I often think about this precise scenario. There are so many cases and times where a big company shuts something down that would be perfectly viable at a different scale. My previous company got acquired by Verizon and then shut down because it didn't scale to a $1B business within five years (or something like that). I'm not claiming it was a viable business in the first place (it probably wasn't) but now we'll never know. And for this story, there's a thousand others. I understand that sometimes the small company becomes intertwined with the big company to a detrimental extent, but there are also plenty of cases where a separation is still very well possible. The separation doesn't even need to be the business whole, but it could be a constellation of IP and resources, for which someone creates a new business entity. I wish that more execs created that possibility, instead of just writing off a financial loss and calling it a day. While the write-off makes business sense to the bigger company, and there may not a huge business justification for spinning off instead of shutting down, there's also just something to doing the right thing in terms of providing continuity to the users of your product, and giving engineers a chance to double down on a product development that they may have faith in.
From the company’s perspective it’s a straightforward calculation.
Considering that this will only apply to failing products, the price they can expect to get for it is negligible, more so considering the buyer is going to be a handful of regular employees rather than a big company. So selling vs killing makes no material difference to their bottom line.
On the other side, there’s a mountain of due diligence they have to do to make sure that the decision is sensible. Is the product tied to the company’s brand at all? Will it reflect badly on them if the new owners decide to take it in some different direction? Or can it be used to compete with the company in the future? Does it have user data? Are they in accordance with the TOS and a thousand data laws when selling it to someone else?
So from the business side the sensible answer is usually to just kill the product.
Will it reflect badly on them if the new owners decide to take it in some different direction?
I think there's still a flip side to these decisions. Google has an established reputation as a product killer, I'm sure the effect of that won't bring them down but it's there and I doubt handing a product off to someone else would either.
> Considering that this will only apply to failing products
Companies like Google often shut down products that would be called incredibly successful if they were a startup or small business. In $BigCorp, the yardstick is their main moneymaker, and if you are less profitable and don't fit in the larger strategy you can get cut simply to help the company keep focus on what's important.
On the other side, there are so many companies that would never really make it without a lifeline that extends into the hundreds of millions. Even after IPO, there are so many companies losing heaps of money. So maybe Google just doesn't want to be losing $100M a year for 10 years.
I worked for a tiny, independent project for a giant corporation for a couple of years. It absolutely would have worked as a 2 or 3 person company but it was definitely the wrong place for a dozen engineers as part of a giant corporation. They shut it down, but now I'm wondering whether they would have entertained a small offer to buy it. Probably not, but I guess I'll never know.
There are similar examples within companies. For instance, I led the establishment and growth of a ~50m cyber security practice for a US vendor in a region. Ended up ~22% EBIT. Unfortunately the software business is >65% so my business was diluting regional performance. I got the call to slow down growth so I left. Ultimately they shut down the services altogether and gave it to channel. I offered to buy the services business but they weren't interested.
As a viable language-learning app (on the freemium tier), it's mixed and getting worse. I'm a 3.5-year Duolingo user.
See the 2/2023 HN post "How Duolingo reignited user growth" [0] describing how they/ the former CPO aggressively traded off reducing the utility for actually acquiring language vs too much gamification (not all users want 'Candy Crush' levels of gamification), user growth, leaderboards, challenges, cutesy animations, inventing silly revenue streams like 'streak protect' (all prior to the 7/2021 IPO, ticker 'DUOL').
Duolingo locked the Chinese course mid-2022 [1], that means no more fixes ever, no corrections, the broken or missing audio (and answers, and hints) stay broken or missing, all discussions (users helping users, handy links to third-party sites) are frozen. For no good reason. They don't give a hoot for gamifying valuable user contributions which add/improve course content/fix mistakes. If any of you were contemplating paying for DL Chinese before they locked it on the charitable basis that they'd fix the broken bits someday after they'd banked the IPO loot, well obviously not now. (Here's e.g. Langoly's list of "The 11 Best Apps to Learn Chinese (Mandarin) Fluently" [2])
By comparison the Spanish course is alive and being improved; they added Stories.
