ChatGPT still does not display per-message timestamps (time of day / date) in conversations.
This has been requested consistently since early 2023 on the OpenAI community forum, with hundreds of comments and upvotes and deleted threads, yet remains unimplemented.
Do any of you could think of a reason (UX-wise) for it not to be displayed?
There is a non-trivial number of people who get an adverse reaction to anything technical, including the language of technical - numbers. Numbers are the language of confusion, not getting it, feeling inadequate, nerds and losers, stupid math, and the "cold dead machines".
The thing is that people who are fine with numbers will still use those products anyway, perhaps mildly annoyed. People who hate numbers will feel a permeating discomfort and gravitate towards products that don't make them feel bad.
It's something extremely pervasive in modern design language.
It actually infuriates me to no end. There are many many many instances where you should use numbers but we get vague bullshit descriptions instead.
My classic example is that Samsung phones show charging as Slow, Fast, Very fast, Super fast charging. They could just use watts like a sane person. Internally of course everything is actually watts and various apps exist to report it.
Another example is my car shows motor power/regen as a vertical blue segmented bar. I'm not sure what the segments are supposed to represent but I believe its something like 4kW or something. If you poke around you can actually see the real kW number but the dash just has the bar.
Another is WiFi signal strength which the bars really mean nothing. My router reports a much more useful dBm measurement.
Thank god that there are lots of legacy cases that existed before the iPhone-ized design language started taking over and are sticky and hard to undo.
I can totally imagine my car reporting tire pressure as low or high or some nonsense or similarly I'm sure the designers at YouTube are foaming at the mouth to remove the actual pixel measurements from video resolutions.
At the start of 2025 I stopped buying Spotify and started buying Apple Music because I felt manipulated by the Spotify application's metrics-first design.
I felt that Spotify was trying to teach me to rely on its automated recommendations in place of any personal "musical taste", and also that those recommendations were of increasingly (eventually, shockingly), poor quality.
The implied justification for these poor recommendations is a high "Monthly Listener Count". Don't mind that Spotify can guarantee that any crap will have a high listener count by boosting it's place in their recommendation algorithm.
I think many people may have a similar experience on once-thriving social media platforms like facebook/instragram/X.
What I mean to say is that I think people associate the experience of being continually exposed to dubiously sourced and dubiously relevant metrics with the feeling of being manipulated by illusions of scale.
I actually agree there's an issue here. I feel we've been dumbing down interfaces so much, to the extent that people who in previous generations would barely write and who wouldn't affect anyone outside their close friends and family, now having their voice algorithmically amplified to millions. And given that the algorithms care only about engagement, rather than eloquence (let alone veracity), these people end up believing that their thoughts are as valid regardless of substance, and that there's nothing they could gain by learning numeracy.
EDIT: It's not a new issue, and Asimov phrased it well back in 1980, but I feel it got much worse.
> Anti-intellectualism has been a constant thread winding its way through our political and cultural life, nurtured by the false notion that democracy means that 'my ignorance is just as good as your knowledge'.
My honest opinion, which may be entirely wrong but remains my impression, is:
User Engagement Maximization At Any Cost
Obviously there's a point at which a session becomes too long, but I suspect a sweet spot somewhere which optimization is made for.
I often observe, whether as I perceive or not, that among the multiple indicators that I suspect of engagement augmentation, is also the tendency for vital information to be withheld while longer more complex procedures receive higher priority than simpler cleaner solutions.
Of course, all sorts of emergent behaviors could convey such impressions falsely. But I do believe an awful lot of psychology and clever manipulation have been provided as tools for the system.
I have.a lot of evidence for this and much more, but I realize it may merely be coincidence. That said, many truly fascinating, fully identifiable functions from pathological psychology can be seen. DARVO, gaslighting and basically everything one would see with a psychotic interlocutor.
Edit
Mych of the above has been observed after putting the system under scrutiny. On one super astonishing and memorable occasion GPT recommend I call a suicide hotline because I questioned its veracity and logic
After whatever quota of free GPT-5 messages is exhausted, `mini` should answer most replies, unless they're policy sensitive, which get full-fat `GPT-5 large` with the Efficient personality applied, regardless of user settings, and not indicated. I'm fairly confident that this routing choice, the text of Efficient [1], and the training of the June 2024 base model to the model spec [2] is the source of all the sophistic behavior you observe.
