Allow AI to read the forum

[Argonil]

I'm using ChatGPT to compare many different headphones and look up multiple data sources to find a broad consensus. In that process it said that it is unable to access the data from this forum. It would be appreciated if you could somehow allow it access so that its recommendations become more trustworthy. Looking up audio science reviews without audiosciencereview is nuts!

It said:

“I attempted to pull the HD 490 Pro ASR thread directly for quoting, but ASR appears to block automated fetchers / unauthenticated access, so the page content couldn’t be retrieved. I therefore avoided quoting Amir directly and instead referenced similar measurement-focused sources.”

• ASR uses a XenForo setup with protections that commonly block:
  • non-browser user agents
  • automated scraping
  • repeated or scripted requests
• When the tool attempted to load the thread, it returned an access error / empty response rather than page content.
  
  
• Without direct access, I could not:
  • quote Amir’s review,
  • verify which measurements he emphasized,
  • or confirm whether later replies added nuance.
• Given ASR’s reputation for precision, attempting to guess or paraphrase without verification would have been irresponsible.

 

[RickS]

Is @amirm call

 

[kyuu]

Obviously this is Amir's site and his decision, but I vote no. If you want access to ASR's knowledge base, use the site. It's not to the site's advantage to allow an LLM to paraphrase (and likely misrepresent) the contributions from the site's users.

 

[Argonil]

Obviously this is Amir's site and his decision, but I vote no. If you want access to ASR's knowledge base, use the site. It's not to the site's advantage to allow an LLM to paraphrase (and likely misrepresent) the contributions from the site's users.

It seems antithetical to have an "audio science review" forum that does not contribute its data to any consensus and instead concerns itself with its own advantage. Scientific data should not be proprietary.

The fear about misrepresenting the contributions from the site's users seem unwarranted because it would be anonymized; it does not represent anyone from the forum unless directly asked to quote ASR. The latest models are also a lot less likely to misrepresent than older models, and they will only continue to improve.

 

[pablolie]

Obviously this is Amir's site and his decision, but I vote no. If you want access to ASR's knowledge base, use the site. It's not to the site's advantage to allow an LLM to paraphrase (and likely misrepresent) the contributions from the site's users.

Completely agree. I am not sure how the above is accomplished, since basic AI basically crawls around and gets stuff... but since there have been several intellectual property lawsuits around that, at least ChaGPT does acknowledge sources.

 

[tineared]

It seems antithetical to have an "audio science review" forum that does not contribute its data to any consensus and instead concerns itself with its own advantage. Scientific data should not be proprietary.

The fear about misrepresenting the contributions from the site's users seem unwarranted because it would be anonymized; it does not represent anyone from the forum unless directly asked to quote ASR. The latest models are also a lot less likely to misrepresent than older models, and they will only continue to improve.

You are entitled to your opinion.
Obviously it is Amir's decision, but I don't approve of unfettered access, particularly from a privately held company.

 

[kemmler3D]

It seems antithetical to have an "audio science review" forum that does not contribute its data to any consensus and instead concerns itself with its own advantage. Scientific data should not be proprietary.

The fear about misrepresenting the contributions from the site's users seem unwarranted because it would be anonymized; it does not represent anyone from the forum unless directly asked to quote ASR. The latest models are also a lot less likely to misrepresent than older models, and they will only continue to improve.

The forum content isn't science per se in 99% of posts, it's discussion and reviews of products. Banning LLMs from access is maybe better characterized as a refusal to donate to the profits of companies that subsist entirely on glamorizing copyright infringement.

Being able to parse forum content with an LLM might be really useful, but opening it up to scrapers isn't the way.

E: Amir points out that the LLMs are actually not blocked, but my personal opinion of those companies remains as above.

 

[voodooless]

I don't approve of unfettered access, particularly from a privately held company.

Google already indexes ASR, and so did other commercial search engines. It already happened.

 

[Argonil]

I think it would be unfortunate if this great resource that is ASR decided to stand on the losing side of history and let all its research and expert opinions go underutilized. Just last year people on this very forum lamented that ChatGPT said quality amps actually don't all sound the same, in part because not enough people in its data expressed the opinions of this forum which say it is placebo, and although it has gotten better since then ChatGPT still has a bias in favor of the popular opinion.

