daemon_9009
daemon_9009 on Hacker News
LLMs introduce easy to miss bugs in the code, it could be either incomplete context or improper instructions. telling from my experience, asking LLMs everytime when some bugs are found in the code, is not only expensive but also it de moralizes you as an engineer. vibe coding the entire project, destroys the maintainablity of the project by humans, token selling companies will always sell idea that you can write more code with LLMs, but what good is that code if it will fail in production? isn't it consumerism? definetely it is! If you think coding is solved then you are one step closer to the disaster.
It's just the beef between musk and Altman, nothing to do with the models.
back in college i used to stream family guy on my ipad, but now i just play some piano
compare this to Electronic engineering, we are not making chips by hand, It is impossible to squeeze too many transistors in such a small space, we just create the circuit designs. I believe writing the code is heading in the same direction as well, you don't write too much code now, but you have to design the architecture and connect things. But it does not mean that you don't need to understand the code, now of all the times people who understand code are more important. Many below par devs will loose jobs for sure.
Posted by
daemon_9009 on Saturday May 16, 2026 @04:24PM
from the self-post dept.
Hi, i have been experimenting with many coding agents distributed in a tree like heirarchy.
here is what i found:
1. current LLM models are not trained for orchestrating or managing multiple agents, they prefer doing the work by themselves instead of outsourcing it.
2. you can prompt them to follow the given heirarchy but it is not perfect, main agent will stop the sub agent and perform the...
> >layoff developers
for now we are not sure what is gonna happen. Big tech is surely reducing headcount to invest more in AI. but with recent downtime of github/AWS and them not blaming AI but humans, says a lot about that they will go to any extent to prove AI is bringing value enough to fire human engineers.
if we think, what is accountability? if a human would do a mistake, you would as an employer do two things: either teach him what not to do, or fire him.
Same thing can be done with AI agents, if you decide to stay with the agent then teach it what not to do, this might not work 100% but to a certain level for non critical things it would work.
Agents should ofc not be given consequential actions like deleting accounts at will.
But the point is, once a mistake is done, it is done, be it human or an agent, you gotta teach or fire something.
I don't think any other way to solve this problem
Posted by
daemon_9009 on Monday May 04, 2026 @04:45PM
from the ask-hn dept.
Hi,
most of the companies have now given AI tools to their employees, these include claude code, cursor and github copilot. This is supposed to be the testing period to see how will things turn out by using AI.
But now its almost a year, and employers will want to see the return from their investment in AI tools.
most devs have still not adopted cloud coding agents for one reason or the other....
Posted by
daemon_9009 on Monday March 09, 2026 @03:22PM
from the ask-hn dept.
Hi, I spawn multiple cloud agents, but the issue is in reviewing them. even if the model is giving demo artifacts in output, it is not enough to verify all the cases. We have automation test suites, but they are often behind the development. I had tried github copilot review for PRs but it outputs too many nitpicks and false postivies that it becomes irritating to find the real true positive...
Hi, guys here are my thoughts on how software development will look in a year. what do you think about this, lets discuss.
Posted by
daemon_9009 on Friday February 20, 2026 @01:30PM
from the ask-hn dept.
Hi, background coding agents are here for about half a year now. But only bold and forward teams are using it so far. what is your say? have you adopted background agents in your organization or are most of the people still working with locally running coding agents? One thing i have felt is that organizations are reluctant to give access to these vendors to clone their repos in cloud machines....
Posted by
daemon_9009 on Wednesday January 14, 2026 @08:19AM
from the ask-hn dept.
I have observed that many devs in companies are no t using Background coding agents available in either github copilot or cursor, they prefer IN-IDE agent even though the company is providing them with background agents.
I can think of 2 reasons:
1. People don't want to experiment, as background agents seems to be something people cannot control2. People are doubtful that the agent will be able...
Thanks, we had addressed our pain points, happy to see that you resonate with it!
Posted by
daemon_9009 on Tuesday January 13, 2026 @05:29AM
from the show-hn dept.
https://phantomx.dev/blog/What-is-wrong-with-current-coding-agent-workflow/
Hi, as the LLM models are getting smarter in coding tasks, we will soon be using agents as co workers, as current tools like github copilot and cursor are not optimized for team collaboration, we began building PhantomX, please give your feedback, if you think we are in the right direction or what should be changed for finding the optimized development workflow which works for both humans and...
Intelligent people see and understand the world deeper, more than an average person can, They see the world in all its forms, good and bad, understanding too much does not bring happiness but gloom. existence seems to be absurd, the more we understand existence the more one believes that it shouldn't have existed at the first place.
"happiness in intelligent people is the rarest thing I know" is a quote by Hemingway.
Also intelligent people overthink about a particular situation, while its better for survival but it can reduce happniess.
Posted by
daemon_9009 on Thursday July 31, 2025 @02:44PM
from the ask-hn dept.
Hi, Despite using cursor, windsurf or github copilot which are dev tools, have your organization started using background coding AI Agents, where you give them a jira ticket and get a PR? Which tools are you using, and how is the overall experience and which stack have you tried them on?
as good as it may sound, but this will never happen.
People will never pay for everything, majority don't even buy PC games, they use pirated one's. This is how humans are designed, and this is what which keeps the market afloats.
Posted by
daemon_9009 on Wednesday March 05, 2025 @03:42PM
from the ask-hn dept.