TL;DR: optimizing the product to juice up metrics like DAU prior to the IPO is good for valuations, but is not a great long-term approach to a language learning app and its community.
I agree that there can sometimes be a tradeoff between retention and learning. But having been on the inside the overwhelming impression I got was that Duolingo really does care about teaching effectively. They have a whole Learning Area with multiple teams dedicated to this and I believe the CEO and exec team really care about it.
Obviously Duolingo isn't perfect but they're very aware that there's still lots to improve. And sure, maybe their approach to gamification isn't for everyone, and that's fine, since there are many people who do like it!
No, I'm talking about the tradeoff between monetization/gamification vs learning. Too much of the former is degrading the latter and this has been getting worse since they switched to juice their metrics (CURR, DAU, $/user) for the IPO, as Mazal posted.
User Kortaggio [0] talks about how Duolingo's claim “an average of 34 hours of Duolingo are equivalent to a full university semester of language education” is misleading because it's based on their long-discontinued SRS algorithm. Sounds like false advertising.
The gamification features are one-size-fits-all (whether you're age 13 or 30 or 65, occasional or dedicated user) and default-on: interstitial animations, success videos, chests of gems, then yet more 5/15/30-second ads... I challenge you to measure the % of time within a 10-minute segment that is actually spent on learning. Or at minimum, they could show me the cutesy stuff while I'm doing the language task, Super-Puzzle-Fighter style.
I'm a 3.5-year user (>1200 days), I clearly don't need somersaulting owls and faux-challenges to keep me going and I passed that point 1190 days ago, if not always.
Many (adult) DL users write about how the ever-increasing pushiness with leaderboards, quests, streaks ('create false urgency' per Candy Crush which the former CPO cites as a model) turn them off. Should have different use-modes for different segments of user.
I believe DL care about teaching effectively only up to a limit, and that limit is anything that might reduce their metrics, as a freemium app.
They don't care about teaching Chinese effectively, not since back in 2021 if not earlier, they simply gave up. This is quite sad and weird for the world's second-largest language. There isn't "still lots to improve" on the Chinese course, they simply gave up and locked the forums permanently so that now not even well-intentioned volunteer users can fix that one.
Also, DL committing intentional trust and GDPR violations without any online opt-out doesn't sound ethical "Facebook Still Tracks People on Yelp, Duolingo, Indeed" [1]. Obviously tracking without user consent is for monetization of ads. Like I said, monetization trumps other considerations at DL.
(PS I signed up for your ReadLang, but for Tagalog it's pretty beta. Good luck with its second incarnation).
(Update: China banned for-profit foreign tutoring 7/2021. But that still doesn't justify why DL locked their Chinese course, leaves lots of other countries where people want to learn Chinese.)
Yes I have a brief one, sorry that it's not specifically related to Readlang!
You kind of stopped blogging as much when you joined Duolingo, what would you say were the biggest factors why? I'm assuming Duolingo weren't super restrictive on what you could post so that might not be the big reason, but I could be wrong!
Good question! There was a lot to do and I was kept busy just with internal communication, so didn't feel the urge to share externally so much. Also, getting outside attention didn't feel as important given my role at the company compared to when I was alone running my own project.
I actually remember asking them how restrictive they would be when it comes to sharing when I joined and they said they weren't as secretive as Apple, but that they weren't completely open about everything either. If I had had the urge to post anything I would have run it past people before publishing details about what our team was working on, and it would have probably been fine. But in the end, like I said, I was always busy and blogging fell by the wayside. (I was never a naturally prolific blogger anyway)
The internal/external rift is so interesting and perfectly reasonable. Hard to spend time self editing after an exhausting day, and guess that's where places like Twitter really shined. Yet I wish that gap could be bridged somehow, it feels like many great posts with overlooked details are left unwritten because of the lack of external validation combined with internal hurdles.