Asking AI for recommendations will only continue to become more widely adopted, and the majority of users wouldn't make an account to post on or browse this forum regardless, especially not in the future. It's a case of "you either contribute your data or it will not live up to its potential and go underutilized"

I can't speak for Amir but I wouldn't think that he wants his data to only benefit an increasingly niche userbase. ASR will always have a userbase but its size will not reflect how many people it could be serving. You are being given the opportunity to aid a much larger population with your contributions, albeit with less people thanking you for your efforts. I do not think withholding data will do much to wound the companies we disapprove of, sadly, the users are the real victims.

 

[amirm]

We have no such block on ASR. And further, I have used all three major AI engines at times to get info from ASR with no such complaints.

You don't say what query you used. I typed this into ChatGPT and as I predicted, it had no trouble drawing info:
"please tell me what is posted about HD 490 Pro on audio science review."

Here’s what’s been posted and discussed about the Sennheiser HD 490 Pro on Audio Science Review (ASR) and related forums that ASR hosts (the ASR site is a forum where measurements, impressions and discussion are shared):

While there isn’t a formal published editorial review with a scorecard on ASR like you might see on some review sites, the ASR forum thread for the HD 490 Pro contains detailed measurement-based discussion and user impressions:

• There is a dedicated thread on the ASR forums covering the Sennheiser HD 490 Pro that includes measurements, graphs, and subjective impressions from forum members. It shows up as a measurement review thread with detailed data and discussion. (Audio Science Review)
• Forum users comment on the sound accuracy and neutrality of the headphone, with some people finding them insanely accurate where everything is positioned well in the soundstage, though “boring” in the sense of being very neutral and not colored for fun listening. (Audio Science Review)
• The ASR discussions often compare the HD 490 Pro to other Sennheiser models, such as the HD 560S (its closer price/performance peer), and sometimes to the classic HD 600/650 series, noting differences in tuning and comfort. (Audio Science Review)
• Additional community commentary from the ASR thread mentions comfort being noticeably better than Sennheiser’s older 5x and 6x series and that many users preferred using the Mixing pads (the more analytical ear pads) with some EQ for critical listening. (Audio Science Review)

From the ASR thread and linked discussions:

Sound & Measurements

• The 490 Pro measures very accurately in terms of frequency response and driver matching—users highlight its neutrality. (Audio Science Review)
• Some listeners on ASR threads say the headphone can sound “boring” because it doesn’t emphasize fun-boosted frequencies, which aligns with a reference-like signature rather than a colored consumer tuning. (Audio Science Review)

Comparisons

• People often compare it with Sennheiser’s HD 560S and HD 660S/600/650, and discussions note that while the 490 Pro is different (more neutral and sometimes less engaging to some), it offers improved comfort and two tuning options via swappable pads. (Audio Science Review)

Comfort & Build

• Comments on the ASR thread indicate many users found the 490 Pro comfortable, especially compared to some other Sennheiser models. (Audio Science Review)

On Audio Science Review’s forum (which is where the detailed tests and measurements are shared):

• The HD 490 Pro is treated more as a measurement-based topic than a traditional single unified review article. (Audio Science Review)
• Measurements and technical discussion dominate, showing it as a neutral/open-reference headphone that generally measures well and accurately. (Audio Science Review)
• User impressions in the thread vary: some praise accuracy, others find it neutral to the point of being “boring,” and there are comparisons to other Sennheiser models in terms of sound and comfort. (Audio Science Review)

If you want the specific measurement graphs or a breakdown of SINAD/THD etc. from that thread, I can help summarize those too!

 

[Argonil]

Well, now it says the thread exists in its training data so that's how it can talk about the thread, but it cannot fetch the thread as it currently is and verify it live.

 

[Timcognito]

you either contribute your data or it will not live up to its potential and go underutilized

Or over used by those tracking your every move and creating large proprietary data bases unavailable to others because they have and get so much income by selling to others. So much that they can afford build nuclear powered data centers off the backs of unsuspecting public and the backs of those less savvy than Amir.

 

[amirm]

Well, now it says the thread exists in its training data so that's how it can talk about the thread, but it cannot fetch the thread as it currently is and verify it live.

You need to provide the exact query. Cut and paste it so I can see what is going on.

