[AI] agent is not going to work for you...

[aeric]

You still need to do it yourself.

They (AI agents) cannot help you to build from start to end or work for you 100%.
There are some parts they still can't do. One of them is the asset files!

Let say I want to build a game.
The agent only provide you an MD spec file listed out the plan and guideline (and asked you to do the WORK!)
So you still need to create the layout file (e.g .bal, .bil or .bjl), the SVG file (they cannot generate it), the sound or music MP3 or OGG file, etc.
You need to follow the naming convention he wanted you to create for him.

It seems to me that I am working under him even though I thought I am the boss who give him the instructions.

Beware!

1. The agent can still make typo errors.
2. He can repeat the mistakes he already made before by deleting my code that solve a previous problem.
3. Hallucinations is still exist and never has improved since.
4. It mixes 2 languages in 1 app (in my case, local Bahasa Malaysia and English content)
5. You may end up doing a lot of work harness the agent, provide a lot of specs.md, instructions.md, skills.md or what ever md.

 

[Lucas Siqueira]

Congratulations on the tests! I'm using claude.ia, but I still need to improve its .md file. As you said, sometimes even with the commands it goes haywire and does things it shouldn't, haha...

What programs do you use to operate the agents and what AI?

 

[aeric]

What programs do you use to operate the agents and what AI?

If you check the image, you will notice I am using Qwen3.6 Plus Free listed in OpenCode.

 

[Mashiane]

1. The agent can still make typo errors.
2. He can repeat the mistakes he already made before by deleting my code that solve a previous problem.
3. Hallucinations is still exist and never has improved since.
4. It mixes 2 languages in 1 app (in my case, local Bahasa Malaysia and English content)
5. You may end up doing a lot of work harness the agent, provide a lot of specs.md, instructions.md, skills.md or what ever md.

Same experiences here.

I am using Kimi 2.6 with claude via Ollama inside vscode

ollama launch claude --model kimi-k2.6:cloud

I just open my b4x folder project and execute that via the terminal.

Because the context gets larger each time you prompt and receives a response, one thing I do to avoid hallucinations is after 30 minutes, ask it to summarize our conversations and save it. Then start a new chat and give it the context of the summarized conversations.

After each sussessful iteration, I create a backup of "LastWorkingVersion" so that when it deletes or changes things that already worked, I refer it to that version.

Using AI is a patience exercise because no matter how much you train it, it will lie, it will assume, it will break your code. Can be very frustrating.

Write a function? it does, is the function 100% accurate? Response No. Then it suggests what can be changed and improved. Why not just do it right first time?

All the best guys and girls...

 

[aeric]

Now I noticed it treats my comments are not important and clean them up.
Comments are important for me so the future me can recall what the code is meant for.