Meandering now, but your blogs are enjoyable reads and that's the most envious quality I have of writers!
Hmmm... I'm actually not sure if I can talk about the numbers from the original sale in 2017. But I'll say that the original sale was paid partly in stock options which vested over a few years and ended up being worth a lot. And the price of the buy back was much much less than that.
Funnily enough, in the original sale I negotiated for more cash and fewer options. Luckily for me they only moved a little bit in my direction since the options ended up being worth much more.
Not related to the buyback but more generally to Readlang, how did you select the pricing?
I've noticed a sort of bimodal distribution of prices in language companies with the sleek/modern looking ones centering around 5$/month, and more traditional companies going for 20$/month for seemingly the same service (so the latter not presented as a luxury alternative to the former). Wondering if you did any A/B testing or generally what your methodology was if you don't mind sharing.
I started at $10 per year, then gradually raised prices as the product got better, always keeping existing subscribers happy by grandfathering them. At one point it was $4.99 every 3 months, which is the plan my mum is still on :-) For a brief time I offered a lifetime subscription for $100 and sold a few but felt uncomfortable offering to keep the service running forever with no further payments so killed it.
I ended up at $5 / month or $48 / year. It's possible I might increase it a bit more in future but for now I think it's better to keep these prices and try to grow user numbers instead.
One thing I noticed with some companies was that the yearly plan was very heavily discounted compared to the monthly one. To me that gave the impression of lacking confidence that monthly users will stick around long term, so I didn't want to do that.
Yeah I think it's true that popular mainstream consumer products tend to be cheap and highly polished, and that more niche products tend to be higher priced and less polished.
The yearly plan is discounted because it allows self-funding and retains control, versus VC dilution. Explained here: https://youtube.com/watch?v=otbnC2zE2rw (I am not working at present, but I rewatch this every once-in-a-while because it is an amazing talk!)
> One thing I noticed with some companies was that the yearly plan was very heavily discounted compared to the monthly one. To me that gave the impression of lacking confidence that monthly users will stick around long term, so I didn't want to do that.
It probably reflects reality, but I can see the point of showing lack of confidence in the product.
Not a language product, but Bumble (the dating app) at one point -- no idea if they still do it -- offered a lifetime membership priced at around 6 months of monthly subscriptions. I find looking for that kind of pricing can be highly instructive about a business and their competitive landscape, because presumably they'll have run their numbers and are expecting to earn more that way.
So it's not just signalling lack of confidence, but also giving away a very strong signal about the lifetime value of their customers.
I think it slightly works different with a dating app. In theory, if the app works you don’t need it anymore. So in their case, it is confident to offer a big discount.
In terms of the specific, very low, multiple you're of course right - a dating app is an extreme.
But the overall principle that you should expect the discount to reflect their estimated lifetime value of a customer unless the amount is high enough that the investment return can exceed the regular income. With the exception, as noted by conradfr, that if someone suddenly offers a steep discount it could reflect an attempt to raise expensive capital fast
Assuming you're aware of those factors, it's a useful way of gaining insight into customer retention (assuming they're competent enough to run the numbers...)
Highly polished it depends, but mainstream products certainly won't cater to the long tail of niches. Some niches are still large enough to be profitable for a smaller product, others aren't (and will hardly be supported by any product at all)
For now it provides the whole sentence that the word was in for context. It works pretty well but I'm sure it would be better if I gave it a little more. 2 or 3 sentences would probably be great, but obviously more expensive to run.
Small suggestion: You may want to fix your DNS configuration which currently only resolves readlang.com and not www.readlang.com. This might confuse some visitors (it confused me when I typed readlang and pressed Ctrl+Enter):
dig has the worst output I've ever seen in a CLI tool. Fantastically useful when I've bothered to learn it, but it's just not intuitive. I always forget what everything means. What am I looking at here? The _lack_ of an answer section?
