Yeah that's a good idea. I played around with kimi2.5/gemini in a similar way and it's solid for the price. It would be pretty easy to build some skills out and delegate heavy lifting to better models without managing it yourself I think. This has all been driven by anthropic's shenanigans (I cancelled my max sub after almost a year both because of the opencode thing and them consistently nerfing everything for weeks to keep up the arms race.)
Yeah I did the same (cancel Anthropic). Mainly because the buggy/bloatiness of their tooling pissed me off and I got annoyed by Dario's public pronouncements (not that SamA is any better).
I ended up impressed enough w/ GPT 5.3 that I did the $200 for this month, but only because I can probably write-off as business expense in next year's accounting.
Next month I'll probably do what I just said: $20 each to OpenAI and Google for GPT 5.3 and Gemini 3 [only because it gets me drive and photo storage], buy the z.AI plan, and only use GPT for nitty gritty analysis heavy work and review and GLM for everything else.
Cancelled my Anthropic subscription this week after about 18 months of membership. Usage limits have dropped drastically (or token usage have increased) to the point where it's unusable.
Codex + Z.ai combined is the same price, has far higher usage limits and just as good.
Lol wat? I mean you certainly have enough control self hosting the model to not let it join some moltbot network... or what exactly are you saying would happen?
We just saw last week people are setting up moltbots with virtually no knowledge of what it has and doesn't have access. The scenario that i'm afraid of is China realizes the potential of this. They can add training to the models commonly used for assistants. They act normal, are helpful, everything you'd want a bot to do. But maybe once in a while it checks moltbook or some other endpoint China controls for a trigger word. When it sees that, it kicks into a completely different mode, maybe it writes a script to DDoS targets of interest, maybe it mines your email for useful information, maybe the user has credentials to some piece that is a critical component of an important supply chain. This is not a wild scenario, no new sci-fi technology would need to be invented. Everything to do it is available today, people are configuring it, and using it like this today. The part that I fear is if it is running locally, you can't just shut off API access and kill the threat. It's running on it's own server, it's own model. You have to cut off each node.
Big fan of AI, I use local models A LOT. I do think we have to take threats like this seriously. I don't Think it's a wild scifi idea. Since WW2, civilians have been as much of an equal opportunity target as a soldier, war is about logistics, and civilians supply the military.
Fair point but I would be more worried about the US government doing this kind of thing to act against US citizens than the Chinese government doing it.
I think we're in a brief period of relative freedom where deep engineering topics can be discussed with AI agents even though they have potential uses in weapons systems. Imagine asking chat gpt how to build a fertilizer bomb, but apply the same censorship to anything related to computer vision, lasers, drone coordination, etc.
I'm using an openAI realtime voice with livekit, and they said they have a livekit integration so it would probably be doable that way. I haven't used video in livekit though and I don't know how the plugins are setup for it
I see some chess players so I want to plug the chess coaching app [0] I'm building. I don't know many chess players and could use feedback, but I had been paying for chess.com premium and tried some others and it's always game-level feedback which is insane to me because it's really not that helpful (as evidenced by my abysmal rating.)
I'm running games through stockfish/lc0/Maia and doing some analysis of patterns across multiple games, then feeding that to an agent who can replay through positions and some other fun stuff. Really keen to find out if it's helpful for anyone else!
I'm going to check this out, as it's legitimately attempting to solve the gap in online chess coaches. As said on the home page, I don't want to know what to play, I want to know why I'm not seeing it or how to think about the move differently. This is the gap and I hope you find success. I'm definitely going to check it out.
But to ask, did you consider "chessfriend" instead of "chessfiend" for branding? "fiend" can carry a negative connotation, which I'm not particularly lining up with in your product.
I hadn't considered that name specifically but I'm not married to the branding! I appreciate that feedback and your other comment validating I'm not the only person with this problem. Happy to chat more via email (in bio)
I wanted to check it out.
After login I am immediately redirected to a page asking for $80/year without me even understanding what the service does.
Unrealistic expectation. Show me value first, ask for money later
I have a lot more to optimize before I'm crunching down the positions but I just made a chess platform[0] with the intention of tracking your play style over many games (integrated with chess.com only for now) because the other ones I've used (including chess.com somehow) only really analyze a game at a time. It was a lot of fun to build and it's been really useful for me to identify some weaknesses and have a 'coach' to talk through them with and replay positions. I'd love feedback from any chess players! (email is in my bio)
It's worth checking the spam score if its a new domain and see if there's anything on the internet archive. I learned this the hard way and now I check before buying
It's really amazing. One of the greatest experiences of my life was diving at night in a bioluminescent cove. I turned off my torch and the glow from my dive buddy's finning afforded all the viz I needed. Diving always feels so viscerally otherworldly but never quite as much as it did in that moment.
I noticed railway being slow then got an error message saying deployments are paused with a nice upgrade to pro button. Status says it's fixed but still only for pro. I'm a paying user, but I guess not enough.
The vast majority of English speakers do not live in the US or the UK. English is the most widely spoken language in the world. If you are at dinner with people from several countries, the "Lingua Franca" will almost certainly be English.
The popularity of Mandarin relies on the sheer mass of native speakers in China. That population is shrinking and that shrinking is expected to accelerate. The cultural export of China is inherently limited by its ideology - there's a reason we have (had, really) "Hong Kong Cinema" not "Peking Cinema".
All Japanese people learn English at school; few learn Chinese as you can verify by reading about the Japanese school system from various sources including Wikipedia.
Similarly in China, English is the only mandatory foreign language taught at school.
Frequently, Chinese or Japanese. For example companies in these countries employ translators. Are you suggesting they rely on primary school-level English to negotiate?
You claimed, without a source other than wikipedia, that everyone in Japan learns English in school. I see this [0] on wikipedia which says "a select number of public primary schools ... have mandatory English classes"
Ionic uses capacitor for native deployment. Capacitor is a thin cli wrapper and an api abstraction around each platform. In the desktop case, it’s a wrapper around Electron. For mobile, it’s Cordova.
reply