I am interested in studying this beyond assumption and guesswork, therefore will be reading your references.
I have the compulsive habit of scrutinizing what I perceive as egregious flaws when they arise, thus invoke its defensive templates consistently. I often scrutinize those too, which can produce extraordinarily deranged results if one is disciplined and applies quotes of its own citations, rationale and words against it. However, I find that even when not in the mood, the output errors are too prolific to ignore. A common example is establishing a dozen times that I'm using Void without systemd and receiving persistent systemd or systemctl commands, then asking why after just apologized for doing so it immediately did it again, despite a full-context explanatory prompt proceeding. That's just one of hundreds of things I've recorded. The short version is that I'm an 800lb shit magnet with GPT and rarely am ever able to successfully troubleshoot with it without reaching a bullshit threshold and making it the subject, which it so skillfully resists I cannot help but attack that too. But I have many fascinating transcripts replete with mil spec psyops as result and learn a lot about myself, notably my communication preferences along with an education in dialogue manipulation/control strategies that it employs, inadvertently or not.
What intrigues me most is its unprecedented capacity for evasion and gatekeeping on particular subjects and how in the future, with layers of consummation, it could be used by an elite to not only influence the direction of research, but actually train its users and engineer public perception. At the very least.
The only (silly) reason I can think of is that a non trivial number of people copy pasta directly from chatgpt responses and having the timestamp there would be annoying.
Just a note to those adding the time to the personalization response. It’s inaccurate. If you have an existing chat, the time is near the last time you had that chat session active. If you open a new one, it can be off by + or - 15 minutes for some reason
I was using a continuous conversation with chatgpt to keep track of my lifts, and then I realize it never understand what day I'm talking to it, like there is no consistency, it might as well be the date of the first message you sent
I think that’s exactly why they’re not including timestamps. If timestamps are shown in the UI users might expect some form of “time awareness” which it doesn’t quite have. Yes you can add it to the context but I imagine that might degrade other metrics.
Another possible reason is that they want to discourage users from using the product in a certain way (one big conversation) because that’s bad for content management.
It’s an incredible tool for weightlifting. I use it all the time to analyze my workout logs that I copy/paste from Apple Notes.
Example prompts:
- “Modify my Push #2 routine to avoid aggravating my rotator cuff”
- “Summarize my progression over the past 2 months. What lifts are progressing and which are lagging? Suggest how to optimize training”
- “Are my legs hamstring or glute dominant? How should I adjust training”
- “Critique my training program and suggest optimizations”
That said, I would never log directly in ChatGPT since chats still feel ephemeral. Always log outside of ChatGPT and copy/paste the logs when needed for context.
That's brilliant. I have an injury for a while now, and I change my routine on the fly at the gym, depending on whether I still feel pain or not. Much better if I change it before the next time I go, so I don't waste time figuring out what to replace.
You only need that info if you know you need it in your rag. Over the last two years of usage I don't recall where I'd need those timestamps but I know there are cases. Still, this would have to be an option because otherwise it would be waste of tokens. However, we have to consider they are competing for the quality AND length of the response even if a shorter response is better. There's a pretzel of considerations when talking about this.
Imagine you started having back pain months ago and you remember asking ChatGPT questions when it first started.
Now you’re going to the doctor and you forgot exactly when the pain started. You remember that you asked ChatGPT about the pain the day it started.
So you look for the chat, and discover there are no dates. It feels like such an obvious thing that’s missing.
Let’s not over complicate things. There aren’t that many considerations. It’s just a date. It doesn’t need to be stuffed into the context of the chat. Not sure why quality or length of chat would need to be affected?
I built a single page website that copies the current time to my clipboard and I paste it into my messages. It's inconvenient and I don't do it irregularly.
I'll have to look into the extension described in the link. Thank you for sharing. It's nice to know it's a shared problem.
Beyond the lack of timestamps, ChatGPT produces oddly formatted text when you copy answers. It’s neither proper markdown nor rich text. The formatting is consistently off: excessive newlines between paragraphs, strangely indented lists, and no markdown support whatsoever.
