Dave Kreitter

i create jobs for robots 🤖

[Wade Foster @wadefoster]

We're killing the DM at @Zapier. Starting with the executive team.

We've long held Default to Transparency as a value. That value has largely encouraged communication in public channels. But as the company grew, DMs are a hard habit to resist and break.

But every DM is a gap in our Shared Brain. It's context that is lost for humans and AIs. As a result the cost of DMs keeps going up.

So earlier this year I posted about our exec transparency leaderboard. The leaderboard has become quite the competition internally…

I'm 3rd today. My co-founder @BryanHelmig has held the top spot as long as I can remember…

It sets a standard for the rest of the company. In fact, since last year we’ve seen the % of Slack messages in public channels go from 33% to 46%.

What the leaderboard measures

Transparency is a team sport, and a disinfectant. Every month we track what percentage of our execs' Slack messages happen in public channels versus private DMs.

When your CEO debates strategy in a DM, that decision is invisible to every agent and every team that needs to know what was decided and why. The decision happens but the reasoning vanishes.

When that conversation happens in a channel, it stays. New hires can search it, agents can read and verify it, etc. Your Shared Brain knows what's true now: ask it a question and the answer reflects the latest reality.

Taking It to the Next Level

Reducing DMs are one way to increase transparency and open up context for humans and AI, but there are other mechanisms that help too. Three things beyond the leaderboard:

1. Meetings get recorded, transcribed, and become queryable

2. We run a shared skills library. Anyone on the team can encode a workflow they've figured out into a skill and share with the team

3. And we keep score. It's a silly scoreboard, but it subtly drives positive behaviors

Raising Your Ambition

In order to get the most of AI in your company, the AIs need context. So making your context queryable is one of the most practical moves you can make to improve the effectiveness of your AI agents.

P.S. I’m coming for #1, Bryan...

[Dave Kreitter @dkreitter]

@thsottiaux @RonanMckinney @OpenAI don't forget Chronicle research preview! 😵

[Dave Kreitter @dkreitter]

@simpsoka bonus points for allowing the user to override their default settings on a per-worktree basis in the app

[Dave Kreitter @dkreitter]

@simpsoka in Settings > Worktrees, add checkboxes for:

- copy ignored files
- copy untracked files

[Bruno Lemos @brunolemos]

Codex uses feature flags to hide experimental features in the desktop app.

But you can force enable them, here’s how: https://t.co/N44qDTp2Us

[Dave Kreitter @dkreitter]

@petergyang use `/effort ultracode` and let Claude Code decide for you 🙂

[Dave Kreitter @dkreitter]

@ajambrosino don't worry; that's coming...

half joking, but I can def imagine a future state in which businesses are able to surface questions/approvals/etc via GPT. Kinda like a master data management system — always ingesting new data, then sending it out to consumer systems (humans)...

[Dave Kreitter @dkreitter]

major outages at BOTH @AnthropicAI && @OpenAI rn.

Doesn't appear to be Cloudflare... other guesses?

[Dave Kreitter @dkreitter]

@thsottiaux I use it when I'm out of credits for both Codex and Claude Code (unless reset is imminent, ofc).

[Dave Kreitter @dkreitter]

@thsottiaux ability to start a session in a pre-existing worktree (without creating a new project)

also, are automations unable to spawn subagents? cuz if so, that!

[Dave Kreitter @dkreitter]

@trq212 very much looking forward to soon!

[Pankaj Kumar @pankajkumar_dev]

GPT-5.6 Pro Leaks: Coming Thursday

- Knowledge cutoff: December 2025 (previous versions had August 2025).
- Reasoning effort ("Juice Value") increased to 960 (vs 768 on GPT-5.5).
- Vision and image to design replication are much better (it can almost copy designs)
- SVG generation, especially 3D/static SVGs, is excellent and can outperform Fable 5.
- Frontend generation has improved, but Fable/Claude still have the edge.
- Game generation is more stable with fewer visual glitches, though Fable 5 is still better overall.
- Playwright support is in ChatGPT for browser automation.
- GPT-5.6 / GPT-5.6 Pro is most likely coming Thursday.

[OpenAI Developers @OpenAIDevs]

Show Codex a workflow once. Reuse it as a skill.

Record & Replay lets you show Codex a recurring task, like filing an expense report or submitting a time-off request.

Codex turns that demo into an inspectable, editable skill.

You control when recording starts and stops.

[Q @q_yeon_gyu_kim]

codex desktop app @OpenAI is crazy

i have a session with nearly 300 subagents running more than a day
thanks to @justsisyphus lazycodex

and it is just smooth as hell
no bad experience

[Dave Kreitter @dkreitter]

@mark_k @OpenAI This was a major blocker for my father's adoption of Codex. He is a retired engineer with decades of experience working in Silicon Valley. It took me a while to figure out what he had done wrong.

That said, I'm not sure what "better" looks like.

[David Sacks @DavidSacks]

I’ve had a number of conversations with folks inside and outside government about the current situation with Anthropic, and here is what I believe to be true:

— As we know, Anthropic publicly released its Mythos class models earlier this week under the commercial name Fable.

— Fable is Mythos with guardrails. But if those guardrails fail, then you’ve exposed Mythos and its advanced cyber capabilities to people who shouldn’t have them. (Keep in mind that Anthropic itself widely promoted the idea that Mythos was a cyberweapon and needed to be regulated as such. They asked for government regulation of Mythos and championed the guardrails on Fable. If there is a vulnerability — big or small — it is Anthropic’s responsibility to patch.)

— A highly credible trusted partner of both Anthropic and the USG who was testing Fable came forward with a jailbreak of those guardrails. The Admin asked Dario to fix the jailbreak or de-deploy the model. Dario refused.

— In their blog post, Anthropic defended its decision by saying the jailbreak isn’t serious. That is not what the trusted partner and the USG believe; nor is that kind of minimizing language consistent with Anthropic’s brand as the AI safety company. It’s difficult to fathom how they could claim a jailbreak allowing operability of a cyber weapon could be defined as not “serious.”

— In the past, Anthropic has always said that safety must be top priority and taken super seriously. In this case, Anthropic prioritized the continued offering of the consumer model over safety.

— In reaction, the Admin issued the export control. The Admin did this reluctantly. It’s been very surprised that Anthropic hasn’t wanted to cooperate with a reasonable safety request (ie fixing the jailbreak issue). Anthropic’s reaction is very much at odds with their branding and ethos as a safe AI research community.

— The Admin’s hope now is that Anthropic remediates the safety issue, the export control is lifted, and Fable goes back into general release. The Admin wants all of this to happen as soon as possible. It is frankly bewildered that Anthropic hasn’t wanted to comply with safety requests that it previously said were its highest priority.

— Those trying to misdirect and tie this action to the prior DoW/Anthropic issues are wrong. The Admin values Anthropic’s technical capabilities and feels that this issue, while serious, should be easily resolved. The ball is in Anthropic’s court.

[Google Research @GoogleResearch]

🚀 Introducing Gemini-SQL2, our breakthrough text-to-SQL capability powered by Gemini 3.1 Pro! We've achieved state-of-the-art results on the highly competitive BIRD benchmark, translating natural language into execution-ready SQL queries. 🧵👇

[Dave Kreitter @dkreitter]

🙄

https://t.co/4HaC7tfCUw

[Dave Kreitter @dkreitter]

@thsottiaux 👀

[Dave Kreitter @dkreitter]

@morganlinton @thsottiaux rad!! congrats