Adam.GPT

“A head of broccoli complaining about the weather” #DALLE

@OlivierDDR @SemiAnalysis_ ack, thx. cc: @ajambrosino

@TheRealAdamG @SemiAnalysis_ I use CLI but yeah that’s the biggest blocker just give me AgentStop hook bro

Olympian Gold Medalist Alysa Liu, recently went viral for her Teen Vogue rant on OpenAI Codex. “I can see why Sam Altman open sourced Codex. Clearly the experience is significantly worse than Claude Code. I was unable to feel the AGI using Codex. As oppose to using Claude Code, I felt the enlightenment coming and support UBI ”

@OlivierDDR @SemiAnalysis_ If it had hooks would that flop to true?

@TheRealAdamG @SemiAnalysis_ true false codex doesnt have hooks bro, let alone aysnc hooks

openai.com/index/how-we-m… "How we monitor internal coding agents for misalignment - Using our most powerful models to detect and study misaligned behavior in real-world deployments."

Imo, Codex has been way better than Claude Code for a few months now. So glad to see the OG using it!

We've reached an agreement to acquire Astral. After we close, OpenAI plans for @astral_sh to join our Codex team, with a continued focus on building great tools and advancing the shared mission of making developers more productive. openai.com/index/openai-t…

@fingerInYHd Hmmm… tbh idk. Cc: @jxnlco @dkundel

@TheRealAdamG Hehe. That’s usually the case! I also used to brag to my Claude colleagues all the time, but the last three days have changed everything. x.com/fingerInYHd/st…

GPT-5.4-mini is that fast slot receiver you always wanted to pair with your stud QB (GPT-5.4).

@fingerInYHd Limits are too high? sorry. :)

@TheRealAdamG Is someone looking at codex limits situations?

I added a /codex skill that does plan and code review in Claude Code and it has found so many more bugs and helped with far more elegant architectural designs And tomorrow I will launch native Codex support so you can use GStack on Codex

OK Codex is GOAT at finding bugs and finding plan errors

5.4 is the first true "coworker" model that can "work alongside" you every other model feels like you have to DRAG IT along with the task 5.4 steadily passing the uncanny valley of being a true teammate

In just two days, using OpenAI Codex app GPT-5.4, I created a fully functional flow cytometry data analysis software, ~20,000 lines of code from scratch! This is a highly sophisticated and specialized biology software tool that every immunologist relies on. The best part is that I can continuously improve it and add new features that are not even available in comparable commercial software, which can cost thousands of dollars per user! For those not familiar with what flow cytometry software is, here is the detailed explanation from Grok: Flow cytometry analysis software is like a super-smart graphing calculator for biologists and doctors who study cells. What the machine does firstImagine you have a sample of blood or tissue with millions of cells. The flow cytometer machine lines the cells up single-file like cars on a highway and shoots lasers at each one as it zooms by (thousands of cells per second). The lasers tell the machine things like:How big is the cell? How “grainy” or complicated is it inside? Does it have certain “flags” (proteins) stuck on it? (These flags light up in different colors, like red, green, purple tags.) The machine spits out a huge computer file full of raw numbers — no pictures, just data. What the software is forThe analysis software takes that messy pile of numbers and turns it into clear pictures and answers you can actually understand. Think of it as the “translator” or “artist” that draws the story from the data.With a few clicks you can see:Colorful dot plots or graphs that show different groups of cells (like “these blue dots are healthy immune cells, these red dots are cancer cells”). Exactly what percentage of the cells are a certain type (e.g., “78% of the cells in this blood sample are fighting the infection”). How strongly a cell is “glowing” with a certain color tag (which tells you how much of a protein it’s making). Side-by-side comparisons of a patient’s sample before and after treatment. The magic trick scientists use every dayThe most common thing they do is called “gating.” It’s like drawing a circle around a group of similar dots on the graph and saying, “Only look at these cells.” The software instantly counts everything inside that circle and gives you the numbers. You can keep drawing smaller and smaller circles to zoom in on very specific cell types — kind of like zooming into a crowd photo until you only see people wearing red hats and glasses.

I don’t give a lot of compliments but the way Codex cli & app is designed so it reuses code (that anyone else can reuse as well) is really quite elegant. Elegant in a way that it could only be the result of an experienced & thoughtful team. Which is rare at their speed & scale.

@BrendanFoody There's even a benchmark with a Search sub-score that shows this! x.com/deredleritt3r/…

it's under appreciated how excellent OpenAI models are at web search

@arakharazian No doubt you have an offering, but if a customer doesn't use it -- you aren't capturing things, right?

@TheRealAdamG It does come through Ramp, we have bill pay too ramp.com/accounts-payab…

Here's why Ramp data shows Anthropic is gaining on OpenAI 1/ An early focus on intensive AI use-cases. Not just consumer chatbots, Anthropic captured software engineers and early adopters. These people became evangelists as broader orgs started to adopt AI 2/ Right place, right time with a consumer rollout. Cowork captured the less technical corporate users who wanted access to Claude, without having to use terminal / Claude Code. 3/ Early signs that DoD move helped Anthropic's brand >> fueled growth with users who supported it.

@arakharazian But if it doesn't come through Ramp's systems -- where are you getting your data to account that for that?

@TheRealAdamG Invoicing / bill pay spend is included in this analysis, in addition to card