I'm curious if you can have a judge XYZ skill where you have an ai analyze how that judge ruled for certain judgements in the past, and how similar lawsuits/arguments did in front of them. Might help to angle the ai's findings a tad, or might also not be worth the effort. Both are possible
> mostly stuff that works for humans also works for AIs but you need to know to ask for it
I'm most curious about this sentence. What have you noticed about the similarities? I'm getting really good at asking for confidence levels, tests and pushing back, but I'm curious what you found
Where does discussion on gut training occur? All I know is you need a 5:4 ratio of glucose to fructose? Then when you train, you use the gels and the more you do it, the more capable your gut gets at absorbing without distress.
I agree. Gemini models are held back by their segmentation of usage between multiple products, combined with their awful harnesses and tooling. Gemini cli, antigravity, Gemini code assist, Jules.... The list goes on. Each of these products has only a small limit and they must share usage.
It gets worse than that though. Most harnesses that are made to handle codex and Claude cannot handle Gemini 3.1 correctly. Google has trained Gemini 3.1 to return different json keys than most harnesses expect resulting in awful results and failure. (Based on me perusing multiple harness GitHub issues after Gemini 3.1 came out)
They likely already have. You can use all caps and yell at Claude and it'll react normally, while doing do so with chatgpt scares it, resulting in timid answers
I think my next steps are:
1) try out openai $20/month. I've heard they're much more generous.
2) try out open router free models. I don't need geniuses, so long as I can see the thinking (something that Claude code obfuscates by default) I should be good. I've heard good things about the CLIO harness and want to try openrouter+clio
I used it to speed up an codecompass-like repo from 86 files per second to 2000. Still haven't used the repo in production, so maybe it secretly broke things, but the ability to say: "optimize this benchmark and commit only if you pass these tests" is nice
Jane Street had a cool video about how you can address lack of training data in a programming language using llm patching. Video is called "Arjun Guha: How Language Models Model Programming Languages & How Programmers Model Language Models"
The big take away is that you can "patch" llms and steer them to correct answers in less trained programming languages, allowing for superior performance. Might work here. Not a clue how to implement, but stuff to llm-to-doc and the like makes me hopeful