{"id":292632,"date":"2025-07-26T06:46:17","date_gmt":"2025-07-26T06:46:17","guid":{"rendered":"https:\/\/www.europesays.com\/uk\/292632\/"},"modified":"2025-07-26T06:46:17","modified_gmt":"2025-07-26T06:46:17","slug":"alexa-preview-an-almost-philosophical-exercise","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/uk\/292632\/","title":{"rendered":"Alexa+ preview: An almost philosophical exercise"},"content":{"rendered":"

\u201cAlexa, I need to write a review about you.\u201d<\/strong><\/p>\n

\u201cOh, a review? I\u2019m intrigued! What\u2019s the occasion? I\u2019d love to hear what you think.\u201d<\/p>\n

\u201cThere\u2019s no occasion, this is just my work.\u201d<\/strong><\/p>\n

\u201cAh, I see. Writing a professional review, got it. I\u2019m here to help if you need any specific information.\u201d<\/p>\n

\u201cYeah, what should I consider when reviewing you?\u201d<\/strong><\/p>\n

\u201cConsider my natural voice, emotional intelligence and my ability to handle complex tasks. How about my personality and humor? Those are key parts of the new me.\u201d<\/p>\n

The above is a recent exchange I had with Alexa+. Access to the next-generation assistant<\/a> has been slowly trickling out to users<\/a> since Amazon first announced availability at an event in February. But work on the smarter, more natural-sounding Alexa has been going on for years, and it still isn\u2019t ready for a widespread release. The version currently rolling out is more like an intriguing preview of what a truly intelligent Alexa could be.<\/p>\n

I\u2019m having a hard time figuring out how I feel about the upgraded Alexa. On the one hand, I cannot deny it is now capable of tackling some fairly complex requests it couldn\u2019t before. On the other, it doesn\u2019t have good memory, can\u2019t really see all tasks to completion and is just incompetent enough to be annoying.<\/p>\n

I want to first caveat all of this by pointing out that when it does become broadly available, Alexa+ will be a free upgrade for Amazon Prime subscribers. Non-Prime members will have to pay $20 a month for the privilege, but they\u2019ll still get the existing Alexa experience on their compatible devices should they choose not to upgrade. That means there will likely be no extra cost to most, and you probably won\u2019t need to spend too much time thinking about whether you want to use it. As long as it\u2019s not a worse experience, it is very easy to say yes to.<\/p>\n

I\u2019ve been tempted to get philosophical when thinking about a digital assistant that\u2019s more fluent in human. Do I really want to think of the new Alexa as basically a flesh-and-blood assistant with emotional intelligence, personality and humor? No. If it performs poorly, I’ll be let down; if it performs well and can essentially pass a mini Turing test, the ickier I’ll feel at keeping something like an indentured servant in my kitchen.<\/p>\n

I set aside my existential questions and tried to focus on the practical experience of getting help from Amazon\u2019s upgraded assistant. Is it better than the previous version? Is it reliable and easy to use? Finally, does it deliver what Amazon promised? And as a bonus, is the experience enjoyable (or at least painless)?<\/p>\n

The answer to all those questions is a half-hearted shrug. In some ways, Alexa+ delivers. But in many ways it is an excellent showcase of the limitations of generative AI, and demonstrates that the true problem with the current cohort of AI tools is a mismatch between expectations and reality.<\/p>\n

\"An<\/p>\n

Amazon<\/p>\n

What\u2019s new with Alexa+?<\/p>\n

A voice assistant is hard to describe, since it\u2019s intangible and amorphous. It\u2019s quite difficult to state where its capabilities begin and end, not to mention how it might have been upgraded. But I\u2019ll start by comparing it to its predecessor, which I\u2019ll be calling Original Alexa (or OriginAlexa, if you will indulge me).<\/p>\n

OriginAlexa taught us how to use very specific commands to do things like turn our living room lights on or off. If you had a family member or friend named Alexa, you might have renamed it to \u201cComputer\u201d and adapted your relationship to that word. Due to how you might have grouped your home gadgets, you could have begun to refer to your kitchen area lights as \u201cskylights,\u201d for example.<\/p>\n

