. What's different: two agents working in relay with zero human code.

@perplexity_ai Perplexity Computer architected PulseView in 6 hours. OpenAI Codex shipped 16 production commits over the next 18. Full multi-agent orchestration.

https://t.co/Ch9Gjdr4Vb

Full writeup: https://t.co/eChWjZO2VH

(and yes the video was made by Perplexity Computer)

[Brad @BradButner]

@thsottiaux Yes 👍 Would be useful to keep things going overnight on long running tasks at a lower usage rate

[Brad @BradButner]

Been away from Cursor for a while. Looks like it’s time to return https://t.co/OFYr6e65Xq

[Brad @BradButner]

/goal build a clone with GH actions support, make no mistakes

[GitHub @github]

We are investigating unauthorized access to GitHub’s internal repositories. While we currently have no evidence of impact to customer information stored outside of GitHub’s internal repositories (such as our customers’ enterprises, organizations, and repositories), we are closely monitoring our infrastructure for follow-on activity.

[Brad @BradButner]

@kristelxo 🫡 here with two and five year olds and also haven’t slept in years

[Brad @BradButner]

Having a lot of fun with Codex Remote, the Mac Mini has a new purpose in life, working on ideas when I’m on the go

[Brad @BradButner]

Just got this setup tonight too on the Mac Mini. Monitoring a goal from my phone. Pretty awesome.

[Matt Shumer @mattshumer_]

Just wiped the Mac Mini I set up for OpenClaw.

I’m turning it into an always-on devbox to use with Codex mobile.

Have a feeling this is gonna be amazing.

[DANΞ @cryps1s]

Your ChatGPT account is one of the most important and valuable digital accounts you'll ever have.

Secure it with Advanced Account Security today. https://t.co/VaSjEZ5ck5

[Brad @BradButner]

Final results on a Codex goal run. Absolutely crazy.

[Brad @BradButner]

Been working on a new voice assistant with the original realtime release and dropped this into the codebase with some prompt tweaks. So far, a much more natural conversation and feels less forced. Just had a casual chat with it over realtime.

[OpenAI Developers @OpenAIDevs]

Building voice applications with GPT-Realtime-2?

Our new prompting guide covers how to tune reasoning effort, use preambles, design tool behavior, handle unclear audio, capture exact entities, and maintain state in longer sessions.

https://t.co/9zfdhIX4Vq

[Brad @BradButner]

52 hours of Codex running and going. Using /goal is fun with a good prompt

[Cursor @cursor_ai]

We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor.

Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.

[Nate Berkopec @nateberkopec]

One detail from this story: the AI finding credentials laying around. I have moved to scrub all credentials stored anywhere in plaintext on my system. No more .env, no more ~/.aws/credentials, etc. I use fnox with a 1password backend.

[kate @whoiskatrin]

cloudflare sandboxes are now generally available

agents get a real computer: terminal, interpreter, live preview urls, secure credentials. it sleeps when idle and wakes on demand

they can do actual engineering work: clone a repo, run tests, fix failures, repeat

that loop is what makes engineers effective. now agents have it

https://t.co/p7ooV6R9eQ

[Rita Iglesias @rita_codes]

We’ve been cooking something…
Here it is! ✨

https://t.co/gFKQ3GqxeM

#scheduler #mui #react

[Blaine Wilson @optomachina]

Holy smokes

Beats sonnet 4.6

74TPS

$.25 in / $.90 in

arcee-ai/trinity-large-thinking @ openrouter

[Ben Sigman @bensig]

My friend Milla Jovovich and I spent months creating an AI memory system with Claude. It just posted a perfect score on the standard benchmark - beating every product in the space, free or paid.

It's called MemPalace, and it works nothing like anything else out there.

Instead of sending your data to a background agent in the cloud, it mines your conversations locally and organizes them into a palace - a structured architecture with wings, halls, and rooms that mirrors how human memory actually works.

Here is what that gets you:

→ Your AI knows who you are before you type a single word - family, projects, preferences, loaded in ~120 tokens
→ Palace architecture organizes memories by domain and type - not a flat list of facts, a navigable structure
→ Semantic search across months of conversations finds the answer in position 1 or 2
→ AAAK compression fits your entire life context into 120 tokens - 30x lossless compression any LLM reads natively
→ Contradiction detection catches wrong names, wrong pronouns, wrong ages before you ever see them

The benchmarks:

100% recall on LongMemEval — first perfect score ever recorded. 500/500 questions. Every question type at 100%.

92.9% on ConvoMem — more than 2x Mem0's score.

100% on LoCoMo — every multi-hop reasoning category, including temporal inference which stumps most systems.

No API key. No cloud. No subscription. One dependency. Runs on your machine. Your memories never leave.

MIT License. 100% Open Source.

https://t.co/KggwTqijmD

[Kyle Mistele 🏴‍☠️ @0xblacklight]

🚨 URGENT 🚨

if you have run npm install / bun install / equivalent in past couple hours

run this - if IoC is found your device is cooked, shut it down and get it to infosec/IT folks asap

[Feross @feross]

🤨 People keep asking how to protect yourself.

#1: set min-release-age=7 in .npmrc

#2: install Socket for GitHub (it's free!) to protect PRs from bad dependencies: https://t.co/D9bsRJj65R

#3: install Socket Firewall (also free!) to protect your laptop: https://t.co/u1NRD57PQ8

[ESCHA (๑ˊ͈ ^ˋ͈) @eschadiol]

you might scroll past this and think “cool little experiment” and then never think about it again but really this dude just tore the fabric of space time, web-based editorial design about to go crazy after 30 years of broken text rendering holding us back

[Brad @BradButner]

So someone thought it would be funny to put this in our agents.md file, which has been causing this headache 😐

[Brad @BradButner]

Anybody seeing a lot of “This conversation has been compacted and I have lost detailed context” in Codex lately?