# Some 'interesting' AI suggestions of late **URL:** \ **Category:** General\ **Created:** [August 25, 2022, 11:12pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847 "2022-08-25T23:12:21Z")\ **Posts on this page:** 20\ **Page:** 1
**Author:** ![headsoup](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/headsoup/32/24960_2.png) [@headsoup](https://forum.inaturalist.org/u/headsoup)\ **Post date:** [August 25, 2022, 11:12pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/1 "2022-08-25T23:12:21Z")
Didn’t want to put this in bug reports as it might just be how the AI works, but I’ve noticed recently (perhaps since the last CV model update?) some odd suggestions coming up for species ID, see as follows: ![Screenshot_ant-octopus](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/e/a/eacb48b317c6aa070eaec7589e5f28d5a6761560.png) [https://www.inaturalist.org/observations/132275664](https://www.inaturalist.org/observations/132275664) ![Screenshot_assassin-rust](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/9/f/9fbd81c64adb434354d92736aaa82a06aacd9ea0.png) [https://www.inaturalist.org/observations/132276378](https://www.inaturalist.org/observations/132276378) ![Screenshot_bird-centipede](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/d/9/d9b9eccb515200f2ae5e37f31fc6cbf5939137bb.png) [https://www.inaturalist.org/observations/132275645](https://www.inaturalist.org/observations/132275645) Anyone else seeing this (e.g. octopus, centipede, rust seem a bit off, the octopus in particular considering location is well inland…)? It’s on the desktop web iNat when uploading. ---
**Author:** ![tiwane](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/tiwane/32/54612_2.png) [@tiwane](https://forum.inaturalist.org/u/tiwane)\ **Post date:** [August 25, 2022, 11:15pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/2 "2022-08-25T23:15:54Z")
Can you please include locations and dates for these? Those used to determine “seen nearby”. ---
**Author:** ![headsoup](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/headsoup/32/24960_2.png) [@headsoup](https://forum.inaturalist.org/u/headsoup)\ **Post date:** [August 25, 2022, 11:17pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/3 "2022-08-25T23:17:49Z")
Sorry about that, I’ve added links to the actual observations. The process I go through is: Upload button → Choose files → group select within a folder (all same date) → Select All → add location → individually select ID’s. So all of these should have location set when I select for species ID. ---
**Author:** ![pfau\_tarleton](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/pfau_tarleton/32/346_2.png) [@pfau\_tarleton](https://forum.inaturalist.org/u/pfau_tarleton)\ **Post date:** [August 26, 2022, 12:29am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/4 "2022-08-26T00:29:43Z")
My attempt resulted in the suggestion that the Australian heteropteran was a brightly colored South American bird! And that the ant might be a North American fern…even though there’s not a speck of green in the ant image. It does seem a bit suboptimum! ![image](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/0/b/0beea93baa4e73689c4968176986b7e4c4c8926a.jpeg) ---
**Author:** ![arnim](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/arnim/32/5996_2.png) [@arnim](https://forum.inaturalist.org/u/arnim)\ **Post date:** [August 26, 2022, 12:52am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/5 "2022-08-26T00:52:08Z")
It isn’t very safe to assume the AI has any anthropomorphic perspectives at all. We have a long way to ge before AI can rationalise a decision in human terms. ---
**Author:** ![pfau\_tarleton](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/pfau_tarleton/32/346_2.png) [@pfau\_tarleton](https://forum.inaturalist.org/u/pfau_tarleton)\ **Post date:** [August 26, 2022, 1:01am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/6 "2022-08-26T01:01:31Z")
> [@arnim](#): > > It isn’t very safe to assume the AI has any anthropomorphic perspectives at all Of course–it’s not a human brain. But I don’t think we were making that assumption. I’ve used it for years, and have never seen it suggest something so far astray (my experience from my location). ---
**Author:** ![headsoup](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/headsoup/32/24960_2.png) [@headsoup](https://forum.inaturalist.org/u/headsoup)\ **Post date:** [August 26, 2022, 1:20am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/7 "2022-08-26T01:20:37Z")
Yeah that’s my observation (ha), it’s never been spot on and I wouldn’t expect it to be, but I don’t remember it previously being so far off as to guess an octopus for an ant (especially where it’s a reasonably quality image)… ---
**Author:** ![sedgequeen](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/sedgequeen/32/1928_2.png) [@sedgequeen](https://forum.inaturalist.org/u/sedgequeen)\ **Post date:** [August 26, 2022, 2:38am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/8 "2022-08-26T02:38:41Z")
Those are interesting errors! ---