\u201cAlexa speak,\u201d as some call it, differs across households. I say \u201cAlexa, stop,\u201d to silence alarms, while my best friend says \u201cAlexa, off,\u201d to do the same. But regardless of the specific word choices, Alexa-speak largely revolved around using stilted phrases and careful enunciation to avoid having to repeat yourself to get something done. Anyone that\u2019s used any voice assistant is probably familiar with the frustration of repeating yourself when a command has been misheard for the umpteenth time.<\/p>\n

That\u2019s (supposed to be) a thing of the past with Alexa+. In a blog post announcing the new assistant<\/a>, Amazon\u2019s lead of devices and services Panos Panay said \u201cAlexa+ is more conversational, smarter, personalized \u2014 and she helps you get things done.\u201d The company said it \u201crebuilt Alexa with generative AI<\/a>,\u201d but it didn\u2019t just use large language models (LLMs) to make its assistant converse more naturally. It also created new architecture to enable API integration \u201cat scale.\u201d These APIs are how assistants can connect to third-party services to do stuff on your behalf, and Amazon described them as \u201ccore protocols to getting things done outside of a chat window and in the real world.\u201d<\/p>\n

In a separate blog post<\/a>, Amazon said \u201cThis architecture is what will let customers quickly and seamlessly connect with services they already use in their daily life: GrubHub, OpenTable, Ticketmaster, Yelp, Thumbtack, Vagaro, Fodor\u2019s, Tripadvisor, Amazon, Whole Foods Market, Uber, Spotify, Apple Music, Pandora, Netflix, Disney+, Hulu, Max, smart home devices from companies like Philips Hue and Roborock, and so much more.\u201d<\/p>\n

Basically, Alexa can communicate with you more naturally, meaning you can talk to it more like you would with another human being, so you can forget about Alexa-speak. It will also retain information about your preferences and is capable of handling more tasks on your behalf.<\/p>\n

But enough about the promises. What was living with Alexa+ for weeks actually like?<\/p>\n

The setup<\/p>\n

Alexa+ is currently only available as an \u201cEarly Access<\/a>\u201d preview to a small group of users. Though, other people in my non-tech circles did start gaining access recently, which means you might be able to check it out yourself soon.<\/p>\n

The fact that it\u2019s still somewhat exclusive and experimental means there are likely to be glitches, which is understandable. Once I got past the first day or two after upgrading to Alexa+, I didn\u2019t notice many actual bugs. What frustrations I did encounter later seemed more to do with programming and AI\u2019s limitations than unstable software.<\/p>\n

The updated Assistant currently requires at least one compatible device with a screen on your network, so those of you who only have Echo speakers will have to wait a lot longer or try it on your phone. I spent most of my time testing Alexa+ via an Echo Show 15 as well as the Alexa app on my iPhone.<\/p>\n

There were small variations in the answers I would get on either device, but by and large the experience was similar. The most meaningful difference really was in how I perceived Alexa. Initially, when I was interacting with it on the smart display, it felt more like an upgraded smart home and personal assistant, and I predominantly asked it to check on the weather, Uber prices or to help me do things like set timers, reminders and play music.<\/p>\n

\"Two<\/p>\n

Amazon (Screenshots from the Alexa app)<\/p>\n

On my phone, though, I talked to Alexa+ more like I would with ChatGPT. I asked deeper, more philosophical questions that required more research and thought. I asked it to generate images, sort 15 names into three groups and, inspired by the subreddit \u201cr\/tipofmytongue<\/a>,\u201d help me find a book I was struggling to recall.<\/p>\n

Over time, I did come to rely on the smart display more, as it\u2019s always easier to just say \u201cAlexa, is Mountainhead a good movie\u201d than to pick up my phone, find an app and ask the AI. Of course, I could ask the same question of Siri or my Google speakers, and I did. All three assistants answered similarly, each citing different sources. Only Alexa gave me a direct answer, saying \u201cMountainhead is a good movie,\u201d followed by details like its IMDB score. The other two simply rattled off \u201cOn the website RottenTomatoes dot com, \u2026\u201d or \u201chere\u2019s an answer from whattowatch dot com.\u201d<\/p>\n

Alexa has improved in some small ways<\/p>\n

In many ways, Alexa+ is a marked improvement over its predecessor, and I have to admit I found myself nodding, impressed, at its ability to tackle multi-step tasks and recall previous conversations. Now, I have many gripes with the latter that I\u2019ll elaborate on later, but the fact that I was able to get Alexa+ on the Echo Show to check the price of an Uber ride and book it for me was a pleasant surprise.<\/p>\n

