I throw all my queries at Grok 4 Expert, GPT 5 Thinking and Opus 4.1 Extended Thinking.. for Golang it's been my experience that Grok produce the best results about 90% of the time as well.
Claude definitely engage in some shady and illegal behavior. I wanted to see what the annual plan would cost as it was just displaying €170+VAT, and when I clicked the upgrade button to find out (I checked everywhere on the page) then I was automatically subscribed without any confirmation and without ever seeing the final price before the transaction was completed. Turns out that price was €206.50. Getting refunded was also a pain in the ass.
The bottle caps are a joke, but how can anyone in their right mind be against transparent pricing?
You think it's acceptable that a company say the price is €170+vat and then after the transaction is complete they inform you that the actual price was €206.50?
A bit off topic but I wanted to let you know that anthropic is currently in violation of EU Directive 98/6/EC:
> The selling price and the unit price must be indicated in an unambiguous, easily identifiable and clearly legible manner for all products offered by traders to consumers (i.e. the final price should include value added tax and all other taxes).
I wanted to see what the annual plan would cost as it was just displaying €170+VAT, and when I clicked the upgrade button to find out (I checked everywhere on the page) then I was automatically subscribed without any confirmation and without ever seeing the final price before the transaction was completed.
They don't need to sue, they'll just ban your account with no warning or explanation the moment you get on their radar.. at least that's what they did to me.
I wanted to do something similar, but ultimately went with Hugo and Astro for my projects because I wanted to host it on Cloudflare Pages. Are there any similar hosting options available for this approach?
It's amazing - sadly won't use it since shadcn/tailwindui-catalyst is tied to react.. I'd definitely pay for something like this if it used vanilla js (mainly interested in Text/Headings/Tabs/Button/Badge/etc components that wouldn't require any js, and for the ones that require js then I'd prefer vanilla or vue).
> I had a bug that wouldn't let me login to my work OpenAI account at my new job 9 months ago.
I also cannot login on Firefox (latest version) with strict privacy settings and AdNauseam on desktop.. and a few weeks ago they broke their website on iOS v14 as well for no apparent reason (it certainly didn't make me to download their app since that require v16.1+).
Are OpenAI still limiting Whisper to 50 requests per minute (and gpt-3.5-turbo at 3/min)? If so then they don't need to undercut OpenAI but just provide unlimited requests.. it's near impossible to provide user-facing AI solutions to customers due to these limits, and it's a very bad user experience (and security risk) to force users to provide their own OpenAI API keys.
https://replicate.com/ is much better with an average 10 requests per second but would still very much prefer unlimited (where they can monitor high volume users to see if it's legitimate), or add new pricing model where e.g. 0-10k/rpm is at $0.001/sec, 10-100k/rpm is at $0.010/sec, 100k+/rpm is at $0.100/sec (pricing would of course need to be fine-tuned, just a quick example).
They look amazing but it feels like a huge mistake to even include a camera (unless it's only inward-facing).. they should focus on Audio + AR + AI.
The camera quality will be terrible compared to what you can get from the phone that's already in your pocket, and it just going make a huge portion of the population feel creeped out by it.. whereas there would be no real pushback against a HUD that provided real-time transcript (big win for deaf people) and translations powered by Llama.
1) Receive popup asking if I want to install the latest version (no warning of the consequences of doing so) which I accept
2) Be greeted by a 'sign in' screen as well as a new Scratchpad icon which doesn't contain any of my projects/collections/requests.. at this point I believe all my data has been wiped (and it probably would've been if I had uninstalled the app when I downgraded instead of overwriting the existing one)
It's a shame because I have promoted your product to over a hundred classmates/coworkers/friends that were previously using Postman/HTTPie/curl.. even if you didn't financially benefit from my use then it also didn't cost you anything, and I provided a lot of free conversions (some of whom might be using your cloud solutions, no idea)..
At least version 2023.5.8 is almost perfect so I'll probably be happy with using that for decades if no better alternative appear.. only downside is that the generated code snippets are kinda shitty (especially for golang, and some obvious languages missing) and I guess I won't be benefiting from improvements made there.
--
A couple of ideas I would personally pay for with the local version of Insomnia:
- Create my own code snippets (so I don't need to rewrite code generated from your Generate Client Code).
- Ability to create HTTP Request templates so you don't need to duplicate existing ones (which you can't do across collections as well).
Have more but I guess it would be a waste of time since you seem fully committed to your choice of violence ^_^
If you use Mac then you can consider Orion by Kagi (natively built with WebKit) which supports both Chrome and Firefox extensions (experimental).
(I personally use Firefox since I feel it's a much better browser (especially thanks to Firefox Multi-Account Containers), so can't comment on quality since I just tested it briefly.. but I do use Orion as my main browser on iOS where it's amazing.)
I don't think Kagi is close to that amount of traffic to be honest (although I'd love to be wrong, in which case they might bypass the limit by rotating between different Programmable Search Engine accounts).. I mean they require signup and even then limit to 50 searches/month unless you start paying $10/month, which is totally fair but a very high barrier of entry.
$7 per 1000 searches was already incredibly expensive.. increasing it to $25 is a joke. It feels like now that they're going all-in with Bing then they don't want to deal with other competition.
Also worth noting that Bing doesn't allow small websites access the Microsoft Advertising network to help offset the cost. I've been told by a kind stranger that you need at least 10k searches per day to get access, that's $7500/month you now need to pay before you can even begin to monetize your service (and you'll probably spend tens of thousands before you reach the threshold). No idea how much you can expect to earn per 1000 searches with Microsoft Advertising if you're lucky/influential enough to get access, but I doubt it's much more than $25.
You're only allowed up to 10k queries per day, so you can't really use it to build a competing search engine.
I used their Programmable Search Engine (which doesn't have this 10k/day limit, but instead is client-side with other limitations), but the moment my Google-approved-non-profit was about to receive its first AdSense payout that would be donated to other charities, then they not only banned my AdSense account, but they also went a step further to ban my Programmable Search Engine account.. I have no idea why since it's impossible to get in touch with a human.
API's that charge by usage usually have terms that prevent caching API results. This also applies to Bing:
> You must use results you obtain through the Services only in Internet Search Experiences (as defined in the use and display requirements) and must not cache or copy results. (https://www.microsoft.com/en-us/bing/apis/legal)
It's really unfortunate Microsoft doesn't provide a free API that require users to display ads, or at the very least make their ad network accessible to all.
Some simple example:
https://claude.ai/share/6d178173-cdf7-4e50-a467-73ee9f479d56.
https://chatgpt.com/share/69102735-46ac-8012-9cf0-0969585c86....
https://grok.com/share/bGVnYWN5LWNvcHk%3D_54b5f2f1-732e-4372....
I don't use Gemini but haven't been impressed whenever I tried it with GitHub Copilot.