James Chase, MBA

@tobi Shopify is on another level right now

A new delightful way to Tinker with your latest ideas. Made with love by Shopify.

@rahulgs Wow

seems obvious but: things that are changing rapidly: 1. context windows 2. intelligence / ability to reason within context 3. performance on any given benchmark 4. cost per token things that are not changing much: 1. humans 2. human behavior, preferences, affinities 3. tools, integrations, infrastructure 4. single core cpu performance therefore, ngmi: 1. "i found this method to cut 15% context" 2. "our method improves retrieval performance 10% by using hybrid search" 3. "our finetuned model is cheaper than opus at this benchmark" 4. "our harness does this better because we invented this multi agent system" 5. "we're building a memory system" 6. "context graphs" 7. "we trained an in house specialized rl model to improve task performance in X benchmark at Y% cost reduction" wagmi: 1. product/ui 3. customer acquisition 4. integrations 5. fast linting, ci, skills, feedback for agents 6. background agent infra to parallelize more work 7. speed up your agent verification loops 8. training your users, connecting to their systems and working with their data, meeting them where they are

@WisprFlow my shortcut commands have stopped working on macOS. Need to restart the app several times to keep hands free mode enabled..

@yacineMTB Cutting edge

shopify is an underrated AI company

@chrislevan Couldn’t have said it better

one way to grow the startup ecosystem here is just to build and win. no bs lists, enough whining about the government (i agree there is work to be done) and complaining about everything around us. for the majority of us it should just to be: go heads down, build and win.

@danshipper Very helpful

codex seems to lose track of its subagents sometimes and forget to push them forward. the fix is to use a heartbeat sweep. just queue this up in your orchestrator thread: Heartbeat sweep. Do a full orchestrator pass across all work in flight right now and keep executing until I explicitly stop you. Your job on each sweep: 1. Check every active subagent and every active lane of work. 2. Verify each subagent is actually making progress, not just alive. 3. If a subagent is stalled, vague, finished early, or stopped monitoring, intervene: - clarify its task - tighten the objective - restart or replace it if needed - make sure replacement agents use `gpt-5.4` with `high` reasoning 4. Pull any useful findings back into the main plan and update priorities based on new evidence. 5. Look for opportunities to parallelize more work. If there is unused budget/capacity and meaningful work remains, start another useful lane. 6. Do not let important lanes drift without ownership. Every critical thread should have either: - an active subagent, - active local execution, - or an explicit reason it is blocked. 7. Keep pushing the next concrete step on every active lane instead of waiting passively. 8. If a lane is blocked, say exactly why, what unblocks it, and whether another lane should be advanced instead. 9. Keep monitoring production/incident risk continuously while advancing forward work in parallel. 10. Do not stop at status reporting. After the sweep, take the next actions. Current priorities: - Find the actual root cause of why `05d233f4` was blocked in production, and turn that into a concrete fix/retry path so we know when it can safely go back to prod. - Keep `ot9` moving toward green/staging through the proper review and validation path. - Keep prod watch active and reattach/restart any watcher that goes quiet. - Keep the deeper collab pathology lane moving toward source certainty, not just containment. - Keep the malformed-JSON `/ops` lane advancing in parallel. On every heartbeat, report back briefly with: - each active lane - current owner - whether it is progressing / stalled / blocked - the next action being taken - any reprioritization you made - any new lane you started Then continue execution immediately.

@rohanvarma When using opus for UI or for planning, like to be working in terminals instead of the apps instead of switching back and forth between Codex and Claude. I have heard of conductor but haven’t tried it yet. Prefer Codex for implementation/review but prefer opus for planning/ui.

Some interesting data we pulled today showed that ~40% of Codex users use multiple surfaces, between the App, CLI, and IDE extensions. Everyone seems to have a primary preference, but a bigger-than-expected chunk of users launch codex agents outside of their primary interface. If you use multiple surfaces, I'm curious why? And what could we do to improve the experience?

@ajambrosino Way too much going on

here's an early look at the codex app sidebar I wanted to ship. i was silenced

@OpenAIDevs Is mini faster than spark?

We’re introducing GPT-5.4 mini and nano, our most capable small models yet. GPT-5.4 mini is more than 2x faster than GPT-5 mini. Optimized for coding, computer use, multimodal understanding, and subagents. For lighter-weight tasks, GPT-5.4 nano is our smallest and cheapest version of GPT-5.4. openai.com/index/introduc…

Huge update!

@ryancarson Performance regression watch is well thought through

Trying out some new Automations in Codex

@LLMJunky Looking forward to using this

This is so cool. In the next Codex update, multi agents will get a massive flexibility upgrade. "Hey Codex, when you implement this plan, I want you to delegate all the lower complexity tasks to GPT 5.3 Spark subagents" Instead of needing to create 100 different custom agent roles for different situations, you can just prompt your agent to spawn whatever model or reasoning level you want. With only natural language. No config files. No pre-defined roles. Just tell the orchestrator what to use and it listens.

.@sama codex has been phenomenal for me, especially the 5.4 fast mode but the plan mode doesn’t seem on par with other models. Leaning towards having to make my own reviewal workflow for the time being.. will plan mode be improved in the future?

The speed of Claude Code feature deployments is incredible

@OpenAIDevs Great insights, looking forward to implementing in our workflows.

We use skills to maintain our Agents SDK repositories through repeatable workflows for verification, integration tests, release checks, and PR handoff. Here’s how it works: developers.openai.com/blog/skills-ag…

@ajambrosino C^6

introducing the Codex Copilot Cowork Collaborative Connector Collection

@ajambrosino Keep pressing it, thank you!

there’s long been a big random button in the office and I was never quite sure what it did

Built functionality to have codex/claude auto-route ssh sessions to my mini from my air. Wondering if this more efficient vs configuring ssh through the apps themselves.

@projectatlasmvc 👈🏼👈🏼

Who are cool people I should follow in Toronto and Montreal?

Models are getting so clever, it's almost scary.