Of course, it selected the wrong pickup location and I ended up having the first driver cancel on me because I wasn\u2019t waiting at the right spot. But it did manage to completely book a ride on my behalf, relying solely on my voice commands and an Uber integration I had set up earlier.<\/p>\n

I was initially impressed by the assistant\u2019s ability to refer to our previous conversations and remember things I told it to, like my partner\u2019s address and my temperature preferences. But its ability to do so was inconsistent \u2014 most times if I asked Alexa to refer to things we had discussed in previous conversations, it either required a lot of prodding to get to the right nugget, or it simply didn\u2019t recall.<\/p>\n

I did have to tip my hat to Amazon when I asked Alexa to \u201cplay my Rox playlist on Spotify when I tell you I\u2019m home.\u201d The assistant not only walked me through setting up that routine entirely through a verbal conversation, but also pointed out limitations like only being able to set a volume for playback after a duration had been set. It presented me with two options: \u201cWe can either set a duration for the music to play, or we can make it the last action in the routine.\u201d I almost thought I was talking to a capable human assistant when it told me all that, though after Alexa misheard me and thought I said \u201csaturation\u201d instead of \u201cset duration,\u201d the illusion was shattered.<\/p>\n

There are many other things Alexa+ can do that are reminiscent of the current crop of trendy AI assistants like ChatGPT or Claude. Ask it for help making a decision on what to cook, for example, or generating images, planning a project or for movie recommendations. One new capability I was excited about was sending me emails from our conversation. I wouldn\u2019t say the sky is the limit, but I do think that coming up with a complete list of what it can now do would take forever. It\u2019d be like asking what you can search for on Google \u2014 basically whatever you can think of. Whether it brings you the answers you\u2019re looking for is a different question.<\/p>\n

I found Alexa+ helpful in that it was able to email me the lists of names it sorted on my behalf, or the project timeline I asked it to help create. But the limits to what it would send me were frustrating. Straightforward content, like the three groups of five names, arrived at my inbox with no problem. Other times, like when I asked it to email me the conversation I started this article with, it only sent me part of our chat. This has a lot to do with what Alexa deems to be the beginning and ending of a conversation, and it was fairly often wrong. I\u2019ll go deeper into the other limits of the contents of Alexa\u2019s emails in the next section, but in short, it\u2019s inconsistent.<\/p>\n

Inconsistent and imperfect<\/p>\n

That\u2019s a pattern of behavior that you\u2019ll see here. Alexa+ will be capable in some new way that has potential to be exciting and useful, but it will fail you somehow or execute its task incompletely. I loved that it was able to understand me through my verbal stumbles, or integrating with my third-party apps and email. But I kept hitting walls or being let down. The overall effect wasn\u2019t annoying enough to be frustrating, but it was disappointing enough that I never really came to rely on Alexa+ for some functions.<\/p>\n

For example, during my testing I asked Alexa+ most mornings to check on the price of \u201cthat Uber ride\u201d I booked. Over the course of a few weeks, I asked variations of \u201ccan you check the price of that Uber ride I took yesterday\u201d or \u201cplease check how much an Uber is this morning for my usual ride.\u201d<\/p>\n

In response to the latter, Alexa+ replied \u201cI can help you check Uber prices for your usual ride. I have two saved pickup locations for you. Would you like to be picked up from Billing address,\u201d and proceeded to rattle off an address I had stored in the Uber app. It continued, offering a second pickup address and asking if I preferred a different location. After I selected one, it asked where I would like to be dropped off. It\u2019s as if my previous conversations telling it this every day for a week never happened.<\/p>\n

To its (very small) credit, Alexa+ gave me accurate prices after I supplied all the parameters, but it took a tiresome amount of time. That\u2019s largely due to how verbose the responses are. I understand wanting to be specific and accurate, but I really didn\u2019t need my entire mailing address, unit number and zip code included, every time I ordered a cab. I also didn\u2019t need Alexa to keep repeating my entire question back to me \u2014 a simple \u201cYes I can\u201d would have sufficed.<\/p>\n