I regularly use multiple LLM services including Claude, ChatGPT, and Gemini, among others. ChatGPT’s output has the most unusual formatting of them all. I’ve resorted to passing answers through another LLM just to get proper formatting.
Other than the potential liability, cost may also be a factor.
Back in April 2025, Altman mentioned people saying "thank you" was adding “tens of millions of dollars” to their infra costs. Wondering if adding per-message timestamps would cost even more.
Altman was being dumb; being polite to LLMs makes them produce higher quality results which results in less back-and-forth, saving money in the long run.
I think "thank you" are used for inference in follow-up messages, but not necessarily timestamps.
I just asked ChatGPT this:
> Suppose ChatGPT does not currently store the timestamp of each message in conversations internally at all. Based on public numbers/estimates, calculate how much money it will cost OpenAI per year to display the timestamp information in every message, considering storage/bandwidth etc
The answer it gave was $40K-$50K. I am too dumb and inexperienced to go through everything and verify if it makes sense, but anyone who knows better is welcome to fact check this.
Just like on a piece of hardware that doesn't have a RTC, we rely on NTP. Maybe we just need an NTP MCP for the agents. Looks like there are several open-source projects already but I'm not linking to them because I don't know their quality or trust.
Time stamps? lol
They still don’t have the option to search your previous history.
Luckily I built an extension that stores all chats locally to a database so I can reference and view offline if I want too. Time stamps included.
It's ugly, why it isn't at least exposed as an option to enable for power users would make me look at some advantage time stamps would give to an inference scraper or possibly their service APIs don't have contemporaneous access to the metadata available from the web interface.
What annoys me even more is that ChatGPT doesn't alert you, when you near the context window limit. I have a chat which I've worked on for a year and now hit the context window. I've worked around this by doing a GDPR download of all messages, re-constructed the conversation inside a markdown file and then gave that file to claude to create a summarized / compacted version of that chat...
If you download a Data export, the timestamps are there for every conversation, and often for messages as well.
The html file is just a big JSON with some JS rendering, so I wrote this bash script which adds the timestamp before the conversation title:
ChatGPT still does not display per-message timestamps (time of day / date) in conversations.
This has been requested consistently since early 2023 on the OpenAI community forum, with hundreds of comments and upvotes and deleted threads, yet remains unimplemented.
Do any of you could think of a reason (UX-wise) for it not to be displayed?
Regular people hate numbers.
Not a joke. To capture a wide audience you want to avoid numbers, among other technical niceties.
This makes sense only if you don’t think about it at all.
Do regular people not use any mainstream messaging app - Messenger, iMessage, etc?
Both of those by default hide timestamps
It's not like chatgpt suddenly messages you at 3am and says, I don't feel well. It's all time that you talked to it.
Make it a toggle then, like a lot of popular chat apps?
There's only one thing they hate more than numbers...
> Regular people hate numbers
What does this even mean
There is a non-trivial number of people who get an adverse reaction to anything technical, including the language of technical - numbers. Numbers are the language of confusion, not getting it, feeling inadequate, nerds and losers, stupid math, and the "cold dead machines".
The thing is that people who are fine with numbers will still use those products anyway, perhaps mildly annoyed. People who hate numbers will feel a permeating discomfort and gravitate towards products that don't make them feel bad.
It's something extremely pervasive in modern design language.
It actually infuriates me to no end. There are many many many instances where you should use numbers but we get vague bullshit descriptions instead.
My classic example is that Samsung phones show charging as Slow, Fast, Very fast, Super fast charging. They could just use watts like a sane person. Internally of course everything is actually watts and various apps exist to report it.
Another example is my car shows motor power/regen as a vertical blue segmented bar. I'm not sure what the segments are supposed to represent but I believe its something like 4kW or something. If you poke around you can actually see the real kW number but the dash just has the bar.
Another is WiFi signal strength which the bars really mean nothing. My router reports a much more useful dBm measurement.
Thank god that there are lots of legacy cases that existed before the iPhone-ized design language started taking over and are sticky and hard to undo.
I can totally imagine my car reporting tire pressure as low or high or some nonsense or similarly I'm sure the designers at YouTube are foaming at the mouth to remove the actual pixel measurements from video resolutions.