It's very verbose by default, but that's when/why you use it. If you just want to know why something doesn't work, you use ping.
$ ping nxdomain.example.com
ping: nxdomain.example.com: Name or service not known
$ ping example.com
PING example.com(2606:2800:220:1:248:1893:25c8:1946 (2606:2800:220:1:248:1893:25c8:1946)) 56 data bytes
64 bytes from 2606:2800:220:1:248:1893:25c8:1946 (2606:2800:220:1:248:1893:25c8:1946): icmp_seq=1 ttl=52 time=93.2 ms
If you want a short summary, you use host:
$ host nxdomain.example.com
Host nxdomain.example.com not found: 3(NXDOMAIN)
$ host example.com
example.com has address 93.184.216.34
example.com has IPv6 address 2606:2800:220:1:248:1893:25c8:1946
example.com mail is handled by 0 .
or nslookup (from the same bind9-dnsutils package as dig):
When I dig my personal domain name, I get 19 lines of output of which 1 comes from the zone file and contains the actual answer. The rest is mystery meat.
I mean, sure I can decipher that "rcvd" stands for "received" but if I have my timeline correct there never was a time when such character count mattered and dig existed.
But why can't it be --short (or --quiet) like every other tool, so that I then have a chance of being able to remember it the 2-3 times/year I need it?
Out of curiosity I asked ChatGPT what the output means and this is what it responded :) Maybe this helps you!
This output is the result of using the dig command to query the DNS (Domain Name System) for an A (Address) record associated with the domain name "www.readlang.com". Here's a breakdown of the output:
; <<>> DiG 9.10.6 <<>> a www.readlang.com: This line shows the version of dig being used (9.10.6) and the command executed (dig a www.readlang.com). The "a" argument is asking for the IPv4 address associated with the domain name.
;; global options: +cmd: This line displays global options for the dig command. "+cmd" is a default option that includes the initial command line in the output.
;; Got answer:: This line indicates that the DNS server has provided an answer to the query.
;; ->>HEADER<<- opcode: QUERY, status: NXDOMAIN, id: 65131: This line shows details about the response header. "opcode: QUERY" means it's a standard query, "status: NXDOMAIN" indicates that the domain name does not exist (non-existent domain), and "id: 65131" is a unique identifier for this query.
;; flags: qr rd ra; QUERY: 1, ANSWER: 0, AUTHORITY: 0, ADDITIONAL: 1: This line provides information about the response flags and the number of entries in each section of the response. "qr" means the response is a query response, "rd" indicates recursion was desired, and "ra" means recursion is available. The number of entries in the QUERY, ANSWER, AUTHORITY, and ADDITIONAL sections are 1, 0, 0, and 1, respectively.
;; OPT PSEUDOSECTION: and ; EDNS: version: 0, flags:; udp: 1280: This part shows information about the Extension Mechanisms for DNS (EDNS). The version is 0, and the UDP payload size is 1280 bytes.
;; QUESTION SECTION: and ;www.readlang.com. IN A: This part displays the question section of the query, which is asking for the A record (IPv4 address) associated with "www.readlang.com".
;; Query time: 62 msec: This line shows that the query took 62 milliseconds to complete.
;; SERVER: 2406:3400:41e:5a80::1#53(2406:3400:41e:5a80::1): This line displays the IPv6 address and port number of the DNS server that responded to the query.
;; WHEN: Fri Mar 24 10:06:36 AEST 2023: This line indicates the date and time when the query was executed.
;; MSG SIZE rcvd: 45: This line shows that the total size of the message received was 45 bytes.
The main takeaway from this output is that the domain name "www.readlang.com" does not have an associated IPv4 address (A record) in the DNS, as indicated by the "status: NXDOMAIN" and "ANSWER: 0" parts.
