They've got an openai + anthropic compatible endpoints. I got far enough to run some tests on the openai endpoint, albeit with some finagling (their /models list is empty, my tool auto-configures using that, was an initial stumble).
Thanks! I found the OpenAI-compatible endpoint and got it working. I ran Inkling on a couple of my own evals. It looks promising, but on my cases it still fell short of GPT-5.4 and GPT-5.6 Luna.
This is the best voice/tone I've seen from any model so far. It's using filler words and phrases in places that normal people would put them, rather than sounding like a corporate customer support agent!
what model did you try it with? I agree and also push back a bit: How will we know when the LLMs reach the point of handling it if no one takes the leap? I applaud more people sludging through the slop and hauling their slop buckets around.
An example is Fable being released. I felt like the most complex thing I was willing to sludge through was having it clone llama-server's web UI with my own opinions (I really like the original, kudos to them). And the initial skeleton was working so well I felt like I had sunk the tokens and committed to getting it the rest of the way: https://inkcap.click
I'll agree and expand on "weird restrictions" -- I used to check the claude usage graphs multiple times a day to see where I'm at on my weekly budget. With gpt 5.5 I don't think I'm working differently but haven't felt the need to check anything because I think I've hit my limit... once? on some egregious edge case scenario iirc
Same here - it's probably that OpenAI needs to buy goodwill with developers to infiltrate corps and Anthropic is trying to squeeze the lead into revenue. The only question is - how much longer can OpenAI burn money before it needs to start showing signs of profitability
Probably not _as_ good, but you can run gemma 4 for the ears/brain (accepts audio input), and kokoro TTS for the mouth. You want something like silero VAD sitting in front of the LLM so you aren't passing wasteful audio to gemma 4, so you send only voice activity segments. I type all this because I tried it out recently as a Zork experience, seeing how creative Gemma 4 12B could be. It was surprisingly good!
Yeah, I mostly mean for the TTS, which in my testing is flat and has no emotional register, or no nuanced variation. OpenAI speech in my experience is very good at things like communicating understanding or questions non-verbally using intonation, and I'm yet to see a local TTS model that will do contextual intonation well at all.
The best project I found to throw it at was cloning llama-server's web UI essentially in one shot. I'm not sure what I'll do with 5 extra days, maybe try to imagine some complex features. I'm no longer surprised at how much seems to work in these "new brain what can it do?" test, and instead think the risk is feeling like I have to take it the rest of the way once I've sunk the token cost :| https://inkcap.click
Yeah, I've been quite skeptical of LLMs, but I was wrong. The new models are capable of generating good quality code reasonably reliably. They still do some dumb things, but it's becoming more capable of one-shotting non-trivial stuff. I've no idea what software development will look like in a decade beyond absolutely nothing whatsoever what it looks like today. Even if we get sublinear progress from now on out, the current SOTA is already enough to redefine coding.
In general I expect the value of software, as a thing in and of itself, to sharply decline. With no barriers to entry, having software that just does something competently will no longer be worth much of anything. It's unclear what that will mean in the bigger picture. It'll also be interesting if this proves correct, given that software companies are largely the ones dumping so much money into this. Another probable outcome is major damage to the support-as-a-service model which again is going to directly affect many of the companies directly enabling this.
I guess the logic is that if you control the systems creating this, you control everything they're used for. But it seems equally obvious that free/local models will catch up to the SOTA today - and eventually tomorrow, so that's not a particularly realistic vision for the future.
Lately I've been following https://loco.rs/ as it aims for a rails-like experience, complete with generators for workers, controllers, etc. I've only had time to experiment but it's the closest I've gotten to feeling rails-y in rust.
reply