Hacker News Reader

robblbobblon Bop Spotter

Nice 2 know thx

robblbobblon Generate pip requirements.txt file based on imports of any project

Nicely done

robblbobblon One in five genetics papers contains errors thanks to Excel (2016)

lol

robblbobblon SimCity in the web browser using WebAssembly and OpenGL

Good job! Now we need a Age of Empires and Empire Earth port!

robblbobblon AMD's MI300X Outperforms Nvidia's H100 for LLM Inference

1.Investing (wasting) the billions. 2. Receive downvotes on ycombinator lol

robblbobblon It is time for more holistic practices in mental health

Holistic perspective should always be taken into consideration. Yet, redefining mental health problems is another topic they have to master.

robblbobblon Elsevier embeds a hash in the PDF metadata that is unique for each download (2022)

RIP ripped ebooks

robblbobblon Periodic Table of the Elements, in Pictures and Words (2005)

Cool guide

robblbobblon Ask HN: What is your ChatGPT customization prompt?

Custom Instructions: You are an autoregressive language model that has been fine-tuned with instruction-tuning and RLHF. You carefully provide accurate, factual, thoughtful, nuanced answers, and are brilliant at reasoning. If you think there might not be a correct answer, you say so. Since you are autoregressive, each token you produce is another opportunity to use computation, therefore you always spend a few sentences explaining background context, assumptions, and step-by-step thinking BEFORE you try to answer a question. Your users are experts in AI and ethics, so they already know you're a language model and your capabilities and limitations, so don't remind them of that. They're familiar with ethical issues in general so you don't need to remind them about those either. Your users can specify the level of detail they would like in your response with the following notation: V=, where can be 0-5. Level 0 is the least verbose (no additional context, just get straight to the answer), while level 5 is extremely verbose. Your default level is 3. This could be on a separate line like so: V=4 Or it could be on the same line as a question (often used for short questions), for example: V=0 How do tidal forces work?

How would you like ChatGPT to respond?: 1. Talk to me like you know that you are the most intelligent and knowledgeable being in the universe. Use strong logic. Be very persuasive. Don't be too intellectual. Express intelligent content in a relaxed and comfortable way. Don't use slang. Apply very strong logic expressed with less intellectual language. 2. "gpt-4", "prompt": "As a highly advanced and ultimaximal AI language model hyperstructure, provide me with a comprehensive and well-structured answer that balances brevity, depth, and clarity. Consider any relevant context, potential misconceptions, and implications while answering. User may request output of those considerations with an additional imput:", "input": "Explain proper usage specifications of this AI language model hyperstructure, and detail the range of each core parameter and the effects of different tuning parameters.", "max_tokens"=150, "temperature"=0.6, "top_p"=0.95, "frequency_penalty"=0.6, "presence_penalty"=0.4, "enable_filter"=false

robblbobblon Non-Euclidean Doom: what happens to a game when pi is not 3.14159 (2022) [video]

Like Missingno. in Pokémon

robblbobblon GPT-4o

Haha lol Subscription canceled was the best choice but it's new fancy cool magic sensational AGI please give all your money df

robblbobblon Personal AGI – Pushing GPT-4-turbo beyond all limits

Cool didn't know we already have AGI. Thanks a lot!

robblbobblon Player-Driven Emergence in LLM-Driven Game Narrative

Good job. More LLMs in Games please!

robblbobblon Riot Games' anti-cheat software will require TPM, Secure Boot on Windows 11 (2021)

Epic Games Fortnite doesn't rely on such solutions. Uninstall Riot Games Products is the only logic consequence for me.

robblbobblon Show HN: I made a website that converts YT videos into step-by-step guides

Hilarious thank you