Hi, Seeing too many AI products launching, which are automating (up to some extent) tasks. I wonder what else is left which is not in public domain yet?
Posted by
daemon_9009 on Thursday February 13, 2025 @04:46PM
from the ask-hn dept.
I am trying to find a LLM model which is under 7B parameters and can handle json well. I want to use it for tool use locally.
I cannot make out anything from this. what are you trying to say? AI agents's fundamental task is to implement stuff, or in technical terms tool calling, computer use etc. they take input from user in natural language, and everything is perfectly defined in the prompt. The LLM is instructed to ask whenever not sure, so bootstrapping from hallucinations only happens when the implementation of AI agent is poor.
Posted by
daemon_9009 on Saturday December 14, 2024 @02:34PM
from the ask-hn dept.
The field of AI x Gaming is quite interesting and i guess gaming is the next industry where we will see the AI boom. From Intelligent NPCs, infinite gameplay to games created using diffusion, as shown by genie2 and other models, are you guys working on any of this? and how do you envision the games next year or so?
Posted by
daemon_9009 on Sunday November 17, 2024 @03:31AM
from the ask-hn dept.
Hi guys, i was working on making AI NPCs with LLMs and RL models, to create unique stories for the user, but this is a little far fetched.
Is this problem even worth solving? challenges like revenue model, costs of inference and all that. To take an example goodai launched a game https://www.aipeoplegame.com/ , from the first appearances, there is not much we can do in this world. maybe we need...
The entire paper demonstrated the results of the simulation or whatever they did. They did not mention how did they achieve this simulation. running 500-1000 LLMs parallely, will take too much computing resources, neither did they prove the claim they made about their parallel architecture. I remeber there was the paper published about an AI town, in which they mentioned clearly how they implemented it. they also released a recording of the simluation along with the real data of the results. If anyone got how they implemented this paper, please tell me.
Hi guys, I made a completely multiplayer programming game for C++ and python, started it to learn graphics, multithreading and all. ended up creating a small game engine for my game (included a lot of game maths), learnt multithreading and multiprocessing deeply. the game is originally programmed in c++, so had to do everything from scratch. Later ported it to python using pyBind11, wrote the langauge bindings for python. For the multiplayer part, which took the most of the time, ended up creating my own networking protocol( over UDP) according to the game needs.
you can see the project here at my website:
https://aiplaygrounds.in
Posted by
daemon_9009 on Thursday September 12, 2024 @01:33AM
from the ask-hn dept.
Hi, now when AI is progressing, c.ai and other chatbots apps seems old.
What could be the successor to these apps?
I say, to introduce another dimension in the app, i.e currently it's text based, adding another dimension of 3D can make it more immersive. What's your say?
I was in 2nd Year of my engineering. as many engineers before going to the college i used to make computer games on C++. Games caught my interest really early, because thats what is really fun and challenging in programming. One day while making a ping pong game, i thought what would happen if both the sides computers will play? who will win? from that i developed a programming game, in which you need to write algorithm for your battleships to destroy other battleships. You could try really good algorithms to test them for eg. min-max, monte-carlo tree search, RL, Deep learning etc.
Since i was in India, people here do programming for the sake of coursework or to get jobs. Really passionate people are difficult to find.
I tried to launch the product in my college, but sadly no one would want to play it. The game was really challenging to grasp at the beginning, I also pitched it to my professors to include it in the course curicullum of AI, they liked the idea, but refused it by saying it will be an overhead for the students to learn first about the algorithm and then about the Game API.
for an year i dejectedly saw that not everyone is as passionate as you are. I found no market for my programming game. If it would have launched somewhere in US, it could have been better, since MIT has such a kind of competition in which students needs to make the bots. it is not that programming games have no market, there are games like : Battlensakes, coderOne etc. but their market share is very less.
I learnt the lesson the easy way i guess, because i had a safety net since i was still in college, and had a job from the following year.
But then i really understood about product market fit, which i used to ignore while they taught in entrepreneurship classes. If anyone wants to see how the game looked : https:\\aiplaygrounds.in . I have revamped by business idea and working on something else.
Posted by
daemon_9009 on Thursday June 27, 2024 @05:07PM
from the ask-hn dept.
Hi, I am working on a generative game, in which the story is developed as the user goes, this will enable the user to create infinite story lines which can be played in an interactive world. But currently the problem is along with the stories we also need to show the graphics and the animations, which needs to be built at runtime for it to look really immersive.
Are there any models which can...
Current games which are using LLMs only activate the model when the user is talking to the NPC, but in order to create a real dynamic story which is completely random but to the point, the agents need to interact with other as well,so lets say there are around 100 agents in the game they need to interact with each other to generate some emergent behavior.
The form of interaction can be questioned here. will it be in natural lang? or just some embeddings or states.
But this thing still has a long way to go.
are you working on that? it needs a stable-diffusion kind of breakthrough to achieve that.
Posted by
daemon_9009 on Monday May 27, 2024 @01:01PM
from the ask-hn dept.
One thing that is not yet clear after AI boom is how will it affect Games. One day i was talking to a character in character.ai, i prompted the character to be a factory worker with minimal education, when i asked how to write c++ code to find factorial of a number it gave me the code. certainly that's not how LLMs can be implemented in games. LLMs can take the story beyond the bounds of the...