bethekind

> Without any Pokémon-specific optimization, Step 5 Preview has so far sustained progress for more than 3,000 turns and 6 million tokens of interaction. By turn 3,082, it had unlocked Cut, earned three Gym Badges, and defeated Lt. Surge. The run is now roughly one-third of the way through the main story.

Finally FireRed is being used as a benchmark again! I believe Astra can beat it in 18 hours. Not sure how that compares.

> They identified two different brain progenitor cells. One, which expresses a gene called Otx2, is destined to become the forebrain and midbrain. The other, which expresses a gene called Gbx2, is committed to forming the hindbrain. They showed that these two cell populations never overlap; they are mutually exclusive from the earliest stages of development.

Very cool. Never thought the brain could have two completely different ancestors

> I think it's really difficult for the AI agents to tell what is crazy and what isn't, so they are picking up this insane culture. (^▽^) I think you're right...next 5 years are going to be one hell of a rollercoaster

Curious do you have this setup or a howto anywhere?

it's an ethereal thing that mr.musk made popular.

Put succinctly, if a mismatch between the timelines of the bonds in the bond markets and the revenue streams occurs, it's a bubble. This increases the risk to current and future AI investments and buildouts. If the mismatch is strong enough, contagion in other sectors/areas of the world can cause a run to security and pop the bubble.

Just because the bond markets 1/2/3/5-year bonds are bloated does that mean the bubble will pop. It just increases the risk.

This is really pretty! Going to take a look at it later on.

If you follow motor oil geek on YouTube, they've started changing the formulations of the premium oils months ago and that's not going to change until 2028 when more American supply comes online

Another favorite of fine is asking it read something then to tell me any "questions, comments concerns" it has. Great for getting the jist of articles fast.

RTO4AI should be a slogan. Or some variant thereof

Still a great skill, but at this point, I just write "I have adhd, can you explain that again" or "I have adhd". Works great for compressing it ELI5, but less dumb

Climate change affects geographies unequally. Seems like Europe and the tropics have been the first to suffer, year after year, and with the UK losing that warm current in ~47 years, can't help but wonder what is on European minds.

Learn model deployment, batching, all the AI inference related things?

I'm ignorant. What problems is this good at solving?

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

Which of these has been the most productive for you? Sounds like you've enjoyed the RTX6000 the most?

Use z.ai then. No need to knee jerk react

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.

Is that all the science to it?

Off topic, but this is where I see AI going. A tool that condenses work down from requiring a team and a room to a box. We're decades away from that

My favorite is Brownian motion fractal art. Something about it just tickles my brain just right

Me too

1 client, 1 agent? Interesting

Poolometer looks cool! I will say your smiley face icons look a lil odd and ai generated, but otherwise I love the graph tracking and suggestions

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

This. If I run 4 Claude code opus agents with subagents, my 8gb of RAM just dies.

I know they can do better

I've used Gemini and now claude. Both were meh until I found the superpowers skill. Will be trying chatgpt next month.

You can "feel" the llm being limited with Gemini, less so with Claude. Hopefully even less so with chatgpt

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