[steve_adams_86]

It’s nice to have access again, but I’m hesitant to include it in my workflow now. In fact I’d rather not use American models at all if I could.

I have the sense that this limited usage model will persist, Opus at its current token price will gradually be phased out, and eventually the cost of these models will be unsustainable and impractical.

I’d rather not play this game anymore and seek out more reliable providers which may provide less capable models but aren’t going to gradually kneecap my plan or rug-pull me.

Frankly I’m much less concerned with sheer model capability these days and more interested in harnesses. Claude Code is not the best on the market, and I think there’s a lot of exploring and learning to do in that arena.

The whole Fable debacle has dramatically changed my perspective on the market and what I want from it/who I should support.

[arjie]

Was there a use-case where you deployed Fable where you couldn’t use Opus in a non-interactive case? Perhaps Sonnet 5 will fill the gap because it’s better in agentic loops.

It’s so expensive, though. Useful interactively in coding agent but boy if you have a kind of task that Fable can do in an agentic loop that Opus can’t then you’re in a good place. Doubtless the frontier will move forward. These kinds of “problems of the future” are great to have solutions for.

And for an interactive agentic loop, not using Fable is just missing out on something. There’s no lock-in there.

[nextaccountic]

> more interested in harnesses. Claude Code is not the best on the market

What is the best harness right now?

[jpeeler]

Good question, anybody know? I've seen harnesses optimize for token efficiency (maki), simultaneous agent operations (jcode), extensibility (pi), etc... But I have no idea if each focus area is superior and if the rest of the operations are comparable.

It bothers me that the Claude Code leak (from what I read, didn't look) a few months ago showed a lot of careful consideration for context handling. I assume this means that each harness performance/correctness would differ drastically just from this alone.

[nextaccountic]

Maki seems so cool, thanks for the pointer

[steve_adams_86]

I’m with jpeeler here and I don’t think there’s a single optimum harness. Pi is really nice in that it allows you to hone in on what suits your needs, though. Some people won’t want to manage their harness though, so for them it’s probably not ideal.

All I can say with certainty is that Claude Code isn’t a panacea, and it’s quite buggy and clunky. I think this is evident just from regular usage, but becomes even clearer when you use harnesses that get in the way less and demonstrate better implementations across the board. Sometimes I think Claude Code feels like software that happened while other harnesses feel like they were engineered intentionally.

[gonight]

I agree with this, the last three months have been complete nonsense. I'll take a less capable model with a workflow I know well over playing "what got silently removed this time" or "figure out the latest model's quirks". The behavior of the american AI field/industry this year feels unstable and unsustainable, and I'm personally ready to wash my hands of this and find/build something reliable.

[altmanaltman]

I mean that's the software playbook, get users addicted by offering it cheap and once you have them hooked, you raise the prices. There is no reason to think any non american company wouldn't follow this strategy. It's a different matter than the export control issue entirely and one that is systematic to software in general.

[steve_adams_86]

> There is no reason to think any non american company wouldn't follow this strategy.

This is generally true, but there are some providers offering inference at relatively stable prices. They aren’t Opus-tier models, but some appear to be at or close to Sonnet 4.5 or so. For much of the work I do, this is fine.

Essentially if you aren’t at the frontier, you can find cheaper tokens that aren’t about to be rug-pulled or decommissioned on a whim.

[altmanaltman]

> there are some providers offering inference at relatively stable prices

for now. Once they get enough customers, why will they not jack up prices is my point.

All businesses will act in that manner because it serves their interests. That is not going to change if you're OpenAI or ChineseAI or BelgiumAI.

Again, this is different from the export control issue because it's a fundamental business thing.

You will always want more money from customers not less and there is no noble business that exists just to make your tokens cheap while they give up potential profits unless they have something to gain from tokens being cheap.

They will gradually up their prices as well and squeeze as much as they can like most first-gen AI providers are gradually doing since they got a lot of people hooked already.

[zarzavat]

Don't worry, now that Fable is freely available, a Chinese distill will be out a few months from now. To riff on Musk, the US AI industry is the bootloader for the Chinese AI industry.