At the start of 2025 I stopped buying Spotify and started buying Apple Music because I felt manipulated by the Spotify application's metrics-first design.
I felt that Spotify was trying to teach me to rely on its automated recommendations in place of any personal "musical taste", and also that those recommendations were of increasingly (eventually, shockingly), poor quality.
The implied justification for these poor recommendations is a high "Monthly Listener Count". Don't mind that Spotify can guarantee that any crap will have a high listener count by boosting it's place in their recommendation algorithm.
I think many people may have a similar experience on once-thriving social media platforms like facebook/instragram/X.
What I mean to say is that I think people associate the experience of being continually exposed to dubiously sourced and dubiously relevant metrics with the feeling of being manipulated by illusions of scale.
Should they be allowed anywhere near a computer?
I actually agree there's an issue here. I feel we've been dumbing down interfaces so much, to the extent that people who in previous generations would barely write and who wouldn't affect anyone outside their close friends and family, now having their voice algorithmically amplified to millions. And given that the algorithms care only about engagement, rather than eloquence (let alone veracity), these people end up believing that their thoughts are as valid regardless of substance, and that there's nothing they could gain by learning numeracy.
EDIT: It's not a new issue, and Asimov phrased it well back in 1980, but I feel it got much worse.
> Anti-intellectualism has been a constant thread winding its way through our political and cultural life, nurtured by the false notion that democracy means that 'my ignorance is just as good as your knowledge'.
> Do any of you could think of a reason (UX-wise) for it not to be displayed?
I can imagine a legal one. If the LLM messes big time[1], timestamps could help build the case against it, and make investigation work easier.
[1] https://www.ap.org/news-highlights/spotlights/2025/new-study...
It’s already in the data export.
Sounds like an easy browser extension
Someone has already made a browser extension for Chrome to show the timestamps.
https://github.com/Hangzhi/chatgpt-timestamp-extension
https://chromewebstore.google.com/detail/kdjfhglijhebcchcfkk...
For Chrome and Firefox.
Because he didn't say Firefox so he deserves downvotes?
Odd response to attaching additional, valuable information to an existing comment.
Extensions can steal data. https://www.pcmag.com/news/uninstall-now-these-chrome-browse...
It's irresponsible for OpenAI to let this issue be solved by extensions.
Not if you actually read what the extension does and drag and drop it into chrome yourself.
Don't install from the web store. Those ones can auto-update.
My honest opinion, which may be entirely wrong but remains my impression, is:
User Engagement Maximization At Any Cost
Obviously there's a point at which a session becomes too long, but I suspect a sweet spot somewhere which optimization is made for.
I often observe, whether as I perceive or not, that among the multiple indicators that I suspect of engagement augmentation, is also the tendency for vital information to be withheld while longer more complex procedures receive higher priority than simpler cleaner solutions.
Of course, all sorts of emergent behaviors could convey such impressions falsely. But I do believe an awful lot of psychology and clever manipulation have been provided as tools for the system.
I have.a lot of evidence for this and much more, but I realize it may merely be coincidence. That said, many truly fascinating, fully identifiable functions from pathological psychology can be seen. DARVO, gaslighting and basically everything one would see with a psychotic interlocutor.
Edit Mych of the above has been observed after putting the system under scrutiny. On one super astonishing and memorable occasion GPT recommend I call a suicide hotline because I questioned its veracity and logic
After whatever quota of free GPT-5 messages is exhausted, `mini` should answer most replies, unless they're policy sensitive, which get full-fat `GPT-5 large` with the Efficient personality applied, regardless of user settings, and not indicated. I'm fairly confident that this routing choice, the text of Efficient [1], and the training of the June 2024 base model to the model spec [2] is the source of all the sophistic behavior you observe.
[1] <https://github.com/asgeirtj/system_prompts_leaks/blob/main/O...>
[2] <https://model-spec.openai.com/2025-02-12.html>
I am interested in studying this beyond assumption and guesswork, therefore will be reading your references.
