Merge pull request #765 from zackproser/add-post-codex-review

Add post codex review

Author: zackproser

src/content/blog/openai-codex-review/page.mdx

@@ -13,6 +13,8 @@ import chatThread from '@/images/chat-thread.webp'
 import launchNewEnv from '@/images/codex-launch-new-environment.webp'
 import codexFinal from '@/images/codex-final.webp'
 import poorErrorHandling from '@/images/codex-poor-error-handling.webp'
+import phone from '@/images/codex-phone.webp'
+import phoneTwo from '@/images/codex-phone-2.webp'
 
 import ConsultingCTA from '@/components/ConsultingCTA'
 
@@ -28,6 +30,8 @@ export const metadata = createMetadata({
 
 <Image src={codexHero} alt="I got hands-on with OpenAI's Codex research preview. Here's what I thought..." />
 
+<figcaption>The interface I want and the performance I'll have to wait for...</figcaption>
+
 ## Table of contents 
 
 On May 16th, 2025, I gained access to OpenAI's Codex research preview. I connected Codex to my GitHub organization and spent 
@@ -62,6 +66,17 @@ This is one of the things I like most about Codex and that I'm most excited for
 
 By the time I start work, I tend to have a laundry list of items I want to complete, so initiating a ton of them in parallel via natural language feels like a reasonable interface. 
 
+### I think this will eventually support my dream untethered workflow
+
+As I wrote about in [/blog/walking-and-talking-with-ai](Walking and talking with AI in the woods), ideally I'd like to start my morning in an office, launch a bunch of tasks, 
+get some planning out of the way, and then step out for a long walk in nature.
+
+<Image src={phone} alt="Codex is even usable on mobile" />
+
+I think, ultimately, once some of the sharp edges are polished, Codex will support me and others in performing our work effectively away from our desks.
+
+<Image src={phoneTwo} alt="Codex and similar tools will ultimately support workers who want to be effective away from their desks" />
+
 ### Follow ups via chat
 
 Once your initial task has had some time to bake, you can click into it to view its progress, see the logs and make follow-up requests via a very familiar chat interface.
@@ -114,6 +129,8 @@ That makes multi-step refactors tricky because you can't reliably iterate on the
 
 ### Lack of network connectivity in execution sandboxes 
 
+To be clear, I understand this is an intentional design choice. It mitigates remote code execution vulnerabilities amongst others.
+
 This currently blocks the use of Codex for a lot of the tasks that working developers are going to want to use it for, namely
 resolving annoying dependency issues by installing a more recent version of a package and regenerating the relevant lockfiles in the process.
 
@@ -131,6 +148,10 @@ Not yet, but I can see how it will once:
 - Codex enables more integrations with additional OpenAI platform capabilities such as generating images. 
 - Codex (potentially) becomes more of the high-level orchestration and signaling layer that humans primarily work out of
 
+At the moment, Codex is useful for flushing the low priority yet numerous and tedious maintenance tasks and small updates. 
+
+For significant refactoring or feature-building, I'm still better served doing that myself in an IDE with optional LLM support.
+
 <Image src={codexFinal} alt="I'm sure that imminent improvements will make Codex even more usable soon" />
 
 I'm confident that shortly I'll be able to use Codex as an indeal interface for starting a day of work and for keeping tabs on what needs attention and what is up next.