Friend/foe individual writers on Hacker News
Friend/foe individual writers on Hacker News
This is also the best approach I've found thus far when I'm seeing how well LLMs can form narrative content.I don't frame its prompt as antagonistic though - I've found in the past (with weaker models, so YMMV) that this can be overly officious, sometimes blocking more creative outputs that you'd want to retain.The structure I've found that works best is to have six or seven agents chained, each roughly mimicking a part of the mind, or a role in film production. Broadly:- A high-temp "Id" agent,view on HN →
Hey Simon, I noticed one thing all LLMs are currently pretty bad at and maybe we could create a benchmark from it. Let an LLM play the role of a dungeon master and tell it to strictly stay in the script/story and only allow realistic player actions. You will notice that they are easily brought off track.E.g.- Tell the LLM that you as a player noticed a strange glow in an NPCs eyes -> the NPC becomes an enemy.- In a fight, tell the LLM you put a sausage (or cigar or something) into the enemies moview on HN →
I do highly unusual, off the beaten path projects with AI.For instance, a game engine written entirely in LuaJIT, but allocating almost all data structures using CFFI, a very unusual, custom object-orientation DSL I designed myself, and that uses SDL3's SDL_gpu library to do all rendering, a ton of GLSL 4.6 compute shaders cross compiled to SPIR-V and Metal (which constraints what GLSL can be written), and is a hybrid tile-oriented and 3D engine.Another example is my Emacs-like live-modifiable iview on HN →
Some sly marketing by Elon. What looks like a gift actually adds to his pocketbook. The agent is free but it runs on his paid models by default, so every task it does spends tokens with him.view on HN →
> This was never about money for him, but about control over a key technologyThat's too flattering. It's about ego.view on HN →
Easy he constantly forces them to cut corners and take risks put their lives in danger "Tesla Has Highest Fatal Accident Rate of All Auto Brands", "Reuters documented at least 600 previously unreported workplace injuries at Musk’s rocket company: crushed limbs, amputations, electrocutions, head and eye wounds and one death. "view on HN →
Musk itself doesn't make things. He only puts the money, and other people build the things. How many times, they need to work around him or fix his crazy ideas ?People must stop trying to compare it to Tesla or Tony Stark. He is more like the bad guy of Jurassic Park 2.view on HN →
You misunderstand Musk's motivation. This was never about money for him, but about control over a key technology. One of the main reasons he exited OpenAI was the fact that the other co-founders wanted to create a structure where no one, Musk included, would be able to seize full control of the company. That was the thing that prompted him to leave, which tells you a lot about what he really wanted in the first place.But he also falsely assumed that OAI would die without his money. Yet, they manview on HN →
It’s a shame that their leader exfiltrated government data.view on HN →
"Grok 4.5 has an advantage on CursorBench because an earlier snapshot of the Cursor codebase was accidentally included in training. The exact impact is unclear. That data has been removed for future models, and in parallel we are working on a larger update to CursorBench, hence the exclusion here."Not enough people are noticing this, they juiced the benchesview on HN →
Hacker Smacker — Friend and foe writers on Hacker News