Aditya_Garg
Aditya_Garg on Hacker News
Jev is so cheap I dont see anyone undercutting them on price. If people/products start using Jev underneath before the incumbents can release something then most likely everyone's jsut gonna stay with Jev
I believe if you're are not willing to back up your opinion with skin in the game then its low value opinion.
Feel free to explain it to me
This is really really cool man
OP is blatantly overconfident on his "prediction", so I called him out. Looks like I struck a nerve with some people.
Shorting bitcoin would be a huge mistake IMO. Willing to be on the opposite of that trade as well!
OP sounds way too confident about the general direction so Im calling him out to take some action on his "insight"
Buying out of money puts with expiration a few years out on AI adjacent stocks should do the trick
Willing to enter a private trade with you if you're actually willing to put up the money
Are you willing to short anthropic and openai on your beliefs? Would love to be on the other side of this trade.
Im really curious about this. Why pay API pricing? I burn 1000s of dollars a month of api according to claude usage but only pay the $100 subscription
yes its ridiculously good at stuff like that now. I dare you to try and trick it.
I’ve said this many times before
AI is just a tool
If you used a fancy auto bake cake machine instead of an oven, you still get to claim that you made the cake.
100 years ago someone would be making the claim that using an oven to make cakes “doesn’t count”
All AI did was raise the bar
It’s quite clear here that the author spent a lot of time on this so he absolutely gets credit as the author
losers, clueless never had to be productive, just scapegoats. But now losers dont get that buffer window to try and become sociopaths, they just dont get hired at all.
Wild stuff and great read
Do you think karpathy's autoresearch would be useful here?
This is a common misconception
OpenAI and others are already profitable on inference (inference is really really cheap)
They are just heavily investing into the latest frontier
The biggest risk is whether they can stay cutting edge, or if open source or others will catch up quickly.
Pretty cool
Your goal.md examples are all features for the existing codebase. Any largish goal.md examples where your system is able to 1 shot a pretty large app?
The goal.md is what makes this thing either amazing or terrible for the user, so any guidelines or clear examples on writing a good one would go a long way.
This is insane man, great work. Video within video blew my mind
Could you push it even further? If I zoom into that smaller video then its made of even smaller videos?
Infini video zoom
It absolutely can be a vm. Someone even got it running on a 2 dollar esp32. Its just making api calls
You just described the ralph loop, and its incredibly effective. Compaction is on the way out
Amazing read! Is it possible to do something like this but for wall street raider?
https://labs.ramp.com/rct
"claude code plays wall street raider" would be very very cool.
I tried codex on a whim when my Claude code rate limited me. Canceled my max subscription and stuck with codex
Yeah I’ve noticed the same problem. Do you know any resources for writing good specs?
Anthropic themselves were able to write a c compiler using teams all at the same time
https://www.anthropic.com/engineering/building-c-compiler
Here is the relevant excerpt:
"To prevent two agents from trying to solve the same problem at the same time, the harness uses a simple synchronization algorithm:
Claude takes a "lock" on a task by writing a text file to current_tasks/ (e.g., one agent might lock current_tasks/parse_if_statement.txt, while another locks current_tasks/codegen_function_definition.txt). If two agents try to claim the same task, git's synchronization forces the second agent to pick a different one.
Claude works on the task, then pulls from upstream, merges changes from other agents, pushes its changes, and removes the lock. Merge conflicts are frequent, but Claude is smart enough to figure that out."
Very very cool. Going to try this out on some of my codebases. Do you have the gist that helps the agent populate the mindmap for an existing codebase? Your pastebin mentions it, but I dont see it linked anywhere.
In Thailand, you can live very very comfortably for 25k.