Jake Bernstein

PM on model behavior / research @openai
From St. Louis

[Jake Bernstein @jake_bern]

I'm a boomer with finance: I download monthly expense CSV from Chase, Amex, WF, BoA, merge them, and then manually tag. Always preferred this to Mint, etc.

For years this meant 30 minutes/month of pure frustration with clicking through archaic banking interfaces to download the right CSV. Tried computer use several times for this past couple years, never worked consistently till now.

@arix @JamesZmSun and team are absolutely cooking and CUA is really turning a page.

[Jake Bernstein @jake_bern]

@businessbarista https://t.co/RWn5kY9hbO is shutting down, but this was a big use case for us! people would share out their usernames, and find an accountability and track together.

heard of a few people become friends over this!

[Justin @JustinBleuel]

Fun fact I built / experimented / shipped this feature as a newbie PM to @ChatGPTapp entirely thanks to Codex

If you're a PM (or designer!) try prototyping + shipping directly to the codebase

The hardest part often the local build and the good news is Codex can help there too

[Michelle Pokrass @michpokrass]

we shipped a new version of gpt-5.5 instant today. the previous model was too bullet pilled. the new one improves on some other important dimensions: sycophancy, factuality, and multilingual performance. hope you'll like it! always interested in feedback

[Jake Bernstein @jake_bern]

@reach_vb @AriX @simpsoka @ajambrosino @embirico @TheRealAdamG @JustinBleuel will fix all your bugs

[Jake Bernstein @jake_bern]

Initially heard about this idea from here: https://t.co/ZnpkR71ASR and also @alexalbert__https://t.co/EwunujPdMG

When I worked at Meta, I used Claude Code for this. Both tools can do the job and quality seems comparable, with a couple key deltas:

1. Codex is cheaper/more token efficient: on a recent batch of 60 screenshots: Codex used 1/4 as many tokens - 31K (5.5 High) vs. 115K (Sonnet 4.6 High)

2. IMO Claude Code provides more friendly/understandable updates for non-technical users

[Alex Albert @alexalbert__]

One of the bigger shifts for me with Claude Code over the past few months has been shutting down that initial dismissal I have when a task feels "not worth my time"

Like I'll think "it would be nice to rename all my screenshots with what's actually in them" and immediately move on. Now I just ask Claude and it takes one minute to find out if it works.

When I zoom out, it gets kind of dizzying. Almost anything you can imagine doing on a computer is quickly becoming available if you can just string together the right words to describe it.

[Jake Bernstein @jake_bern]

My desktop is a wasteland of product onboarding flow screenshots and old receipts.

Codex: “Rename the screenshots on my Desktop based on what's in the actual image.”

[Jake Bernstein @jake_bern]

Text can use some improvement, but the general content/formatting are FAR better than 5.2 Pro, the last time I tried this.

[Jake Bernstein @jake_bern]

Sure you can use GPT 5.5 Pro for frontier math... but you can also use it to make a coffee table book with the history of your home.

Here's my neighborhood in St. Louis in 1941.

[Jake Bernstein @jake_bern]

Prompt: "You are an expert St. Louis Historian and should use all resources available to you. Included is the public record for {redacted address}. Reference these to help you speed up/direct your research.

My parents own {redacted} address.

For a house gift, I want to make a report which talks about the history of their house/neighborhood. I will print this report at Fedex, bind in spiral book and give to them as a gift. It should include things like

1. old photos of house/street/neighborhood
2. old maps, where possible annotated with historically interesting/relevant facts
3. interesting facts about the house, street and neighborhood

Other tips - if you are struggling to find info on S Meramec Ave,, discussing Clayton, Davis Place and N Meramec is also useful. Their interests include fitness, medicine, judaism. If there is anything about these topics in clayton, be sure to include. Constraints - report should be interesting and visually appealing, not strictly a table of facts - output in multiple ways
1/ in PDF
2/ content in thread here
3/ downloadable .md markdown file.

You are an expert St. Louis Historian and should use all resources available to you. Included is the public record for {redacted address}. Reference these to help you speed up/direct your research."

Optionally, attach a public record of your address for better result (download for $1 online).

[Justin @JustinBleuel]

Codex computer use entirely driving iphone simulator to bug bash a feature it just built

[Jake Bernstein @jake_bern]

My favorite use case: https://t.co/azNu3TrTdP

Important caveat: graph ends May 8. Now we're counting ounces instead of tokens :).

[Jake Bernstein @jake_bern]

Spreadsheet++:

I used to live in spreadsheets. Now, when I’m labeling data or auditing LLM judges, I ask Codex to spin up a custom UI with filters, side-by-sides, etc.

These UIs never get committed - they just make reviewing data +50% faster and more fun.

[Jake Bernstein @jake_bern]

I joined OAI in end of Feb. Started as a Codex boomer, bottom 5% of employees. Now I'm a believer.

[Jake Bernstein @jake_bern]

@maxjendrall @Kareld Agree re: expanded support for markdown/in-app tools!

All feedback is appreciated - here or wherever you end. But probably the best way to make sure your feedback is captured is to use "/feedback" in Codex! I personally read lot of the feedback that come through!

[Jake Bernstein @jake_bern]

A month ago, I was in the bottom 5% of Codex users at OpenAI. Now I’m near the top.

Here’s how I’m using billions of tokens:

[Jake Bernstein @jake_bern]

@Kareld I'm holding my own w/@JustinBleuel in token count, but just about 1000X behind him in production PRs :)

[Jake Bernstein @jake_bern]

Data pipelines on demand:

In the past, I’d punt when a “quick analysis” required joining sheets, rater campaigns, CSV exports, and internal tools. Too messy and tedious. Now I ask Codex to fix row IDs, check missing columns, find duplicates, and move everything into a standard schema.