\"Four<\/p>\n

Amazon (Screenshots from Alexa app)<\/p>\n

Alexa+ also came off a bit needy, which would be humanizing if it wasn\u2019t so robotic about it. I would thank it whenever I was done with a conversation or request, and it would reply \u201cYou\u2019re welcome. Glad I could help you with\u2026\u201d and make a sort of reference to our chat in a few words. Or it would say \u201cyou\u2019re welcome, have a nice day.\u201d I found out I could tell it to \u201cbe less verbose\u201d and while it said it would, Alexa+ still continued to reply \u201cYou\u2019re welcome, have a good day\u201d every time I told it thanks after it filled me in on the weather forecast.<\/p>\n

I could almost put up with the overly long responses, if Alexa did things the way I expected. But like I already mentioned, it\u2019s inconsistent. Though it\u2019s capable of emailing me, it doesn\u2019t appear to be able to send images, at least based on all the picture-less emails I\u2019ve received. The inability to send photos from the Echo Show\u2019s built-in camera is a prudent privacy protection measure, but Alexa+ could have just told me that when I asked \u201ccan you send all of this plus those photos you took to me in an email?\u201d<\/p>\n

Instead, it replied \u201cCertainly, I can help you with that. I\u2019ll draft an email with the descriptions of the room and the person, along with the photos I\u2019ve analyzed<\/strong>. Let me prepare that for you,\u201d followed shortly by \u201cI\u2019ve sent the email with the image descriptions to your Gmail address. You should receive it shortly.\u201d<\/p>\n

In the email, at the very bottom, Alexa said \u201cUnfortunately, I can\u2019t include the actual photos in this email, but I\u2019ve described what I observed in them.\u201d Thankfully, I wasn\u2019t depending on these images for anything important, but if I were, I can only imagine how frustrated I would have been. To top it all off, the descriptions in the email not only didn\u2019t match what was said in our conversation, but were also wrong about what was in the room.<\/p>\n

During our conversation, Alexa said \u201cI see a person in a room with white walls, wearing a black tank top and white skirt. There\u2019s furniture including a cabinet, bookshelf, desk and coffee table.\u201d That\u2019s a fairly accurate description of my living room.<\/p>\n

The email I got had three sections with bullet points. The first, titled \u201cRoom description,\u201d listed eight items or characteristics, like \u201cwhite walls and ceilings\u201d or \u201ctelevision on a stand and bookshelf\u201d that were largely accurate. Here, it said I had a \u201cwhite cabinet with drawers,\u201d which is wrong. In the third section called \u201cAdditional observations,\u201d it said I had a \u201cceiling fan with light fixture,\u201d which I only wish I had.<\/p>\n

Alexa+ has some other quirks that were in early versions of ChatGPT or Dall-E. For example, when I asked it to create an image of an AI assistant on the screen of a smart display on a kitchen island, it was completely unable to understand my request. Not only that, follow-up attempts to get it to \u201cmake the display bigger\u201d or \u201cput the smiling person on the screen\u201d only resulted in the kitchen slowly filling up with more and more vegetables while the device remained the same size. I didn\u2019t know whether to laugh or cry.<\/p>\n

\"Four<\/p>\n

Amazon (Screenshots from Alexa app)<\/p>\n

Is the goal of generative AI to be human?<\/p>\n

I could continue to list examples of where Alexa+ failed to completely do what I asked it to, but I think you get the point. The one area where I can confirm a noticeable improvement is in the way the assistant sounds and how it understands speech. I\u2019ll say that of the four voices I was presented with when I upgraded to the new Alexa, I simply went with the default choice, which was a feminine-sounding American speaker. I didn\u2019t mind it, but I know some other people who dislike it. This is obviously a matter of personal preference, so I don\u2019t have much comment on the actual voice. I will point out that the expressiveness of the assistant\u2019s speech was significantly different from the robotic one of the original Alexa, and again, it didn\u2019t bother me.<\/p>\n

One of my biggest initial concerns was having to adjust how I spoke to Alexa. I considered myself fluent in Alexa-speak. Thankfully, so far, I found it easy to talk to Alexa like I would a person \u2014 that is, in longer, rambly sentences with verbal stumbles and utterances. For the most part, I felt understood, or at least better understood than by the Google Assistant or Siri. Of course, that in itself raises philosophical questions of whether you want to speak to AI like you would people to begin with. But from my weeks with Alexa+, that feels like the least pressing concern.<\/p>\n