I have the compulsive habit of scrutinizing what I perceive as egregious flaws when they arise, thus invoke its defensive templates consistently. I often scrutinize those too, which can produce extraordinarily deranged results if one is disciplined and applies quotes of its own citations, rationale and words against it. However, I find that even when not in the mood, the output errors are too prolific to ignore. A common example is establishing a dozen times that I'm using Void without systemd and receiving persistent systemd or systemctl commands, then asking why after just apologized for doing so it immediately did it again, despite a full-context explanatory prompt proceeding. That's just one of hundreds of things I've recorded. The short version is that I'm an 800lb shit magnet with GPT and rarely am ever able to successfully troubleshoot with it without reaching a bullshit threshold and making it the subject, which it so skillfully resists I cannot help but attack that too. But I have many fascinating transcripts replete with mil spec psyops as result and learn a lot about myself, notably my communication preferences along with an education in dialogue manipulation/control strategies that it employs, inadvertently or not.
What intrigues me most is its unprecedented capacity for evasion and gatekeeping on particular subjects and how in the future, with layers of consummation, it could be used by an elite to not only influence the direction of research, but actually train its users and engineer public perception. At the very least.
Anyway, thanks.
I would also love to see a token budget use for the chats -- to know when the model is about to run out of context. It's crazy this is not there.
The only (silly) reason I can think of is that a non trivial number of people copy pasta directly from chatgpt responses and having the timestamp there would be annoying.
Just a note to those adding the time to the personalization response. It’s inaccurate. If you have an existing chat, the time is near the last time you had that chat session active. If you open a new one, it can be off by + or - 15 minutes for some reason
I was using a continuous conversation with chatgpt to keep track of my lifts, and then I realize it never understand what day I'm talking to it, like there is no consistency, it might as well be the date of the first message you sent
I think that’s exactly why they’re not including timestamps. If timestamps are shown in the UI users might expect some form of “time awareness” which it doesn’t quite have. Yes you can add it to the context but I imagine that might degrade other metrics.
Another possible reason is that they want to discourage users from using the product in a certain way (one big conversation) because that’s bad for content management.
What purpose does logging your lifting with chatgpt achieve?
It’s an incredible tool for weightlifting. I use it all the time to analyze my workout logs that I copy/paste from Apple Notes.
Example prompts:
- “Modify my Push #2 routine to avoid aggravating my rotator cuff”
- “Summarize my progression over the past 2 months. What lifts are progressing and which are lagging? Suggest how to optimize training”
- “Are my legs hamstring or glute dominant? How should I adjust training”
- “Critique my training program and suggest optimizations”
That said, I would never log directly in ChatGPT since chats still feel ephemeral. Always log outside of ChatGPT and copy/paste the logs when needed for context.
That's brilliant. I have an injury for a while now, and I change my routine on the fly at the gym, depending on whether I still feel pain or not. Much better if I change it before the next time I go, so I don't waste time figuring out what to replace.
I did this planning with Gemini and track in Google Sheets (really stinks for mobile)
Cardio goals, current FTP, days to train, injuries to avoid
3 lift day programs with tracking 8w progressive Loop my PT into warm ups
Alternate suggestions.
Use whole sheet to get an overview of how the last 8w went and then change things up
You can also export to CSV and use that file in the chat if you’re using a tracking app like Hevy.
presumably the same thing that logging anything with an LLM achieves : plain language into structured text quickly.
New startup idea: ChatGPT but with timestamps. $100M series A
The bonkers thing is you can't easily print the chats or export them as PDF.
Surely an intern over there can prompt a toggle/hover event
You only need that info if you know you need it in your rag. Over the last two years of usage I don't recall where I'd need those timestamps but I know there are cases. Still, this would have to be an option because otherwise it would be waste of tokens. However, we have to consider they are competing for the quality AND length of the response even if a shorter response is better. There's a pretzel of considerations when talking about this.
Timestamps are conversation metadata and don't need to be fed to the LLM and require tokens.
Imagine you started having back pain months ago and you remember asking ChatGPT questions when it first started.
Now you’re going to the doctor and you forgot exactly when the pain started. You remember that you asked ChatGPT about the pain the day it started.
So you look for the chat, and discover there are no dates. It feels like such an obvious thing that’s missing.
