Researchers asked frontier models to play chess. Have a look at the MAR rates in Table 3. When not explicitly told which moves were legal, no model identified legal moves at a rate better than 80%. Many asked for more illegal moves than legal moves. And even when explicitly told which moves were legal, the models continued to ask for illegal moves. With illegal asks discarded, none of the bots could beat a chess model calibrated to 1100 ELO.
The author of the originating post says that "current frontier models need laborious oversight and guardrails on even the simplest tasks", and he's absolutely correct.
> Gemini 2.5 Pro, O3, Claude Sonnet 3.7 and ChatGPT 4.1
The gap in capabilities between those models which they tested, and actual current frontier ones is enormous. I would not trust that any conclusions they made are applicable.
> The gap in capabilities between those models which they tested, and actual current frontier ones is enormous.
Same story every 4 months and yet still no breakout, winning products. I've been hearing "the AI is good now" and "it 10x's my productivity" for a over a year now. If it were true, why aren't the all-in-AI using companies 10-15 years ahead of their competition yet? Why is it still all buggy, poorly designed junk?
I don't get why it is hard to understand there is middle ground. People are 10x their productivity, it isn't all buggy junk, but it isn't all it is hyped up to be either. It isn't that complicated.
If you hold the extreme position that there isn't any value in this, that's fine, but we're only having this discussion because these models have done what humans previously failed to do.
I don't think the poster disagrees with you at all. The middle ground is that there are no breakout products and that the models clearly aren't so powerful as to make these companies not produce shit code.
carodgers · · focus · HN ↗
<a href="https://arxiv.org/html/2509.24239v4" rel="nofollow">https://arxiv.org/html/2509.24239v4
Researchers asked frontier models to play chess. Have a look at the MAR rates in Table 3. When not explicitly told which moves were legal, no model identified legal moves at a rate better than 80%. Many asked for more illegal moves than legal moves. And even when explicitly told which moves were legal, the models continued to ask for illegal moves. With illegal asks discarded, none of the bots could beat a chess model calibrated to 1100 ELO.
The author of the originating post says that "current frontier models need laborious oversight and guardrails on even the simplest tasks", and he's absolutely correct.
joefourier · · focus · HN ↗
> Gemini 2.5 Pro, O3, Claude Sonnet 3.7 and ChatGPT 4.1
The gap in capabilities between those models which they tested, and actual current frontier ones is enormous. I would not trust that any conclusions they made are applicable.
moron4hire · · focus · HN ↗
Same story every 4 months and yet still no breakout, winning products. I've been hearing "the AI is good now" and "it 10x's my productivity" for a over a year now. If it were true, why aren't the all-in-AI using companies 10-15 years ahead of their competition yet? Why is it still all buggy, poorly designed junk?
orangedog · · focus · HN ↗
If you hold the extreme position that there isn't any value in this, that's fine, but we're only having this discussion because these models have done what humans previously failed to do.
freejazz · · focus · HN ↗