Interesting. To save anyone else looking it up, Ctrl+Enter in Chrome, Firefox and Safari (at least) is "Add www. and .com to a site name, and open it in the current tab".
I cannot wait to use your website tomorrow. I've been dying for a resource to learn Serbian outside of the only book that exists ( pretty much ) and my own efforts in getting flash cards, childrens' books, etc. together. You're seriously a life saver, I cannot wait to try this out. I wish I had heard of it a year ago. _Thank you_. You have produce a connection to my heritage and ancestry that nobody else has, and I really appreciate it.
That's a good tip because it is in fact the same language with various dialect and naming differences, similar to the many flavors of English we have today or different variants of German. Montenegrian is the latest addition to the family.
However, everyone I know has a common understanding about this, so I'm not sure who would be reluctant to admit that it is the same language... outside of the very few extremist groups of course :)
Oh definitely. They're pretty few and far between, too. I actually usually say that I'm learning "Yugoslavian" -- not as a callback to the country, but to the whole region. There are definitely slight differences, but they're all very similar languages, and looking into resources for all of them will be a great way to get an awesome view of the rich and diverse culture of the Balkan peninsula.
Wow, how is it that there's only one instructional book to learn Serbian? There are many books to learn Norwegian out there (which I'm familiar with because I have learned a bit of Norwegian in the past), and fewer people speak it than Serbian.
I just think there's a lack of interest, which is a little sad. The culture is rich and fun, and the language is rhythmic and poetic. I wish more people would try to connect with their Slavic history!
Hey, that's great! I was a Readlang subscriber for a few months last year and often had the thought "why isn't this better?". It even has a place on my (long, cluttered) list of potential ideas to work on. So I'm happy it will be revived and improved!
Also, here's the note from my list on what I wished Readlang would do: "check out how News in Slow Spanish (newsinslowspanish.com/) turns each word into a hyperlink. Hovering over it gives you an instant popup. This is a way better experience than Readlang, which requires you to click each word to get its translation."
Thanks for the suggestion! I think in that case I'd probably want it to automatically combine certain adjacent words into phrases, which is definitely doable with AI but could be expensive to do for an entire text vs just paying for the words and phrases you click to translate like it does at the moment. Also, newsinslowspanish only turns some of the content into links - it makes an assumption as to which words you'll know and which ones you won't, which may not be valid. If you turned the entire text into their style of hoverable links it could look cluttered. You'd want more subtle ones. In fact, it would be very much like Duolingo Stories, which does work well! I'll think about this.
Yes, I'm sure it'll take some subtlety to do this well. My struggle with Readlang was always that it just doesn't provide the whole meaning -- for instance, a correctly translated phrase doesn't necessarily tell me what the individual words mean. IIRC I got to where I'd use both monitors: one with original language+Readlang, and one with Google Translate applied to see individual words, and yet another tab on that window to look up words as needed.
My dream Readlang would have been one where I could quickly context-switch or change to see all of that, but it would probably require some significant client-side data and programming to achieve.
Good point! I just made the first mention of Readlang into a link to the website: https://readlang.com
It's a web-app and browser extension to help people learn languages by reading texts or websites in the language they are learning, get helpful translation hints and definitions to aid comprehension, and then to practice the new vocab with flashcards.
The concept looks extremely interesting, but (like the vast majority of language learning tools) Albanian is not supported. I might give it a try for German though
I'm planning to add some more languages after improving the UI. Right now the dropdowns to select languages feel unwieldy with so many options. If you want me to let you know when I get around to adding Albanian, email me at $MY_FIRST_NAME@readlang.com or send a message via https://readlang.uservoice.com/.
Tucan actually works in reverse compared to Readlang. Say you're a native English speaker learning Spanish. With Tucan you browse the English websites you're already used to browsing, and it'll automatically translate some of the words to Spanish to sprinkle in a bit of practice that fits within your normal routine. It's a nice idea (actually this is the first one I saw doing the idea: https://www.theverge.com/2012/5/3/2995523/google-language-im...) but for me it didn't stick. I found it weird to be learning isolated Spanish words out of their normal context, and pretty soon it just became annoying to have these Spanish words popping up everywhere. Maybe it works for some people though.
