🎁 Free

ChatGPT-5 Still Makes Egregious Errors

OpenAI's new model is supposed to represent an improvement over its predecessor. Maybe it is, but it's nowhere near perfect.

Sep 02, 2025 4-min read

Like so many folks, I was curious about the launch of OpenAI's latest and greatest large language model.

In today's post, I'll explore how OpenAI's self-described expert-level tool performed on some simple image tweaks. Would it uncover major issues or pass with flying colors?

Let's find out.

To read the rest of this post, subscribe or sign in with your 🎁 Free account.

It'll only take a moment.

Moving From WordPress to Ghost: The Verdict Battle of the LLMs

Before You Go...
If you'd like to support my writing efforts, I'd appreciate it.

𝗧𝗜𝗣 𝗧𝗛𝗘 𝗔𝗨𝗧𝗛𝗢𝗥

➕ Plus ⭐️ Premium

AI as an English-to-English Translator

Claude helped me solve a longstanding problem.

09/10/25

Notion

🌍 Public

How I Use Notion

The popular tool serves many simple purposes. Trust me, though. You're probably missing out on some less obvious ones.

09/09/25

Communication

➕ Plus ⭐️ Premium

Citation Sloths

Quoting a stat in a post or video? Great. Respect your audience by bringing your receipts.

09/04/25

➕ Plus ⭐️ Premium

Battle of the LLMs

To answer a simple basketball question, I pitted Claude and ChatGPT-5 against each other. Let's see which tool won and what we can learn from the exercise.

09/03/25

➕ Plus ⭐️ Premium

Will AI Make Us All Line Judges?

Not that long ago, the idea of a machine making tennis calls seemed far fetched. Now, thanks to a narrow form of AI, it's the norm.

08/28/25

➕ Plus ⭐️ Premium

The Nvidia Arrow

What if we're looking at the relationship between company success and remote work wrong?

08/27/25

Filed Under

View more like this

AI as an English-to-English Translator

How I Use Notion

Citation Sloths

Battle of the LLMs

Will AI Make Us All Line Judges?

The Nvidia Arrow