Kory Kilpatrick

1.8K posts

Kory Kilpatrick banner
Kory Kilpatrick

Kory Kilpatrick

@kory_kilpatrick

Easily fascinated 😃, Endlessly curious 🧐 Poker 🃏 → Software 👨‍💻 → LLM-whisperer 🤖🚀

Austin, TX Katılım Mayıs 2009
485 Takip Edilen1.2K Takipçiler
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
@thsottiaux @jxnlco Viewing sub agents is glitchy. It would be great if I could reliably monitor their creation/closing/activity via the left under their parent thread
English
0
0
1
70
Tibo
Tibo@thsottiaux·
It’s the little things that matter, what are some small papercuts you have noticed in Codex? We’ll fix as many as possible in the next week.
English
2K
57
2.3K
261.1K
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
@Dimillian More immediately, polishing subagent communication and UI would go a long way. It seems like each new recent has introduced a different bug/regression. I'm nitpicking though - the product is truly fantastic. Great work by you and your team 🔥🙏
English
0
0
0
63
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
@Dimillian Agent Builder style GUI for workflows. It's possible (for technical people) to cobble together the pictured process with skills and hooks, but I think that amount of friction stifles innovation at the orchestration level
Kory Kilpatrick tweet media
English
1
0
0
109
Thomas Ricouard
Thomas Ricouard@Dimillian·
I’m diligently working on enhancing all the features of the Codex app to make it even better for you. If you have any suggestions or ideas for improvement, please feel free to share them with us here!
English
431
11
638
50.9K
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
You think you’re on the leading edge then a colleague tells you he’s gotten significant engineering gains from baby-talking and reading scripture to Claude Code
English
0
0
2
85
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
Traditional interfaces assumed one active task at a time. But as agents take on more work for longer stretches, users need a persistent place to keep multiple live contexts open and move between them while work continues in the background. Software is converging on a new default UI for this: left rail + main canvas. I expect to see this pattern everywhere as agents come online.
Kory Kilpatrick tweet mediaKory Kilpatrick tweet mediaKory Kilpatrick tweet media
Google@Google

Too many @GoogleChrome tabs open? Try vertical tabs, rolling out now. Just right-click any Chrome window and select “Show Tabs Vertically” to move your tabs to the side of the browser window, making it easier to read page titles and manage tab groups.

English
0
0
1
118
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
A pattern I'm seeing: 1. AI gets good enough to saturate a medium 2. Repeated exposure makes its patterns feel normal 3. Human norms and expectations adapt to those patterns 4. The distinction erodes from both sides You can already see this in coding, writing, and video. As AI becomes more human-like, we become more AI-like!
English
1
0
0
243
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
This is a funny one for me bc I agree with the reflex, but I also have a lot of real-world experience suggesting spreadsheets are extremely sticky. I spent years building bespoke finance/data analytics products. I always told my partners that I could provide the same spreadsheet experience, but MUCH richer, in a custom UI, yet I invariably ended up in the google sheets api. I currently have a number of fund managers in my consulting caseload. I show them that building a rich, custom dashboard is ~instant and ~free, and their response is "thats great...show me how to use AI to make a spreadsheet" I think their days are numbered, but I also think when the singularity comes a lot of people will ask to see it proven in a spreadsheet 😂
andrew chen@andrewchen

prediction re the end of spreadsheets AI code gen means that anything that is currently modeled as a spreadsheet is better modeled in code. You get all the advantages of software - libraries, open source, AI, all the complexity and expressiveness. think about what spreadsheets actually are: they're business logic that's trapped in a grid. Pricing models, financial forecasts, inventory trackers, marketing attribution - these are all fundamentally *programs* that we've been writing in the worst possible IDE. No version control, no testing, no modularity. Just a fragile web of cell references that breaks when someone inserts a row. The only reason spreadsheets won is that the barrier to writing real software was too high. A finance analyst could learn =VLOOKUP in an afternoon but couldn't learn Python in a month. AI code gen flips that equation completely. Now the same analyst describes what they want in plain English, and gets a real application - with a database, a UI, error handling, the works. The marginal effort to go from "spreadsheet" to "software" just collapsed to near zero. this is a massive unlock. There are ~1 billion spreadsheet users worldwide. Most of them are building janky software without realizing it. When even 10% of those use cases migrate to actual code, you get an explosion of new micro-applications that look nothing like traditional software. Internal tools that used to live in a shared Google Sheet now become real products. The "shadow IT" spreadsheet that runs half the company's operations finally gets proper infrastructure. The interesting second-order effect: the spreadsheet was the great equalizer that let non-technical people build things. AI code gen is the *next* great equalizer, but the ceiling is 100x higher. We're about to see what happens when a billion knowledge workers can build real software.

