Viewing profile — carsoon

Yeah I do not see an alternative way to easily copy paste links with things like filter settings saved. Filters especially make sense as query params as they are non sequential but…

I saw a waymo go in a nonexistent rightmost lane at a stop light, I thought it was going to turn but it instead proceeded to go forward and force the driver in the actual rightmost…

You can buy IR and UV leds. All high end grow lights have these for plants. Low quality cheap led products won't include them but that is nothing to do with LEDs themselves that is…

Fully sandboxed VMs are more secure but not everyone is looking for the most secure option. They are looking for the option that works the best for them. I want to be able to share…

Those prior recommendations you supplied are worse than the current ones. Added Sugar: it says Fat: it says to choose low fat cuts 95% and low fat milk. There is no basis for these…

If you refresh it changes, thats what the llm thinks it looks like I guess haha.

I made an simulation where you get to be a priest in a confessional booth and different LLMs will confess mistakes they made in moral situations and you get to forgive them. Inspir…

I built it, now you can forgive all the llms for their misdeeds: https://llmpriest.carsho.dev/ https://news.ycombinator.com/item?id=46251110

We could first put the LLMs in very difficult situations like the trolley problem and other variants of this, then once they make their decisions they can explain to us how their c…

These models don't even choose 1 outcome. They list probabilities of ALL the tokens outcomes and the backend program decides to choose the one that is most probable OR a different …

I have a kinda strange chatgpt personalization prompt but it's been working well for me. The focus is me to get the model to analyze 2 sides and the extremes on both ends so it exp…

Yeah I have seen multiple people use this certainty % thing but its terrible. A percentage is something calculated mathemtatically and these models cannot do that. Potentially they…

I think even when this is used they should include "(translated by llm)" for transparency. When you use a intermediate layer there is always bias. I've written blog articles using …

Its definitely a mix, we have been codeveloping better models and frameworks/systems to improve the outputs. Now we have llms.txt, MCP servers, structured outputs, better context m…

Yeah this latest generation of models (Opus 4.5 GPT 5.1 and Gemini Pro 3) are the biggest breakthrough since gpt-4o in my mind. Before it felt like they were good for very specific…

I think the big cost difference is the geothermal generators to convert the heat back into electricity. More of a cost issue versus efficiency.

No, it wouldn't as the whole reason people were giving Openai that 500 dollars is because they thought they could make more than 500 dollars from it. So now that value is just shif…

People don't stop wanting things. Total GDP can keep rising so long as technologist can improve efficiency through robotics, inventions and scientific breakthroughs. GDP just descr…

The problem with suicidal depression is that if someone has created the thought pattern that death is best, then removing the symptoms of depression (lethargy, lack of energy, no w…

Everyone introduces bias. But for instance getting a model trained pre war vs after a war starts is super different. If I want to get raw information about 2 nations then models ar…

The problem is they have to hide their sources due to copyright. So they train on copyright data but must obscure it in the output. Thus they must hide the sources of truth making …

For instance I want information about 2 countries currently at war. By asking about these countries from an older model then we get more factual information about the countries. If…

I don't understand how people use or got used to using em dahshes? How do you even type them? theres no button for it so are you manually inserting, copy pasting it and why not jus…