131–140 of 145 posts
Earlier quoted context omitted.
I usually see doom loops when working with quants. Likely theyre trying to maximize the viability of a efficient model quant that can bw upgraded. Like cutting coke to get crack, quantiry over quality.
Nit pick; cutting (adulterating) cocaine doesn't produce crack cocaine.
Funny how all china companies are expected to release weights by default
All smaller models and models behind frontier are expected to be released by default. Otherwise there’s no reason to produce them. Chinese labs are not releasing all of their model weights. Qwen is known as an open weight model by most, but their top model is not open weight. Releasing weights is a marketing strategy for newer labs to get their brand out there.
Earlier quoted context omitted.
Doom loops are as much of a model problem as it is deficiency of the harness. I have not seen any other open source harness that deals with them except the one I started because of this obvious gap. See my other comment with examples where 0x Alpha is working non-stop on various projects with zero problems.
How do you recover from doom loops? Just send the same prompt again and pray that it works, or anything more sophisticated?
Only reason people are interested is it’s free at the moment. I wasn’t impressed by its performance. Once the model gets a price tag it’s usage will be negligible.
The price is free for some of us, we can run it at home.
Mixed signals, here it's performing below even GPT-5.4 Nano: https://livebench.ai/ while here it outperforms Fable by a significant margin: https://oxalpha.com/ but if the latter is true, will people still say it was "distilled" from Fable?
I had Ox Alpha working on coding tasks for a couple days non-stop, via OpenRouter and OpenCode Zen. Crush harness. It was able to complete tasks at a level that I'd put between Sonnet and Opus. It makes few mistakes, but is not that smart. The main issue for me, is that it degraded into a doom loop several times. One of them was running the same bash command about a thousand times. The last model I've used that had t…
I know that AI is moving fast, but Mimo 2.5 literally came out four months ago. I literally had to double-check after I read this because it felt like just yesterday.
Also, I'm not sure what the industry standard is right now, but my (self-built) harness automatically exits with an error code whenever it detects similar tool calls being sent or when semantic repetition in the reasoning traces reaches a certain threshold. It's pretty easy to set that kind of thing up.
I had Ox Alpha working on coding tasks for a couple days non-stop, via OpenRouter and OpenCode Zen. Crush harness. It was able to complete tasks at a level that I'd put between Sonnet and Opus. It makes few mistakes, but is not that smart. The main issue for me, is that it degraded into a doom loop several times. One of them was running the same bash command about a thousand times. The last model I've used that had t…
Earlier quoted context omitted.
Well, i don't see demands from people to release chatgpt 4o.
It's funny that you chose the exactly model that has a huge fanbase asking for it to be added back. ChatGPT 4o got a lot of people addicted. https://mashable.com/article/chatgpt-gpt-4o-ai-retirement-pr...
Earlier quoted context omitted.
The price is free for some of us, we can run it at home.
How much did you spend on hardware and electricity to run your free models