With Readlang the idea is that you read actual websites in the language you're learning. If you're learning Spanish you might read El Pais or BBC Mundo for example. And to aid you, you can click on the odd word or phrase you don't understand to get a translation in English. It's intended for intermediate and advanced learners. Unlike Tucan you need to seek out texts to read in your target language, and Readlang offers a list of popular sites in each language to help you there: https://readlang.com/es/links, but there's obviously more friction than something like Tucan which fits into your normal English language browsing routine.
Interesting, thank you for the explanation. I tried Toucan a year or so ago and just as you said, it was weird and didn't stick for me either. I will try Readlang!
> It turned out that people were using Readlang for card testing fraud. After I helped them to fix the problem
How does one fix the card testing fraud problem? Certainly you can refund people after the fact, but it seems to me any point where small-dollar service/product can be purchased by card is vulnerable and you'd have to kinda guess whether the usage makes sense?
The ideal fix was to upgrade the version of Stripe checkout. At the time though I was looking for a quick solution and was scared to update the Stripe libraries for fear of accidentally breaking something else. So here's what I did:
- First I tried adding an IP address based rate limiter to the signup and payment routes, and required that all users had translated at least one word before being allowed to upgrade. It stopped the attempts for a few hours, but then they started back up again.
- Next, I used a more drastic approach, which would prevent all payment attempts from all IP address if we received more than 10 failed payment attempts within a 1 minute window. Still didn't work.
- Next, I changed the thresholds to 4 failed payment attempts within 5 minutes, and this finally worked!
Since buying Readlang back, I've updated the Stripe checkout to the latest version, turned off the circuit breaker, and haven't had any further problems.
There a lot of ways to reduce, just some ideias: turn on 3dsecure authentication whenever available. Check user location vs card location. Validate cvc code and postal code. Check for user activity and user signals (user agent, screen size etc) on the website, and other methods.
Nice story, with a good ending. Never heard of Readlang before, but for sure I’m going to give it a try. Bravo Steve and well done on getting back your “creation”.
No direct comment about buying the startup back. But I had never heard of this site before today and I am trying to learn Spanish.
Also, the creator seems like it’s a simple sustainable business model - I give them money and I get a useful service without any advertising or dark patterns.
Yep, I like the fact that it's a simple business model with well aligned incentives. It's a direct relationship between me and my customers. I keep getting paid as long as the site continues to be useful.
I also send an automated "Readlang account renewed" email every time I receive a renewal payment. Most SaaS products don't do this for obvious reasons, but it sucks when I realize I've been paying a subscription for something I'm not using, and I don't want to do that to my customers.
This is great, I love to see these work out. This type of re-acquisition can be difficult to see through to completion. The acquiring company has moved on and doesn't want to spend resources on dealing with it. I had tried to do this too at one point but then then newish CEO of the company we were trying to buy it back from was gone and we sorta gave up.
I imagine it would have been a lot harder in my case if we'd actually integrated Readlang with Duolingo, sharing user accounts and that kind of thing. Luckily it was quite separate. I was a little stressed dealing with accountants and tax stuff here in Spain, and worrying that the technical transfer would go smoothly. But dealing with Duolingo was super easy.
Congrats. Anytime I see someone work on something they truly love, it feels good. It is my dream too.
Is it okay to ask, do you pay for the dictionaries you use? The homepage says "translate words and phrases" - do you use some kind of translation API, like Google?
And recently I've added a feature to get context-aware definitions from the ChatGPT API, but this is just for premium users in English, Spanish and French for now.
There seems to be no Firefox extension, are you ever planning on creating one? The most I could find was a thread with a link to a corrupt extension https://readlang.uservoice.com/forums/192149-general/suggest...
