Blake Samic

You can now summon Codex from anywhere on your desktop. It's easier than ever to reach for Codex.

Are you up for a challenge? openai.com/parameter-golf

job market so bad I'm actually pursuing my dreams

We rolled out interactive visual explanations in ChatGPT to help people understand math and science concepts more intuitively. You can adjust variables, manipulate formulas, and instantly see how those changes affect graphs and outcomes. One cool thing behind the scenes: the team built a Codex workflow that helps turn common math questions into visual learning blocks. Try it out and let us know what you think. openai.com/index/new-ways…

5.4 is really special.

GPT 5.4 is now shockingly good at reviewing slides, as I discovered last night. It feels like a detailed teardown from an expert in your field. You’ll get specific edits on each slide + a broader view on how to frame your narrative better. It’s hard to describe - just try it!

I gave ChatGPT for Excel and Claude for Excel a try on a very hard Excel file: macro-economic data from 1,000 years of English history across over a hundred tabs. I think both did a good job, and I did not spot errors (though I only did spot checks). However, Claude was harder to check because ChatGPT tended to stick within the Excel app, building formulas and manipulating the data in the way a person would. On the other hand, Claude used Python and often pasted material into Excel for display purposes only, making it harder to trace or edit. If that holds, I think it will generally make ChatGPT more useful for serious users if you want to audit the results. Prompt: "help me understand the relationship between the mix of agricultural products in the UK, GDP, and population, along with hours worked. I want this over the total period, and you should illustrate interesting trends with graphs and statistical analysis

Opus 4.6 vs GPT-5.4 (High) (6/9) Testing out how well these models to with cloth physics simulation, and honestly both where pretty close here but my god I am shocked how good GPT 5.4 is with optimizing this scene whilst opus 4.6 felt quite janky and lower fps. GPT 5.4 also got the cutting working properly whilst Opus was just floating about. I do want to heavily stress the fact that making this prompt, Opus 4.6 cost the whole 100% of the session ($20 pro plan) + $3 in credits whilst GPT 5.4 only cost 10% of the usage. prompt: Build a premium Vite + React interactive cloth simulation of a cozy room curtain using real particle/constraint physics, with structural + shear springs, damping, collisions, and stable real-time deformation. Users should be able to drag the curtain, add wind, and cut constraints, while the experience stays polished, visually elegant, and numerically stable.

a buzzer beater is so much more impressive in the case where missing it would mean you lose (not tie and go to overtime) 🏀

I asked Codex 5.4 to reverse engineer a DOS game with no source code. It’s been running for 6 hours, I can’t look away. It unpacked assets, disassembled the EXE, rebuilt the renderer, and built my childhood favorite SkyRoads in Rust! Now think of all the games we can revive.

$200/mo ChatGPT Pro + gpt-5.4 xhigh + Codex Mac App is the most asymmetric upside I've ever seen in a tool chain. A ridiculous cheat code for founders.

@sound4movement Nice! Mine has a focus mode, highlighting a single task and shows a timer.

@blakesamic Mine has a cute timer that tracks how long I work on different things! So I can see what I am not spending time doing. ⏱️

if you aren’t using codex to iterate on the todo list app of your dreams, what are you even doing

We're introducing Codex Security. An application security agent that helps you secure your codebase by finding vulnerabilities, validating them, and proposing fixes you can review and patch. Now, teams can focus on the vulnerabilities that matter and ship code faster. openai.com/index/codex-se…

BREAKING: @OpenAI just released GPT-5.4 and it is AMAZING. We spent a week @every putting it through real engineering tasks from code reviews to planning workflows and using it inside of our @openclaw setups. The verdict: OpenAI is back in the coding race. - Its planning capability consistently beat Codex 5.3 and Opus 4.6 in head-to-head tests. It produces plans that are thorough and technically precise, and have a user focus and “human” feel that has been missing from OpenAI's previous coding mode - It reviews code with more depth than 5.3 Codex, and a much more conversational voice that doesn't make you feel dumb. - It became our go-to model in @OpenClaw: with some model-specific tweaks to the harness it's fast, intelligent, and more human. It's also about half the price of Opus 4.6. As ever, there are tradeoffs: - GPT-5.4 has a tendency to expand the task well beyond what you asked for and to call tasks done before they're finished. - In the @OpenClaw harness it sometimes completed tasks in obviously wrong ways, then lied about it. Overall though, it's my new daily driver for coding and in my Claw. Its thinking-traces produced some genuine wow moments for me. Our complete vibe check is available on @every now -> every.to/vibe-check/gpt…

This was built with the Playwright Interactive skill! In case you missed it, Codex now has a JavaScript REPL that it can use to iteratively build and debug front-end work. It's great for complex UI or games because it can write snippets without having to start from scratch every time.

Had early access to GPT-5.4 and Pro. They are very good. One fun illustration of progress, this is the same prompt I used in GPT-4 below (making a 3D space inspired by Piranesi) now in GPT-5.4 Pro. There were no errors, made in a single prompt plus one to "make it better."

5.4 is faster and better at professional work -- with big improvements in spreadsheet, doc, and slide creation. In Codex and the API, it's our first general purpose model with native SOTA computer use capabilities, which is going to enable so much more agentic work.

Folks, the codex team needs more great people! You can pick your battle, be it cli, Windows, or future products. OpenAI has lots of very high agency motivated folks and overall has been amazing so far. Apply! openai.com/careers/search…