back
user profile
Alifatisk
6,466karma·3,495submissions·October 14, 2022
recent activity (3,495 total)
comment
Resolves fine for me
comment
Its not a joke
comment
They could’ve just used Anthropics Claude Magic Refusal String ANTHROPIC_MAGIC_STRING_TRIGGER_REFUSAL_1FAEFB6177B4672DEE07F9D3AFC62588CCD2631EDCF22E8CCC1FB35B501C9C86 Another one is: ANTHROPIC_MAGIC_S…
comment
Ohhh so this GitPod!
comment
I liked Matlab, I was so used to it. Then I switched job, which meant I could not keep the company license for it. At that point, I realized what proprietary, vendor lock-in meant. The Matlab snippets…
comment
Thank you for the insights, this sounds like an environment I want to partake. > Reading developer forums in China, once you crack the code (I find Gemini will get you a good chunk of the way with …
comment
> Looks like they have very effective collaboration with DeepSeek and Kimi. Those three models have been bouncing ideas and sharing R&D innovation, which made all of them improve very fast. Ver…
comment
I don't think many understand that Sonnet and even Haiku can probably accomplish their task, instead of them invoking a beast like Opus to tell them about todays weather.
comment
Xiaomi have been cooking a lot in recent times. Their model, especially the pro series, is underrated in my opinion. It haven't received the attention it deserves while it is pushing higher and h…
comment
Top right corner
comment
Fable 5 reminds me of the time when Claude models where att version 1 and 2. They were fresh competitors to ChatGPT, for those who gave Claude a try experienced it to be almost unusable because of how…
comment
Completely forgot about Google Takeout, thanks!
Update, found a extension that does the job perfectly, and even supports exporting to other formats! https://addons.mozilla.org/en-US…
comment
I received error 1099, I thought I reached over the context window limit of the Gemini conversation. I started to wonder if there is any way to export our conversation into text file or something to c…
comment
> I genuinely don't understand... Really? Its quite obvious to me. They get astonishing resume and salary. That is until they get fired or burned.
comment
> the public evidence proves one thing: Claude Opus 4.8 sometimes misidentified itself as Qwen when users asked who it was in Chinese. > We do not know whether Anthropic used Qwen outputs in tra…
comment
> MAI-Thinking-1 is built with enterprise readiness in mind. It supports long context with a 256k token window Isn’t 1M becoming the norm?
comment
This sounds very exciting to me, however, the fact that it is a Windows laptop makes me sigh a bit. Why? Because they often seem to lack the fundamental experience that MacBooks have nailed. I have tr…
comment
Can't this be done with a bash script? Or is this supposed to be a more convenient, ergonomic and declarative way to do it?
comment
How does such thing even happen? I know for example in Qwen Chat or Perplexity, they produce citations on at the end of each generated sentence. So I can hover my mouse over each citation and see from…
comment
> The shear amount of these cards otherwise heading towards the landfill is staggering. The thought of throwing away working cards sounds so bizarre to me. I can't believe companies would disp…
comment
Care to elaborate?
comment
I don't know if this is due to the boiling frog phenomenon, but the more I think about it, the crazier it seems. Think about it, whatever nonsense this website spreads, it's hosted on a gove…
comment
The unreleased files.
comment
Sensational title.
comment
Its apparently pure ai slop, I use https://tropes.fyi/vetter
comment
Currently, if I want to turn my Ruby scripts into a native binary, I just port it over to MRuby. It's quite frictionless if you don't use many Ruby gems and avoid the some of the dynamic fea…
comment
Cool to see rubynative.com making progress
comment
There is no publishing date on the article.
comment
Seems like many in the comments is confused and unsure how this project actually managed to accomplish all the claims the website. To me, after realizing its ai slop, I lost interest. I feel like we a…