A\ and OpenAI each have their own unique kind of nonsense. I think OpenAI has just been less successful with persuading the rest of the world that they should have all the money in the world.
Anthropic has been surprisingly successful at convincing them that they should control frontier models because they're so dangerous that... only Anthropic can be trusted with them.
(If they're really so dangerous, the right way to deal with them is through a democratic process and taking them out of the hands of a for-profit private entity.)
A democratic process, of sorts, elected the current government of the United States. The president even won the popular vote this round. There is no guarantee that AI guidance by democratic process will be an effective counter to corporate autocracy; and more realistically, AI guidance by an autocratic executive branch is the more likely alternative before 2029.
Right - the idea that "bigger model = better" might have been true a year ago, but the flash models are extremely effective right now. You simply use them for the tasks they are ideally suited for.
An LLM which provides an OpenAI or Anthropic API-compatible interface + a coding harness like OpenCode or oh-my-pi is a pretty easy "ecosystem" to replicate. Exactly what makes you say Fable or Mythos are "systems, not just pure models"?
Fable can delegate tasks to Opus or Sonnet, so it has some agentic properties and I believe it does them in parallel.
The parallelism is where this starts to fall apart on a local PC. Like I can run some Qwen quants, but I can’t run a decent Qwen model while also running another model smart enough to actually implement it. I’d have to do them in series, and given how long Fable seems to take even with parallelism, I’d probably be waiting days for an answer.
oh-my-pi can delegate tasks to other models too. I usually use DS4 Flash for low priority subagent tasks.
If Fable is "delegating" tasks, then there's actually an agent front end of whatever you think the API is.
We have a local instance of Qwen-3.6 which is more than adequate for running agents. You can mix and match local and cloud-hosted models. (My biggest use case for local models right now is vision models because they're quite small and I can avoid some data-locality issues my customers wouldn't be comfortable with if I sen them to a Chinese model.)
> If Fable is "delegating" tasks, then there's actually an agent front end of whatever you think the API is.
I would say behind (I believe you use the API just like you do Opus), but yeah. I'm not claiming it's a property of the LLM itself, I also presume this is some variety of tool calling agent harness.
> We have a local instance of Qwen-3.6 which is more than adequate for running agents. You can mix and match local and cloud-hosted models.
I'm presuming OP meant local as in the models run locally as well. I do know you can do subagents in Pi (probably others too), but the vast majority of people are going to hit hardware limitations trying to run them in parallel on local hardware.
I'm doubtful Fable's harness is unique in some way that you can't replicate with Pi. I'm mostly doubtful there are more than a handful of people with hardware sitting in their house that can execute more than one meaningfully smart model at a time.
If you're on local hardware, Deepseek v4 Flash is in the ballpark of 180GB of VRAM alone. Even on smaller models, Qwen + a dumber agent to execute is probably in the realm of 60GB of VRAM.
I do suspect you could get Deepseek to do Fable level things with a good harness (or a bunch of models really, I'm fairly convinced the magic of Fable is in the harness rather than the model).
Anthropic's plans are based on user experience of usage, not raw token counts, so you get to run through so many conversation turns, etc. within a 5 hour usage window. (Cursor, OpenCode Go, and others are similar.)
Cursor's $20 a month plan provides a reasonable amount of Opus tokens as well.
One of the first things I do before spending time with a coding agent on generating something is having a pretty long reasoning session where I pressure the agent to find out if the problem I'm solving has been solved before, at all, in any way. Most of the time, it has, and it probably doesn't have utility beyond my own personal education in solving it again.
That seems to be what most of these projects that get accused of being "vibe coded" are doing. Incidentally - there's nothing wrong with writing your own useful utilities, and educational to package these up for distribution/release, but don't be surprised if not another soul in the world finds the particular need you had to be one they share.
The one they ended up going “well I guess we’ll contract with them after all”, after cleverly using their sort-of-refusal to gain a ton of goodwill and new customers?
Anthropic has been surprisingly successful at convincing them that they should control frontier models because they're so dangerous that... only Anthropic can be trusted with them.
(If they're really so dangerous, the right way to deal with them is through a democratic process and taking them out of the hands of a for-profit private entity.)
reply