I'd love to try it out but I can't seem to use it (also if making a extension I'd feel a lot more comfortable getting it off the Firefox Addons from addons.mozilla.org)
I am so glad to hear about this. Readlang has always been one of my favourite language tools and I am sure you can grow it up to to be a pretty decent sized service, with decent MRR.
Let me know if you are ever in Berlin and we can meet up again!
@steveridout Interesting post and journey, thanks for posting.
Readlang - what would you say is the user persona you're going for? I need to learn (tourist) French. I'm not going to read sites about "where is the bathroom?", for example.
It's mainly for intermediate and advanced learners who want to tackle longer texts. I originally made it so that I could read novels in Spanish.
Readlang may not ever be appropriate for complete beginners. But it could do better at providing stories written in simple language appropriate for beginners in specific situations like yours. Right now there is a public library of shared texts: https://readlang.com/fr/library, and a list of popular websites: https://readlang.com/fr/links. But you're largely left to your own devices to find content, which adds friction for new users and isn't ideal.
It was a mix of cash and stock options which vested over a few years. There was a confidentiality clause in the contract so I can't be super specific. But I asked ChatGPT what a typical price per employee is in an acquihire and it gives the following answer. I'll just say that the common range it gives doesn't sound crazy to me.
> In general, the price per employee in an acquihire can range from $100,000 to over $1 million, with a more common range being between $250,000 and $500,000 per employee.
Why do you think Readlang stagnated when it was under Duolingo’s ownership? What were the main factors that prevented it from reaching its full potential?
Basically it's because I don't think Duolingo wanted the product so much as they wanted me. No-one used the term acquihire at the time but I was under no illusions that that's what it was.
I did think that I might push to develop Readlang at Duolingo, but it never seemed like an attractive proposition for a bunch of reasons. I think it would have needed to grow at least 100X to start getting interesting within Duolingo. Not to say this was totally impossible but it seemed like a tough job. Also, some of the things that Readlang does, like browser extension and public sharing of texts, feel a bit "wild west" compared to the rest of Duolingo which is more curated and controlled, so it's not clear exactly how Readlang would have needed to change to fit in. I figured that if I tried this and integrated it tightly within Duolingo, and then failed to grow sufficiently, then the risk of it ultimately shutting down would have increased.
Also, I had other exciting projects to work on there which seemed more valuable for Duolingo, and therefore better for my reputation within the company, so I was happy to work on those!
What a nice story, I wonder if they negotiated much on offers or if it was really a simple low ball for duolingo to get rid of. Generous if the latter!
To be that attached to your idea after all this time is also very impressive. Most people would have just abandoned it and moved on, even if it was making decent money.
> if it was really a simple low ball for duolingo to get rid of
At 4K MMR it was probably a pain in the ass for Duolingo to maintain and the reason for acquisition was hiring the developer and avoiding a potential concurrent (which in the end never realized) so I'd imagine it was a very easy buy.
And I'm not saying that as a criticism of ReadLang, I think it's a great tool actually.
Yeah, it was pretty easy. Relatively low offer and not much negotiating. From their point of view it wasn't worth maintaining. I'm just very happy they offered it back to me instead of shutting it down.
Working in a larger company it's sad to see all the perfectly viable projects canned because they aren't billion dollar businesses. I wonder if there is a marketplace play here where companies can easily resell and offboard these kinds of companies rather than kill them off.
Congratulations on what sounds like an ultimately positive experience.
Cool to see Norwegian on the site, but the very first Library thing I went in to had an error in the Norwegian. I don't really understand how the site works, but that put me off a bit.
Yeah, this is a problem. Anyone is free to share texts to the public library and there's no quality control, just an upvoting feature to try to surface the best content at the top. I accept that the public libraries are a mess at the moment and it's not easy to identify the high quality content there. Lots of room for improvement!