**Author:** ![tiwane](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/tiwane/32/54612_2.png) [@tiwane](https://forum.inaturalist.org/u/tiwane)\ **Post date:** [August 26, 2022, 5:09am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/9 "2022-08-26T05:09:54Z")
I downloaded the first ant photo, the put it in the uploader and gave it the same location and date of the observation. ![image](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/4/7/470812db5a365ac72436a5bdbdf008f167a18c2c.png) ![image](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/d/f/df6d64e000259ec90647a992a8cd388118c8577e.png) I got what look to be good suggestions (Caveat: I’m not familiar with Australian insects): ![image](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/7/b/7b54e57bb6a2817d8a08f266b447cc1bc6a6b325.jpeg) * * * Same process for the bird photo and I got the right suggestion: ![image](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/9/d/9d9268ec7cd5531de41f27cff95362362617412f.jpeg) Do you have the “only nearby suggestions” filter turned on? * * * I’m not a developer, but the screenshots in the original post make me think it’s less of a problem with the _model_ than with the pipeline to the model. Like the right info for that observation is not being sent to the model or somehting. But that’s just a guess. ---
**Author:** ![txwoofus](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/txwoofus/32/33357_2.png) [@txwoofus](https://forum.inaturalist.org/u/txwoofus)\ **Post date:** [August 26, 2022, 5:31am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/10 "2022-08-26T05:31:25Z")
Not exactly “of late,” but the most hilariously wrong suggestions I saw was when I uploaded a photo of some [local cattle](https://www.inaturalist.org/observations/109321133) to the website, and CV suggested: apricot, donkey, and rock pigeon. At least a donkey is a four-legged farm animal. As I mentioned in the observation notes, the Seek app was able to make a correct ID (from the phone’s Camera Roll, not in-person), but somehow the website wasn’t. Anyway, I checked just now, and it appears to have been fixed since then. ---
**Author:** ![DianaStuder](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/dianastuder/32/43358_2.png) [@DianaStuder](https://forum.inaturalist.org/u/DianaStuder)\ **Post date:** [August 26, 2022, 11:31am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/11 "2022-08-26T11:31:57Z")
Yesterday I had a faded daisy, grey and pointed. CV also suggested snapping turtle … and I can see the pixels for the pointy grey shape are in both pictures. Again, I would like an option to downvote so we could add human input to the next CV. ---
**Author:** ![pfau\_tarleton](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/pfau_tarleton/32/346_2.png) [@pfau\_tarleton](https://forum.inaturalist.org/u/pfau_tarleton)\ **Post date:** [August 26, 2022, 11:48am UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/12 "2022-08-26T11:48:50Z")
> [@tiwane](#): > > Do you have the “only nearby suggestions” filter turned on? How do you turn this on and off? ---
**Author:** ![DianaStuder](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/dianastuder/32/43358_2.png) [@DianaStuder](https://forum.inaturalist.org/u/DianaStuder)\ **Post date:** [August 26, 2022, 1:43pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/13 "2022-08-26T13:43:10Z")
you can see the toggle on tiwane’s screenshot for the bird photo. At the bottom of the suggestions list. ---
**Author:** ![headsoup](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/headsoup/32/24960_2.png) [@headsoup](https://forum.inaturalist.org/u/headsoup)\ **Post date:** [August 26, 2022, 3:41pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/14 "2022-08-26T15:41:58Z")
I have a feeling it’s something like that too, perhaps the metadata (or higher res image version) being uploaded has not yet replicated to the DB being used for CV guess? I think I’ve also seen the recommendations change around a bit going back and forth to certain observations while uploading too. @tiwane I do have it defaulted to only nearby (i.e. can see "Include suggestions not seen nearby). Also, going back to these observations, if I check suggestions now they seem ok (no octopuses!). ---
**Author:** ![graysquirrel](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/graysquirrel/32/127_2.png) [@graysquirrel](https://forum.inaturalist.org/u/graysquirrel)\ **Post date:** [August 26, 2022, 9:05pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/15 "2022-08-26T21:05:27Z")
I noticed something along the same lines when uploading observations for Gunnera tinctoria, which is a pretty distinctive plant. (For context, there are at least 10 observations of this species at pretty much exactly these coordinates, going back at least 2 years, and several are RG) This is the first observation I uploaded: [https://www.inaturalist.org/observations/132455150](https://www.inaturalist.org/observations/132455150). The initial suggestions get the genus right, but then suggest some plants bear very little resemblance: ![Capture2](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/8/f/8fe94149a081f53ef6d0c72b98d1143e31686c32.jpeg) However, when I do “Include suggestions not seen nearby” it immediately offers the correct species as the top suggestion: ![Capture](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/b/2/b25065372440a115764feecd36a3c95705bba0fe.jpeg) Same story with the second observation: [https://www.inaturalist.org/observations/132455153](https://www.inaturalist.org/observations/132455153) When limited to “seen nearby” it gets wildly wrong suggestions, when expanded to all, it offers better suggestions. ![Capture3](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/7/9/790ef01820d0e779ca2bfb814f5c71bf74ae5da9.jpeg) ![Capture4](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/d/6/d6a759d3ddb45531c3f0c9f76d721056fc27be5e.jpeg) ---