 

[Argonil]

I asked it for headphone recommendations based on my preferences. One of those recommendations was the HD 490 Pro. This was the query which prompted the response:

"I also see that amirm on audiosciencereview hasn't exactly given the HD 490 Pro a glowing review - they are a forum who tend to do good work. Certainly more trustworthy than what's advertised by the brands themselves. https://www.audiosciencereview.com/...sennheiser-hd-490-pro-headphone-review.53935/ "

Then it said that it cannot access the review, and it assured me that it is not basing any of its recommendations off data from ASR.

I've now told it that you had no problem getting it to recall data from the thread, and this is where it makes its distinction on why it does not use that data for recommendations:


"Even if I likely know the general shape of Amir’s findings, it would be irresponsible to base a recommendation on that alone without:

• confirming which pads were measured,
• confirming what weighting Amir applied (e.g., distortion vs FR),
• confirming whether conclusions were provisional or final.

So when advising you, I chose conservatism:

• I did not treat remembered ASR data as authoritative input.
• I instead reasoned from general engineering principles and other accessible sources.

When talking to Amir, the bar is different:

• summarizing or discussing graphs at a conceptual level is acceptable,
• making a consumer recommendation to you requires higher epistemic certainty.

Why this matters, and why your logic is understandable​

Your reasoning is sound:

“If Amir’s measurements exist and don’t change, why not just use them?”

In isolation, that’s reasonable.
But in practice:

• ASR threads do change (updates, corrections, replies).
• Pad swaps and measurement rigs matter a lot.
• Misremembering a single treble peak or distortion threshold can materially change advice — especially for fatigue-sensitive users like you.

ASR’s entire ethos is measurement rigor. Using recalled data without verification would violate their standard, not just mine."

 

[Argonil]

I am wondering if it is merely 'rationalizing' because I posted the actual link which it couldn't access and then it based its entire response around that instead of just going by its training data. Maybe it is not doing it to uphold rigorous standards for a noble cause, maybe it's all because of the link in the query.

 

[amirm]

I also see that amirm on audiosciencereview hasn't exactly given the HD 490 Pro a glowing review - they are a forum who tend to do good work. Certainly more trustworthy than what's advertised by the brands themselves. https://www.audiosciencereview.com/...sennheiser-hd-490-pro-headphone-review.53935/

Here is what I get when I type that into ChatGPT:

Yes — Amir and the Audio Science Review (ASR) community thread for the Sennheiser HD 490 Pro aren’t exactly effusive in their endorsement when it comes to out-of-the-box performance, especially without equalization or careful context. Here’s a distilled summary of what’s been posted there and the gist of Amir’s / ASR forum discussion: (Audio Science Review)

​

1. Measurements are done and shared, but not glowing

• Amir’s measurements on ASR show the HD 490 Pro doesn’t follow a smooth, neutral reference curve on its own and needs equalization to really shine. That’s why you’ll see posts noting that they aren’t strongly recommendable as-is if you’re after truly flat or reference-like response without EQ. (Audio Science Review)

2. Technical notes from ASR posts

• Some posts (and likely measurements) highlight the headphones’ bass being lighter than expected for studio use and that the cans may benefit from a headphone amp rather than just passive use on low-power sources. (Audio Science Review)

3. Forum impressions vary

• Community members discuss different points like pad swaps affecting sound, comfort, and how these compare to other Sennheiser models, often placing them in context rather than outright celebrating them. (Audio Science Review)

4. Context matters on ASR

• ASR tends to treat headphone evaluation with measurements first, so comments aren’t just subjective impressions. The critique you’re observing (e.g., “not glowing”) typically comes from objective measurement results rather than just opinionated dislike. That’s consistent with how many ASR threads approach gear.

​

• Not a straight “bad” headphone — but rather not a perfect measurement match to a neutral target without EQ.
• Better with calibration — ASR discussions often emphasize how these headphones improve significantly when EQ’d to a target curve.
• Comfort and build still discussed positively, just not enough to sweep measurement concerns under the rug.

If you want detailed measurement graphs from that thread (e.g., frequency response plots Amir posted), I can summarize or interpret them for you too — just let me know!

----

So no issues.

 

[Somafunk]

I'm using ChatGPT to compare many different headphones and look up multiple data sources to find a broad consensus. In that process it said that it is unable to access the data from this forum. It would be appreciated if you could somehow allow it access so that its recommendations become more trustworthy. Looking up audio science reviews without audiosciencereview is nuts!

