Adrián Melic

Bring Codex to your team without fixed seat costs. We’re rolling out usage-based pricing for Codex in ChatGPT Business and Enterprise plans, so teams have a more flexible way to get started.

¿Qué personajes/referencias dejamos dentro y cuáles dejamos fuera? Director: yes

¿Cuántas escenas de acción quieres en la nueva película de Super Mario? Director: yes

@MilksandMatcha I'm trying to make Codex play Baldur's Gate 3 with GPT-5.4 and GPT-5.3 Codex Spark. Things to explore: computer use, adding hotkeys, SKILL.md to map UI and some tactics... I'm curious what it will choose for the romance part 👀 x.com/adrianmelic/st…

Giving away 5 Codex Pro plans Each person will get 3 months of free Codex Pro (highest tier). Winners will be selected from comments in 48 hours, comment below why you want it.

“fake work” and “bullshit jobs” has been fantastically wrong and misleading for understanding the modern world. a much better understanding is of a global economy where minor skill differences and improvements lead to monumentally different outcomes, and the marginal hour of work has never been more measurable or useful after the advent of even moderately effective talent allocation systems and the variability of reward based on effort and skill, people have engaged much harder in a red queen rat race across the world. this is why the Chinese ‘cram schools’ exist and why ‘yuppie striverism’ is a thing and why people trade off later family formation for working more so often. while overall work hours are slightly down, they are actually up for high earners (nber.org/digest/jul06/w…) I see it in the marginal effect with my friends now after the advent of claude and codex: they are actually working harder now than they ever have before. this is due to a personal Jevon’s paradox where they see that the value of their time has increased dramatically, that they can get a lot more visible work done towards goals they care about than they used to after requests from their customers the labs are doing things like inventing dispatch which lets you monitor work and manipulate your computer from your phone, on top of prior changes like having always on communications (slack). You hear about people launching codex jobs from their phone the moment they have an idea and reviewing them later no clue how long this lasts but the most immediate impact of co-existing with the machine state is higher productivity and higher visibility which leads to more work hours

Falta reasoning "paperclip maximizer 📎" con razonamiento infinito, pensando para siempre hasta acercarse a una teoría del todo y acabar computando con toda la galaxia

Propina: decir "gracias" aún sabiendo que pagas por esos tokens

@reach_vb @xeophon For open tasks and hard problems, I ask (in AGENTS md) to generate an EXPERT_REPORT md. Then I upload it to ChatGPT 5.4 Pro, along with code or other files. I pass the answer to Codex and repeat the process

@xeophon Good request! I have an internal skill for this which allows you to use GPT 5.4 Pro via the API and provide it the right context but I’m not sure if this makes as much sense price wise!

We are expanding Codex’s toolkit - what tools would you love to see work with codex the most?

¿Cómo desinstalar Copilot de VSCode? - Ve a Extensions - Desinstala o desactiva: GitHub Copilot | GitHub Copilot Chat - En Settings, escribe `chat.disableAIFeatures: true` - Reinicia VS Code

AGI-pilled people trying to explain to normies that AI progress continues to be rapid

⤴️

Talking to tokenmaxxers for this column gave me a strong suspicion that AI providers are going to be compute-constrained for the foreseeable future. There isn't nearly enough compute in the world for even 1% of white-collar workers to work this way.

En 10 años se verá que no fue ChatGPT, fue Codex

NotebookLM: Do a deep research report and make a video where a consultant gives Sauron a strategy for actually winning the War of the Ring: "All you need to do is sign off to put a simple door on your volcano" The new video generation feature for NotebookLM is very impressive.

the most underrated hire right now is a great product person. when i say product person i'm def not talking about a product manager. perhaps i think there has to be somewhat of a new role. i don't have a good name for it yet but maybe something like "product thinker".. someone with an intuitive grasp of the product as it exists, where it's soft, where it sings, & how to iterate it toward something even sharper. in some sense, this person has to cohesively hold in their head where this product should be 2 years from now & work backwards from that. i say this cuz when building was hard, engineering was the bottleneck & the status hierarchy often reflected that. building is no longer hard. which means the variance in outcomes has shifted almost entirely to judgment on what to build, how to sequence it, & how to talk about it. & the story matters as much as the thing. internally, it organizes the team around a shared model of why. externally, it shapes the interpretive frame users bring to their first experience. you can't retrofit narrative onto a product & expect it to land, it has to be load bearing from the start. the rarest version of this person sits at the intersection of culture & deep technology. someone genuinely bilingual. they know what's technically possible & they know which cultural currents are real vs. ephemeral. that combo is what separates products that feel inevitable from products that feel assembled. before ppl clap back with this person has always been valuable, i know.. i am just saying now they might be the most *important* person in the room. their value compounds like never before.

@jxnlco For curiosity, I tried CoastRunners with Playwright, but without success becouse its a Flash game. It's been almost 10 years! openai.com/index/faulty-r… I will keep trying with more turn based Steam games 😄

@adrianmelic what?! what other games have you tried?

Send me your non coding Codex demos! - 30-50 second video music production, game development, 3d, automations, anything. anything good we'll shoot over some credits so you can go deeper!

Two years later... trying the Codex App with GPT-5.4 to play Baldur's Gate 3. So far it's mostly experimenting with clicks, keyboard, and using the Screenshot Capture skill. I haven't made big progress yet and it still gets stuck a lot, but I want to keep testing and maybe build a sort of "play Baldur's Gate 3" skill.

@Plinz Baldur's Gate 3 is an AGI eval. I would let a future AGI play the game to analyze its choices

I recognize Baldur’s Gate 3 as a screaming triumph of modern interactive storytelling technology, but as a romantic, it remains almost completely empty for me, because nothing in its universe relates to my own existential questions. There is no love for me in Baldur’s Gate.

Gave GPT 5.4 in Vesence for Excel the decompiled Pokemon Red and it made me a playable demo of the overworld. Made with 100% Excel formulas.

What if a codebase was actually stored in Postgres and agents directly modified files by reading/writing to the DB? Code velocity has increased 3-5x. This will undoubtedly continue. PR review has already become a bottleneck for high output teams. Codebase checked-out on filesystem seems like a terrible primitive when you have 10-100-1000 agents writing code. Code is now high velocity data and should be modeled at such. Bare minimum, we need write-level atomicity and better coordination across agents, better synchronization primitives for subscribing to codebase state changes and real-time time file-level code lint/fmt/review. The current ~20 year old paradigm of git checkout/branch/push/pr/review/rebase ended Jan 2026. We need an entirely new foundational system for writing code if we’re really going to keep pace with scale laws.