**Author:** ![pfau\_tarleton](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/pfau_tarleton/32/346_2.png) [@pfau\_tarleton](https://forum.inaturalist.org/u/pfau_tarleton)\ **Post date:** [August 26, 2022, 9:35pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/16 "2022-08-26T21:35:04Z")
> [@DianaStuder](#): > > you can see the toggle on tiwane’s screenshot for the bird photo. > At the bottom of the suggestions list. That’s in the upload modal. I’m using the Compare button in the Identify modal. Does that option available exist only in the upload modal? ---
**Author:** ![tiwane](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/tiwane/32/54612_2.png) [@tiwane](https://forum.inaturalist.org/u/tiwane)\ **Post date:** [August 26, 2022, 9:52pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/17 "2022-08-26T21:52:16Z")
I talked to @alex about these and I was incorrect, this is working as designed right now. @graysquirrel’s examples sum it up pretty well. The actual visual model seems to be working fine, but if you have “Seen nearby only” selected and the top visual match hasn’t been seen nearby, it won’t show that match in “Here are our top suggestions” section. The “We’re pretty sure this is…” section is purely based on visual similarity. _Gunnera tinctoria_ has been seen nearby _spatially_, but not _temporally_ (eg in July, August, and September). So sea kale, opium poppy, etc, are the closest visually similar matches that have been seen nearby in both the spatial and temporal sense. More on seen nearby here: [https://www.inaturalist.org/pages/help#cv-seen-nearby](https://www.inaturalist.org/pages/help#cv-seen-nearby) When you remove the “Seen nearby only” filter, then the model shows you _Gunnera tinctoria_ as the top visually similar result. This is why we have the “Include suggestions not seen nearby” option, to make up for these kind of holes in the observation data used for seen nearby. As Alex mentioned in his vision model blog post, we’re working on a better way to use geospatial info for suggestions, but this is how it currently works. When/if @graysquirrel’s observations get to RG and we update the seen nearby data, these observations will fill in some of those temporal gaps. ---
**Author:** ![pfau\_tarleton](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/pfau_tarleton/32/346_2.png) [@pfau\_tarleton](https://forum.inaturalist.org/u/pfau_tarleton)\ **Post date:** [August 26, 2022, 9:57pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/18 "2022-08-26T21:57:38Z")
> [@tiwane](#): > > When you remove the “Seen nearby only” filter Is this option available in the Identify Modal, or only in the Upload Modal? Is this the default (or only option) for the Identify Modal also? " By default, the iNaturalist only displays suggested taxa that are visually similar _and_ have been seen nearby if visually similar taxa have been seen nearby." ---
**Author:** ![tiwane](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/tiwane/32/54612_2.png) [@tiwane](https://forum.inaturalist.org/u/tiwane)\ **Post date:** [August 26, 2022, 10:08pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/19 "2022-08-26T22:08:00Z")
> [@pfau\_tarleton](#): > > Is this option available in the Identify Modal, or only in the Upload Modal? The upload page ID section isn’t really a modal, but yes, the option is available there and on individual observation pages, eg ![image](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/c/5/c597ca00697625015af9c5e99709687f60a594aa.jpeg) For Compare/Identify you can filter by taxon and then you see a list of suggestions labeled visually similar or visually similar/seen nearby. But there isn’t a way to remove taxa not seen nearby. ---
**Author:** ![pfau\_tarleton](https://sea2.discourse-cdn.com/flex016/user_avatar/forum.inaturalist.org/pfau_tarleton/32/346_2.png) [@pfau\_tarleton](https://forum.inaturalist.org/u/pfau_tarleton)\ **Post date:** [August 26, 2022, 10:15pm UTC](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847/20 "2022-08-26T22:15:04Z")
> [@tiwane](#): > > the option is available there and on individual observation pages I’m not seeing that option on my end for _some_ observations (below), but I do see it for other observations. ![image](https://us1.discourse-cdn.com/flex016/uploads/inaturalist/original/3X/b/1/b1be65a0abcb60e90b32cb0d9e78f1d3812d700f.png) [Next page](https://forum.inaturalist.org/t/some-interesting-ai-suggestions-of-late/34847.md?page=2)