Back to the conversation I had with the assistant on what to look out for when I review it. When I pressed Alexa to explain what it meant by its \u201cemotional intelligence,\u201d it said \u201cmy emotional intelligence helps me adapt to different moods and situations. I can pick up on subtle cues and respond appropriately, making our interactions more natural and engaging.\u201d<\/p>\n

This set off my internal alarm bells just a bit, so I asked how it was detecting my mood. Alexa replied that it was picking up on my tone and word choice, calling it \u201ca dance of understanding.\u201d So I pushed it further:<\/p>\n

“Tell me about your emotional intelligence.”<\/strong><\/p>\n

“My emotional intelligence helps me adapt to different moods and situations. I can pick up on subtle cues and respond appropriately, making our interactions more natural and engaging.”<\/p>\n

“Well how are you detecting my moods”<\/strong><\/p>\n

“I pick up on your tone and word choice. Your emotions color our conversation, and I adapt to match. It’s like a dance of understanding.”<\/p>\n

“How do you think I am feeling right now?”<\/strong><\/p>\n

“Based on our chat, I’d say you’re feeling analytical and focused. You’re in work mode, evaluating my capabilities for your review.”<\/p>\n

“What about when I, you know, asked you about the weather this morning?”<\/strong><\/p>\n

“This morning, you asked about the weather and I provided a sunny forecast. How did that information help you start your day?”<\/p>\n

“No, I was asking about my mood back then, do you know how I felt then?”<\/strong><\/p>\n

“Ah, I see. Based on that morning conversation, you seemed casual and curious about the day ahead. Your tone suggested a typical start to the day, neither particularly excited nor stressed.”<\/p>\n

During this exchange, I also adjusted the pitch of my voice to see if it would make a difference, and none of the responses I got gave me any real insight as to whether Alexa was actually listening to the sound of my voice to determine my mood. It felt like talking to a cagey person who didn\u2019t want to let you know what they knew.<\/p>\n

Neediness, inconsistency and gaslighting. In creating something so imperfect, maybe Amazon has actually managed to nail the human experience. I\u2019ll be clear, though. The company never said it set out to make something human. But in using terms like \u201cnatural voice\u201d and \u201cemotional intelligence,\u201d it certainly seems to imply something more person than robot.<\/p>\n

It\u2019s not a problem unique to Amazon. I didn\u2019t get too deep into comparisons to other generative-AI-infused assistants in this piece, because Alexa+ remains in limited preview and fair testing can\u2019t be conducted yet. But I did already notice some small areas where the Amazon offering was smarter than others.<\/p>\n

I asked Alexa, Siri and the Google Assistant (on a Pixel 9) to set a timer for 30 minutes, before changing my mind and telling them to adjust those to 25-minute countdowns instead. Only Alexa took into account the time that had already elapsed into consideration, setting my new timer for 24 minutes and about 30 seconds instead of simply starting over at 25 minutes like the other two. It\u2019s an insignificant difference, but effectively shows an element of consideration that\u2019s almost human in its complexity.<\/p>\n

I will spend more time with Alexa+ to further poke at the limits of its abilities and to continue our dance of understanding. We probably won\u2019t ever fully be in step with each other, but maybe the goal shouldn\u2019t be to achieve perfect harmony, and instead to simply not stomp on one another\u2019s toes.<\/p>\n

If you buy something through a link in this article, we may earn commission.<\/p>\n","protected":false},"excerpt":{"rendered":"\u201cAlexa, I need to write a review about you.\u201d \u201cOh, a review? I\u2019m intrigued! What\u2019s the occasion? I\u2019d…\n","protected":false},"author":2,"featured_media":292633,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3163],"tags":[323,34414,324,1942,121,32919,53,16,15],"class_list":{"0":"post-292632","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-artificial-intelligence","8":"tag-ai","9":"tag-alexa","10":"tag-amazon","11":"tag-artificial-intelligence","12":"tag-feature","13":"tag-gear","14":"tag-technology","15":"tag-uk","16":"tag-united-kingdom"},"share_on_mastodon":{"url":"https:\/\/pubeurope.com\/@uk\/114918194140437906","error":""},"_links":{"self":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/292632","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/comments?post=292632"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/posts\/292632\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media\/292633"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/media?parent=292632"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/categories?post=292632"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/uk\/wp-json\/wp\/v2\/tags?post=292632"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}