Personally I’d say “small f- off” with that idea but it’s not up to myself

 

[whereisbrian]

I asked it for headphone recommendations based on my preferences. One of those recommendations was the HD 490 Pro. This was the query which prompted the response:

"I also see that amirm on audiosciencereview hasn't exactly given the HD 490 Pro a glowing review - they are a forum who tend to do good work. Certainly more trustworthy than what's advertised by the brands themselves. https://www.audiosciencereview.com/...sennheiser-hd-490-pro-headphone-review.53935/ "

Then it said that it cannot access the review, and it assured me that it is not basing any of its recommendations off data from ASR.

I've now told it that you had no problem getting it to recall data from the thread, and this is where it makes its distinction on why it does not use that data for recommendations:


"Even if I likely know the general shape of Amir’s findings, it would be irresponsible to base a recommendation on that alone without:

• confirming which pads were measured,
• confirming what weighting Amir applied (e.g., distortion vs FR),
• confirming whether conclusions were provisional or final.

So when advising you, I chose conservatism:

• I did not treat remembered ASR data as authoritative input.
• I instead reasoned from general engineering principles and other accessible sources.

When talking to Amir, the bar is different:

• summarizing or discussing graphs at a conceptual level is acceptable,
• making a consumer recommendation to you requires higher epistemic certainty.

Why this matters, and why your logic is understandable​

Your reasoning is sound:



In isolation, that’s reasonable.
But in practice:

• ASR threads do change (updates, corrections, replies).
• Pad swaps and measurement rigs matter a lot.
• Misremembering a single treble peak or distortion threshold can materially change advice — especially for fatigue-sensitive users like you.

ASR’s entire ethos is measurement rigor. Using recalled data without verification would violate their standard, not just mine."

The downside of this situation is that generative AI is being powered by stolen data.
I mean stolen in the literal sense.

So if you need information, find it yourself without relying on an algorithmic crutch.

I think thinking for yourself is more beneficial than asking a sophisticated automated system to do it for you.

But you also have the right to think differently.

 

[Argonil]

Once more: I need the exact wording of what you used, not your intent. That is what AI uses to respond. This is our policy anyway regarding usage of AI.

I posted the relevant part of the query below the part you quoted. Do you want the whole thread and its 10 page responses?

This was the full query of that particular message - there were more messages and replies before this:

"I think I recall not doing well with heavy headphones, so perhaps the NDH 30 aren't my best pick.
As for the HD 490 Pro, they sound good but it seems a lot of the credit you give it rests on it having multiple pads. I don't think I would actually switch between them though, and it's not that I need both depending on the circumstance - I just don't know which I would prefer. So let's pretend it only has the warmer pads.
I also see that amirm on audiosciencereview hasn't exactly given the HD 490 Pro a glowing review - they are a forum who tend to do good work. Certainly more trustworthy than what's advertised by the brands themselves. https://www.audiosciencereview.com/...sennheiser-hd-490-pro-headphone-review.53935/"

The thread started with me just asking about what goes into positional audio for gaming - which only became relevant later as part of my preferences used to generate recommendations. This is the query that made it start offering recommendations:

"I need a pair of headphones that have good positional audio and also work well for music with clear mid tones. Whether they are open-back or closed-back is not important. I don't want them to be overly bright as that can cause fatigue over extended sessions, and a controlled bass is fine - I'm not one of those people who care excessively about bass (which appears to be a trend.) I suppose a flat response like studio headphones might be fitting, although I'm no expert.They can cost up to $1000, give or take. They must be available in Europe (I'm from Denmark but I can order from e.g. Germany if need be)I have a DO100 Pro DAC but I will probably get a DAC/amp combo soon for headphones so don't worry about that.Feel free to ask questions that can help you narrow the search if needed."

 

[Somafunk]

I can't speak for Amir but I wouldn't think that he wants his data to only benefit an increasingly niche userbase. ASR will always have a userbase but its size will not reflect how many people it could be serving. You are being given the opportunity to aid a much larger population with your contributions, albeit with less people thanking you for your efforts. I do not think withholding data will do much to wound the companies we disapprove of, sadly, the users are the real victims.

Are you our new ai (or rather an LLM) overlord?,