Telegram is a honeypot. They are supposed to be for privacy but their regular messaging isn’t end to end encrypted, you have to enable that per chat (I think per chat, I’ve almost never used the service).
The Russian government going after this guy is much like the fear mongering OpenAI and Anthropic put out about how powerful their models are or about having to see a doctor after taking Viagra and having a 4 hour erection. It’s marketing to make Telegram seem so private that the tech savvy Russian government has to stop this guy when in fact he’s giving the data to them.
I was concerned.
I thought they just used open weights models on infrastructure they get from someone else. They say,
“What about data and privacy?
The plan is designed primarily for international users, with models hosted in the US, EU, and Singapore for stable global access. Our providers follow a zero-retention policy and do not use your data for model training.”
“The advantage of OpenRouter compared to using API providers directly is that you can switch between API providers without binding your money to a single provider.”
Opencode Go gives you a choice between “the best” open weight models and you’re not tied down to just GLM or MiniMax and Zen gives you an even longer list of providers including Claude and GPT?
Is it that Openrouter gives you access to like… every model and provider?
$10 a month gets you generous usage with the best open weight models and they claim to have zero retention and not to train on your usage.
It’s unclear to me what the advantages of openrouter are but it seems to be a default I see many people talking about here.
Thousands is a conservative under count according to this.
For me MiniMax 3 has really hit the sweet spot of being very cheap, though more than flash, but I’d also very capable.
I’ve been using LLMs for some time now and they’ve been getting better and better but the difference between each version has gotten smaller and smaller (it seems like to me).Anthropic made Mythos super exclusive because it is “too powerful” and released a new generation of their AI models under, not just a new version, but under an entirely new name when it feels like just a new iteration.Is...
Some people have more of everything than they’ll use in 10,000 lifetimes, others have not enough to pay for their AIDS medication to allow them to survive into their 30’s and beyond.
Why not take some from the people who have more than enough for 10,000 life times to give to others so they can not die to a disease that’s practically curable (AIDS)?
I feel EVs at this moment are right at the level of “I’m gonna buy a new car, but maybe I’ll wait for the one after before I jump into an EV”. Better batteries (solid state), better charging speeds and more fast charger availability seem to have a large group of people waiting.
https://www.thelancet.com/journals/lancet/article/PIIS0140-6...
Usually quotes are used to question something another person or other people say so I would think you’d quote “classics” or “classics of American literature” to question this story actually being a classic as many other people might say.
Putting quotes on the word “the” in this context seems to be for emphasis and I’ve seen this numerous times with non-native speakers.
If you are a native speaker I don’t mean to be rude, I’m just curious.
I think they’re okay with someone using their API with anything, including OpenCode.
Please someone correct me if I’m wrong.
I want my interfacing with computers to be mouseless and TUIs offer that. I don’t think I’ve run into a GUI, no matter how many hotkeys it has and I know, where I didn’t have to reach for the mouse.
CLI only also requires remembering commands, some of which I use very infrequently, thus need to look up every time I use them.
I think TUIs hold a very nice spot between GUIs and CLI.
I did this time. I enjoyed reading this.
I try to write whatever code, let’s say a function, by hand. It probably won’t work so I just have the LLM Socraticaly ask me questions about why it’s not working and then I try to fix it by hand and keep repeating this until the function works and does what I want.
If there is some more difficult to understand concept I write a small article to try to explain it and have the LLM explain me though my trial and error of writing until my paragraph or essay or whatever amount of writing needed to explain what I’m trying to learn is complete.