Jack R. Curran

Excel and financial modeling with GPT 5.5 Pro is way better than 5.4 Pro, and takes 60% less time

If you try the agents product in ChatGPT, you'll notice incredible levels of detail and polish. Includes but is not limited to: * agent mascots * amazing animations * thoughtful UX * ...and more @tylernotfound, @zach__johnston & team responsible for a whole lotta that.

ChatGPT for Google Sheets Listing: workspace.google.com/marketplace/ap…

Introducing ChatGPT for Google Sheets! We’re incredibly excited to ship this — bringing ChatGPT directly into the Sheets workflows people already use every day. You can start with a blank workbook and ask ChatGPT to help build, edit, analyze, and update sheets in natural language — whether you’re planning a wedding, building a cafe business plan, or running financial planning for your online business. Excited to see what people build with it! We'll be continually iterating on the experience, so please do let us know what you think. Link in thread :)

ChatGPT for Excel is now available to Plus and Pro plans in Europe! This marks the moment of worldwide availability across Plus, Pro, Business, Enterprise, EDU, and Teachers plans! #ChatGPT @OpenAI

We are super excited to launch the in-app browser inside Codex with comment mode! View any web pages & iterate with your agent quickly with just point and click. Codex will automatically capture a screenshot, the DOM element, and feed it as precise context to your next chat. No more switching between browsers, dragging screenshots, and wrangling with underspecified prompts. It's great for front-end development of apps/pages, but also very useful if you have documentation pulled up on the side and just want to ask a question!

Codex just got a lot more powerful. Computer use, in-app browser, image generation and editing, 90+ new plugins to connect to everything, multi-terminal, SSH into devboxes, thread automations, rich document editing. Learns from experience and proactively suggestions work. And a ton more.

We're bringing Skills and Apps support to ChatGPT for Excel! Available today for Plus, Pro, Business, Enterprise, EDU, and Teachers plans. You can now build your own skills or upload them directly in ChatGPT for Excel. We're also including a few default Skills in the product to help with formatting. Using Apps, you can bring in the data you know and trust from providers like @SPGlobal , @LSEGplc , Daloopa, @PitchBook , @Quartr_App, @Moodys, Ramp, @stripe , @MorningstarInc , @SharePoint and many more. Proud to be a part of the @OpenAI team! More to come. Now back to building. 🚀

@PhilippSpiess @OpenAI Welcome aboard!

Big news: today is my first day at @OpenAI. I’m joining the Codex team to work on the Codex app. Couldn’t be more excited for what’s ahead.

@marianoaavila @OpenAI Welcome to OpenAI!

Excited to share that I'm joining @OpenAI as Member of Design Staff!

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.

This week's guest on Uncapped is @bradlightcap, COO at OpenAI. We talked about the history of OpenAI, the shift in AI from chat to agents, where new startups can endure, Codex, FDEs, working with Sam, and more. Hope you enjoy! (0:00) Intro (0:39) The early days of OpenAI (3:47) A research centric culture (7:32) Post-ChatGPT chapters (11:54) Sci-Fi future or good software (15:26) AI’s impact on rural communities (18:57) Codex and coding of the future (24:04) Doing a lot of things at once (27:55) What VCs should invest in (35:43) The software sell off (38:23) Using Codex over ChatGPT (42:32) FDEs and Private Equity (44:53) Working with Sam

Really excited to get ChatGPT for Excel (beta) into more people’s hands. We've just rolled out globally for Business, Enterprise, Edu, Teachers, and K-12 plans. Also available for Pro and Plus plans everywhere (minus the EU). Many finance, accounting, and ops teams are already using it day to day. Try it out and let us know what’s working, what you’d love to see, or where we can make it better! :)

Chatgpt Vs Claude in Excel TLDR: Gave ChatGPT and Claude the same credit risk modeling task in Excel. ChatGPT followed proper methodology, did variable clustering, train/test split, Excel native model, AUC 0.627 on test data. Claude skipped clustering, inflated IV with sparse categories, ran the model in JavaScript not Excel, reported 0.706 AUC on training data with no split. Chagpt 5.4 nailed a real world Banking and Finance modelling case study. I gave both ChatGPT and Claude the same banking credit risk dataset with the same prompt: bin the variables, calculate Information Value, do variable clustering, select features, build a model in Excel, generate ROC. Basically an end to end scorecard development workflow inside Excel. ChatGPT followed the brief properly. Quantile-based WoE binning, IV ranking across all 33 variables, correlation-based variable clustering at 0.75 threshold to remove redundant features, picked 6 representative variables, built a 2-variable Excel-native decision tree with proper train/test split via ID mod 10, scored leaf-level bad rates, ROC on held-out test data. AUC: 0.627. Claude looked more impressive on the surface. 28 sheets, individual binning for every variable, logistic regression with 27 features, gradient descent at 500 epochs, full coefficient table with importance bars, confusion matrix, precision/recall/F1. AUC: 0.7066. Sounds like it won right? So, The logistic regression was computed in JavaScript via execute_office_js and results were pasted as static values. That's not Excel-native, against the task. The 0.706 AUC? On the full training set, no train/test split. That number is meaningless. Variable clustering? Skipped entirely even though the prompt explicitly asked for it. It "selected" 31 out of 33 features which is barely feature selection. The entire feature ranking was built on a methodological error. I've done this exact dataset myself with deeper feature engineering and ensemble technique hit 0.70 AUC. The fact that ChatGPT got to 0.627 with less feature enigineering and naive modelling is genuinely impressive. Binning and IV based feature selection is one of the most important techniques in credit risk modeling and it nailed the workflow. One thing claude did well is the workbook is visually impressive. One area ChatGPT can improve, the visuals and formatting could be sharper, the workbook is functional but not polished.

GPT-5.4 is the best model we've ever evaluated on our "Investment Banking" benchmark – it's basically starting to saturate the eval at 87.3%. The research team really cooked with this one – and you can try it in Excel today w/ your ChatGPT subscription: openai.com/index/chatgpt-…

Try gpt-5.4 with their new excel/plugin extension. I've tried the claude/opus one and it was fine, nothing super impressive, it was expensive on token burn. 5.4 impressed with speed and accuracy of edits, pasting screenshots from rithmic trading accounts and fixing formulas.

Excited to share that I joined the incredible team at @OpenAI a few months ago -- and today, we’re launching the beta for ChatGPT for Excel. Try it out and let us know what you think! We’re just getting started for what's to come. 🚀🚀

Compete with @PJClark at your own risk. Completely unsurprised by his success over the past few years. And he’s just getting started…

.@ThriveCapital is the world's premier investment fund. Bold statement, but I would bet on them everyday of the week - successfully backing category defining companies across early stage, growth, publics, and even PE/rollup-esque plays with Thrive Holdings. @vhankes is a big part of why I feel that way. He is one of the most thoughtful, insightful, and first-principles oriented investors I've ever met. Find the time this week if you can to listen to this conversation.