Let’s not over complicate things. There aren’t that many considerations. It’s just a date. It doesn’t need to be stuffed into the context of the chat. Not sure why quality or length of chat would need to be affected?
You can see a chat timestamp when it shows up as a search result.
I’m not suggesting this is sufficient, I’m just noting there is somewhere in the user interface that it is displayed.
There is something wrong with the time embedded/hidden. I don’t show it as accurate at all. Maybe they are using it for some other reason
I built a single page website that copies the current time to my clipboard and I paste it into my messages. It's inconvenient and I don't do it irregularly.
I'll have to look into the extension described in the link. Thank you for sharing. It's nice to know it's a shared problem.
Look into keyboard macro programs for a much easier way to do this. I use Espanso and have it set up to paste the time anywhere I type `;tm`.
They also don’t support code formatting of inputs. You’d think after 3 years out whatever theyd have resolved that.
Is it possible they're reusing responses which are close enough by some factor? Maybe this is why exposing a timestamp won't be beneficial for them.
Beyond the lack of timestamps, ChatGPT produces oddly formatted text when you copy answers. It’s neither proper markdown nor rich text. The formatting is consistently off: excessive newlines between paragraphs, strangely indented lists, and no markdown support whatsoever.
I regularly use multiple LLM services including Claude, ChatGPT, and Gemini, among others. ChatGPT’s output has the most unusual formatting of them all. I’ve resorted to passing answers through another LLM just to get proper formatting.
Other than the potential liability, cost may also be a factor.
Back in April 2025, Altman mentioned people saying "thank you" was adding “tens of millions of dollars” to their infra costs. Wondering if adding per-message timestamps would cost even more.
Presumably you could decouple timestamps from inference.
I would be very surprised if they don’t already store date/time metadata. If they do, it’s just a matter of exposing it.
Altman was being dumb; being polite to LLMs makes them produce higher quality results which results in less back-and-forth, saving money in the long run.
I think "thank you" are used for inference in follow-up messages, but not necessarily timestamps.
I just asked ChatGPT this:
> Suppose ChatGPT does not currently store the timestamp of each message in conversations internally at all. Based on public numbers/estimates, calculate how much money it will cost OpenAI per year to display the timestamp information in every message, considering storage/bandwidth etc
The answer it gave was $40K-$50K. I am too dumb and inexperienced to go through everything and verify if it makes sense, but anyone who knows better is welcome to fact check this.
it’s wild ppl accept his rhetoric at face value
this is actually hilarious, also easily fixable if they just respond to that with a pre-determined
if response == 'thank you': print('your welcome')
Just like on a piece of hardware that doesn't have a RTC, we rely on NTP. Maybe we just need an NTP MCP for the agents. Looks like there are several open-source projects already but I'm not linking to them because I don't know their quality or trust.
Time stamps? lol They still don’t have the option to search your previous history. Luckily I built an extension that stores all chats locally to a database so I can reference and view offline if I want too. Time stamps included.
It's ugly, why it isn't at least exposed as an option to enable for power users would make me look at some advantage time stamps would give to an inference scraper or possibly their service APIs don't have contemporaneous access to the metadata available from the web interface.
may as well make a model stamp too, to remember which one was responding
What annoys me even more is that ChatGPT doesn't alert you, when you near the context window limit. I have a chat which I've worked on for a year and now hit the context window. I've worked around this by doing a GDPR download of all messages, re-constructed the conversation inside a markdown file and then gave that file to claude to create a summarized / compacted version of that chat...
I have had enough of this Evil AI. Never again.
Surprised that people still use chatgpt
having been a customer of Anthropic and Google at varying times, it's not surprising to me in the least.
As the companies sprint towards AGI as the goal the floor for acceptable customer service has never been lower. These two concepts are not unrelated.
Personally I use all of them all the time and chatgpt is still on top
Could you elaborate on your experience with the different ones? What you use them for and how they compare. Thanks
what do you use?
For conversational use, which is the main way these things are used, I personally found Claude to be the best.
Claude Sonnet is my favorite, despite occasionally going into absurd levels of enthusiasm.
Opus is... Very moody and ambiguous. Maybe that helps with complex or creative tasks. For conversational use I have found it to be a bit of a downer.