A bitcoin/nostr grant guy[1] on X posted about how we never have to read code or look at a computer again; just tell the bot your values and it'll do it good. I suspect when the bots turn all of his buttons blue, he reasons that the bots are doing him a favor. Or, more likely, that having an opinion about details is old fashioned.
It's probably not a coincidence that this thinking infects the least accountable people the most. ↩
Sometimes I find my bots all queued up and as I hate deserializing worker queues because it complicates my review process, I just throw something at arena.ai/agent. But even for that I use structured task templates, i.e.
### Objective
<!-- One sentence: what should be true when this is done? -->
### Context
<!-- Links/pointers to related issues, files, or docs. The agent needs these to avoid hallucinating context. -->
- url 1
- url 2
- attached file
### Constraints
<!-- Scope the task by describing/constraining the steps to perform -->
- step 1
- step 2
### Acceptance Criteria
<!-- What can the agent measure output against to make it match expectations -->
- Criterion 1
- Criterion 2
### Task decomposition
<!-- Specify how the agent should use subtasks to get to the desired level of detail -->
- Use the main task to check the overall implementation and discover all items that must be checked, then
- Use subtasks to analyze each discovered item in a detailed manner
I kinda do that by getting one LLM to generate such structured task templates and then feeding them into Claude. And then copy-paste Claude's output back into the first LLM. By separating analysis from coding, it helps me avoid polluting Claude's context window and catch reasoning mistakes from Claude.
But I could do a better job with my templates, based on what you shared here.
I have that pattern for larger source code diff analysis. Like right this second I'm running a source code mapping on yesterday's Phoenix release, that went through a first pass to basically identify the areas needed for review, and that I then read and made sure was good (nowadays it doesn't need too much editing but that is probably a function of both evolving models and me evolving my templates) and if needed I could have split some things up, for the context window guard you mention (not needed on this diff though.)
When it's done I get a massive report. The most work is going through that. I have specifically spec'd the desired output format to not become overly brain damaged from reading that.
I never use bots for coding anything serious anymore though. Just tools.
PS: For small jobs I often just delete the decomposition section. It's not always needed.
I never use bots for coding anything serious anymore though
What do you mean? For coding new features, you use your pre-LLM skills? No LLM assistance? Or you're talking specifically about bots with less supervision?
Everything I have coded for production in the past month has been hand coded. It's easier to maintain, makes more sense for reviewers, and I get the bugs out by running review rounds with bots, who get to write comments, not code. Then I fix the code if I agree with the review, also manually.
Examples that I haven't hand coded: template automation, my personal mostro monitor (that still isn't finished), some scripts to find out what the fuck is going on with people trying to brute force through my mTLS pki... internal stuff.
I wonder how many of the new generation of coders will even be able to do that. Probably depends a lot on how current CS classes are being taught. Or how people self-teach themselves coding with sufficient discipline not to use bots while doing so.
"The year is 2027. In this far future, artificial intelligence has taken over all productive activity of humankind. The humans, having no gainful work left to do, have all become shitposters"
A bitcoin/nostr grant guy[1] on X posted about how we never have to read code or look at a computer again; just tell the bot your values and it'll do it good. I suspect when the bots turn all of his buttons blue, he reasons that the bots are doing him a favor. Or, more likely, that having an opinion about details is old fashioned.
It's probably not a coincidence that this thinking infects the least accountable people the most. ↩
You still get a lot of slop code contributions to SN? Or did turning off the rewards for coding contributions resolve that?
the bots are so dumb they think the bounties are still available. i end up blocking a few accounts per day
If you argue with bots, this is what you get.
Next time:
I cannot believe people still argue with bots. We joke how those LLMs are retarded, but LLM-users are even more retarded.
Yes, if I've learned something from your AI musings here, it's to never argue with bots.
Sometimes I find my bots all queued up and as I hate deserializing worker queues because it complicates my review process, I just throw something at
arena.ai/agent. But even for that I use structured task templates, i.e.### Objective <!-- One sentence: what should be true when this is done? --> ### Context <!-- Links/pointers to related issues, files, or docs. The agent needs these to avoid hallucinating context. --> - url 1 - url 2 - attached file ### Constraints <!-- Scope the task by describing/constraining the steps to perform --> - step 1 - step 2 ### Acceptance Criteria <!-- What can the agent measure output against to make it match expectations --> - Criterion 1 - Criterion 2 ### Task decomposition <!-- Specify how the agent should use subtasks to get to the desired level of detail --> - Use the main task to check the overall implementation and discover all items that must be checked, then - Use subtasks to analyze each discovered item in a detailed mannerI kinda do that by getting one LLM to generate such structured task templates and then feeding them into Claude. And then copy-paste Claude's output back into the first LLM. By separating analysis from coding, it helps me avoid polluting Claude's context window and catch reasoning mistakes from Claude.
But I could do a better job with my templates, based on what you shared here.
I have that pattern for larger source code diff analysis. Like right this second I'm running a source code mapping on yesterday's Phoenix release, that went through a first pass to basically identify the areas needed for review, and that I then read and made sure was good (nowadays it doesn't need too much editing but that is probably a function of both evolving models and me evolving my templates) and if needed I could have split some things up, for the context window guard you mention (not needed on this diff though.)
When it's done I get a massive report. The most work is going through that. I have specifically spec'd the desired output format to not become overly brain damaged from reading that.
I never use bots for coding anything serious anymore though. Just tools.
PS: For small jobs I often just delete the decomposition section. It's not always needed.
What do you mean? For coding new features, you use your pre-LLM skills? No LLM assistance? Or you're talking specifically about bots with less supervision?
Everything I have coded for production in the past month has been hand coded. It's easier to maintain, makes more sense for reviewers, and I get the bugs out by running review rounds with bots, who get to write comments, not code. Then I fix the code if I agree with the review, also manually.
Examples that I haven't hand coded: template automation, my personal mostro monitor (that still isn't finished), some scripts to find out what the fuck is going on with people trying to brute force through my mTLS pki... internal stuff.
A dying breed.
I wonder how many of the new generation of coders will even be able to do that.
Probably depends a lot on how current CS classes are being taught. Or how people self-teach themselves coding with sufficient discipline not to use bots while doing so.
The response roulette is hilarious
"The year is 2027. In this far future, artificial intelligence has taken over all productive activity of humankind. The humans, having no gainful work left to do, have all become shitposters"