Scheduled tasks in ChatGPT

I tried this yesterday, asking it to create a simple daily reminder task, which it happily did. Then when the time came and went I simply got a chat that the task failed, with no explanation of <i>why</i> or <i>how</i> it failed. When I asked it why, it hallucinated that I had too many tasks. (I only had the one) So, now I don&#x27;t know why it failed or how to fix it. Which leads to two related observations:<p>1) I find it interesting that the LLM rarely seems trained to understand it&#x27;s own features, or about your account, or how the LLM works. Seems strange that it has no idea about it&#x27;s own support.<p>2) Which leads me to the Open AI support docs[0]. It seems pretty telling to me that they use old-school search and not an LLM for its own help docs, right?<p>[0] <a href="https:&#x2F;&#x2F;help.openai.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;help.openai.com&#x2F;</a>

New killer feature: cron<p>Can’t imagine why everyone doesn’t pay $200&#x2F;mo for even more features. Eventually I bet they can clean out &#x2F;tmp!

I&#x27;m trying to figure out how this would be useful with the existing feature set.<p>It seems like it would be good for summarizing daily updates against a search query. but all it would do is display them. I would probably want to connect it with some tools at minimum for it to be useful.

They&#x27;re really trying to juice the usage numbers

Important caveat:<p>&gt; ChatGPT has a limit on 10 active tasks at any time. If you reach this limit, ChatGPT will not be able to create a new task unless you pause or delete an existing active task or it completes per its scheduled time.<p>So this is pretty much useless for most real-world uses cases.

I&#x27;m surprised it took OpenAI this long to launch scheduled tasks, but as we&#x27;ve seen from our users[0], pure LLM-based responses are quite limited in utility.<p>For context: ~50% of our users use a time-triggered Loop, often with an LLM component.<p>Simple stuff I&#x27;ve used it for: baby name idea generator, reminder to pay housekeeper, pre-natal notifications, etc.<p>We&#x27;re moving away from cron-esque automations as one of our core-value props (most new users use us for spinning up APIs really quickly), but the base functionality of LLM+code+cron will still be available (and migrated!) to the next version of our product.<p>[0]<a href="https:&#x2F;&#x2F;magicloops.dev&#x2F;">https:&#x2F;&#x2F;magicloops.dev&#x2F;</a>

Surely we want to be scheduling and calling LLMs from temporalio, dagster - even cron - instead of whatever this is. Why put the LLM at the middle?

This feature is really bad (unreliable) and they don’t even make a good case for _why_ you would want to use this over literally any other reminder system. I guess it can execute an LLM to decide what to send to you at the scheduled time but its unreliability would never have me relying on it. Some use cases that might be interesting * Let me know the closing stock price for XXXXX * Compile a list of highlights from the XXXX game after it finishes But everything I can think of is just a toy, cool if it works but not ground breaking and possible with much more reliable methods. OpenAI really seems just be throwing stuff at the wall to see if it sticks then moving on and never iterating on the previous features. Dall-e is kind of a joke compared to other things (one-shot only), I trust Claude more for programming, o1 was ho-hum for my needs, desktop app still feels like a solution in search of a problem, etc.

I tried it and it failed to send me desktop notification. I did receive emails (at the wrong time). I do think it is too early to launch. 5 min test could have found out these bugs.It really hurts their brand.

This will be a lot more useful when it&#x27;s able to combine with more tools, such as in custom GPT actions, APIs, &quot;computer use&quot;, the Python interpreter, etc.

Yeah, it’s pretty bad, embarrassingly so quite honestly. Literally a single developer in a day could probably significantly improve it. I’m sure that’s coming, but why don’t they just launch these MVP features at least a quarter baked. It’s essentially unusable as is. If it could ping me on my phone And advanced voice could open or I could go do a basic task, great I’m back to using it. But essentially as it is rolled out, it’s hilariously minimal and borderline unusable.

Works on my machine. (tm)<p>But it won&#x27;t let me reschedule my task execution time or change its prompting... It will just go forever now I guess

Oddly enough, I do not have access to scheduled tasks either on the app or web interfaces and I am a paying customer.

Can I ask it to check for deals on products and make it search the web several times a day?

sounds like theyre trying to get ahead of cron job wrappers so they dont get slammed at peak times

This could be done with an API key and AWS Lambda in minutes.

OpenAI resembles the old Apple: ship the best experience. The ChatGPT app on every platform is the best in business and they are shipping polished features relatively quickly. It&#x27;s quite the contrast to Apple of today, the world&#x27;s largest company who is so inept that they are releasing Apple Intelligence, which is quite literally using ChatGPT 3.5 tech in 2025. It just shows how valuable CEO&#x27;s like Altman, Musk and Jobs are to a corporation.