English
0
0
3
495
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
Nice run from @OpenAI lately. Outside of deep research, their products hadn’t been in any of my workflows since Opus 4 dropped last May, but the Codex app, GPT-5.2 Codex, and GPT-5.4 have all been strong releases. Props to the team! 👏
English
0
0
2
244
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
@staninthesky currently have use cases for codex (gpt5.4 xh), claude code, claude cowork
English
0
0
1
67
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
AI is so deeply embedded in my work that colleagues and I frame messages to each other with the expectation that they will be forwarded to an agent. Human to human messages are for 1) ideation 2) synchronization 3) feedback/approval 4) help with what to ask AI 5) fun
English
2
0
0
257
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
This only works if your team is AI savvy, which is a pre-requisite now
English
0
0
0
117
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
@jeremyausmus I spent years in therapy relearning to be in touch with my emotions. I suspect a healthy relationship with them is better for performance than being disconnected from them
English
2
0
7
1.8K
Jeremy Ausmus
Jeremy Ausmus@jeremyausmus·
When you play poker for a living it trains you to put your feeling aside so you can keep playing well, not letting your emotions effect your decisions. This is very important for a players bottom line. However, recently I've realized that being in the habit of muting your emotions isn't healthy in many other areas of your life. Sure it can give you resilience throughout the day but avoiding these emotions eventually leads to you feeling numb to a lot of things in life. Recently, I'm trying to focus on them more and really feel them and then move on. Maybe at the table isn't the ideal times for this but eventually you need to process these emotions. I'm already finding that being in tune with your mind and body and not shoving feelings to the side definitely has benefits.
English
40
16
443
91.3K
Andrew Rose
Andrew Rose@__drewface·
what are some books of wisdom that have gotten you through hard times in your life?
English
53
0
47
4.3K
@levelsio
@levelsio@levelsio·
Claude Code with Opus 4.6 was so dumb today I finally had to write my own code again A sad state of affairs 🥹
@levelsio tweet media
English
458
29
2K
830.1K
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
@adityaag Seamless multiplayer support is one of my top feature requests
English
0
0
2
128
Aditya Agarwal
Aditya Agarwal@adityaag·
Product Idea: There should be a shared "Claude Code" instance that can be passed around different people. It's dumb to have the software repo as an intermediate step.
English
109
14
501
100K
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
@adityaag @itsJaimeMedina fyi the sessions are saved in your ~/.claude directory on your machine. you can configure slack/gmail/etc connectors in Claude Cowork and have Claude send the session in one prompt (or skill!)
English
1
0
2
224
Kory Kilpatrick
Kory Kilpatrick@kory_kilpatrick·
If you don't want to listen you can just ask Gemini what I talk about. Or you can just read the below screenshot for the most valuable takeaway. I'm here for your attention span, anon
Kory Kilpatrick tweet media
English
0
0
1
170
👺Jesse
👺Jesse@JesseFriedland·
One of my favorite AI hacks: Gemini Ask. I listened to @badams78’s interview with @kory_kilpatrick last night while washing dishes. Today, i wanted to recall the "meta workflow" Kory shared so I went onto YouTube and clicked "Gemini Ask" to summarize it. Massive time saver.
👺Jesse tweet media
English
3
0
2
177
Peter Jennings
Peter Jennings@PeterJennings88·
I have been working with Kory on AI projects, and it's remarkable to see the output. Leveraging these tools has made me wildly more productive. I'm stoked to listen to Brandon and Kory discuss AI on this episode.
Brandon Adams@badams78

I stopped my old podcast because it felt random. This one isn't. The AI Metagame: 12 episodes exploring where AI creates leverage — and where it creates traps. Episode 1: I built for scale before I understood the problem. @kory_kilpatrick youtube.com/watch?v=Fm5K86…

English
3
0
52
21.2K