I know dozens of people who are in a similar state right now, following the November 2025 moment when Claude Code (and Codex) got really good.
I wouldn't worry about it just yet - this is all very novel, and there's a lot of excitement involved in figuring out what it can do and trying different things.
If you're still addicted to it in three months time I'd start to be concerned.
For the moment though you're building a valuable mental model of how to use it and what it can do. That's not wasted time.
I'm seeing the limits when Claude makes some statements that are extremely wrong but incredibly hard to spot unless you're in the field, recently telling me that "some people say" that rydberg atoms and neutral atoms are different enough to be in different quantum computing categories (they're the same). The stakes are lowering somehow, because I know I can't trust it for anything but fun side-projects. For serious research it's still me and reading papers.
I'm not trying to convert you, just want to share process tips that I see working for me and others. We're using agents, not a chat, because they can do complex work in pursuit of a goal.
1. Make artifacts. If you're doing research into a tech, or a hypothesis, then fire off subagents to explore different parts of the problem space, each reporting back into a doc. Then another agent synthesizes the docs into a conclusion/report.
2. Require citations. "Use these trusted sources. Cite trusted sources for each claim. Cite with enough context that it's clear your citations supports the claim, and refuse to cite if the citation doesn't support the claim."
3. Review. This lets you then fire off a subagent to review the synthesis. It can have its own prompt: look for confirming and disconfirming evidence, don't trust uncited claims. If you find it making conflation mistakes, figure out at what stage and why, and adjust your process to get in front of them.
4. Manage your context. LLM only has a fixed context size ("chat length") and facts & instructions at the front of that tend to be better hewn to than things at the end. Subagents are a way of managing that context to get more from a single run. Artifacts like notebooks or records of subagent output move content outside the context so you can pick up in a new session ("chat") and continue the work.
It's less fun that just having a chat with ChatGPT. I find that I get much better quality results using these techniques. Hope this helps! If you're not interested in doing this (too much like work, and you already have something that works), it's no skin off my nose. All the best!
Your mental model point is very true. We all had to learn how to google at some point — explaining how to use these tools to someone outside the bubble feels like explaining how googling works to someone. Much of it is intuitive understanding from experience.
My question would be how much we think the processes will change as the models do. Much advice from two years ago is no longer relevant or realistic. Where do we think it will go next?
Does anyone have a really good way to explain to their relatives and friends how using an agent is different from simply using Google?
Just saying ‘fundamentally different’ doesn’t go very far; the best I’ve found is sitting down and giving a demonstration.
It’s also difficult to explain the enormous gap between frontier models and the free ones many people are accustomed to using. Is there a tangible comparison to a normie real-life ‘thing’ that anyone has used successfully?
I have no idea how to explain agents to a non-technical audience - there is SO much that can go wrong with them, it's still very much a technical power-user technology in my opinion.
ChatGPT and Claude can both execute code now, so a safe subset is to show people how to upload files there and have them do useful things with the data.
> Much of it is intuitive understanding from experience.
You’re mistaking domain expertise with tool expertise. You can’t teach a non dev how to use an LLM effectively for dev without teaching them to be an experienced dev. Once you have that knowledge, LLMs aren’t that hard to use.
I agree, Claude Code has been addictive for me too. It feels like I'm finally churning through a backlog that has been weighing on me for years (decades even). Maybe the addiction is not to Claude but to productivity, and Claude is just an enabler. (And maybe the productivity is an illusion, time will tell.)
I view Claude code same as how I used to use Jetbrains IDEs. I mean yes they are not same but even when I first learned of Pycharm pro and it's features I had this urge to make a lot of random idea apps. The landscape has changed but the solution is same. Prefer spending your time on things that give you long term happiness in any way.
The problem is it's not limited to code. I have Claude Code maintaining my Obsidian Vault, managing my Home Assistant setup via SSH, helping me buy life insurance and file my taxes and and manage my home orchard and...
Find one thing you want to explore or research/visualize and go very deep with it... with Claude Code, it's just a tool after all. Then write a long blog post about it (yourself).
You probably aren't addicted to CC, I suspect you are just hopping from idea to idea too quickly because these new tools allow for it.
I have about six or seven backlogs full of tech debt, bugs, and other various enhancements that every team _wants_ to do, but we either don’t have the bandwidth or know-how to do right now.
I spend a lot of time at my org doing one of the following things:
1. figuring out how to onboard engineers and bootstrap them to do their own work to draw down their backlogs
2. show the team cool ideas to spark their interest or bring them from “I’m never using this useless crap AI” to “oh, wow, I never thought of that… fires up a terminal and creates own cool thing”
3. creating a backlog of other things people want to automate but never wrote down/thought through that Claude can do in short order for immediate value
I hear you! It feels like I got a new toy when I was a kid sometimes. I am a 15+ software developer, and I am not sure if I want to keep working in the same way I used to if claude code suddenly disappears one day.
I’m doing a bunch of deeply horrible ops stuff at the moment, and the ability for Claude to write the worst python script in the world and tell me which machines aren’t configured the way I think is invaluable.
Without it you likely would have been in the same quagmire, but just slower?
It could have taken you years to realize that "oh I'm just exploring stuff and have no output".
Set an ambitious goal that is achievable using Claude Code, and focus on delivering it. Even if it doesn't turn out to be a hit, the experience of releasing it and using AI to accelerate it, will be a talking point to your 10-year-older self.
Have kids, realize there is more important stuff then claude code, lol
Jokes aside, my relationship with my wife is always top priority, kids are priority, health is priority. With those 3 I have about 2 hours per day for myself and yeah, you can use them however you like
I was on a company retreat last month. My coworker was on their phone the whole time on the bus ride over to dinner I finally looked over and it was a Claude Code session. The addiction is real.
Listen, If you truly want help you've made the first step by realising what's wrong, but you won't get help here.
This community is obsessively pro-AI. Asking here is the equivalent of asking the guy who has sat at the slot machine next to you for the past three hours if he thinks you have a gambling problem. Of course he's going to say "no" or try to justify it, to do otherwise would be to admit to himself that he has a problem.
I don't have advice for you, other than to look up what gambling, drug, or alcohol addicts do. The path to recovery for all addiction is long and painful, but it can be done. Good luck.
I know dozens of people who are in a similar state right now, following the November 2025 moment when Claude Code (and Codex) got really good.
I wouldn't worry about it just yet - this is all very novel, and there's a lot of excitement involved in figuring out what it can do and trying different things.
If you're still addicted to it in three months time I'd start to be concerned.
For the moment though you're building a valuable mental model of how to use it and what it can do. That's not wasted time.
I'm seeing the limits when Claude makes some statements that are extremely wrong but incredibly hard to spot unless you're in the field, recently telling me that "some people say" that rydberg atoms and neutral atoms are different enough to be in different quantum computing categories (they're the same). The stakes are lowering somehow, because I know I can't trust it for anything but fun side-projects. For serious research it's still me and reading papers.
I'm not trying to convert you, just want to share process tips that I see working for me and others. We're using agents, not a chat, because they can do complex work in pursuit of a goal.
1. Make artifacts. If you're doing research into a tech, or a hypothesis, then fire off subagents to explore different parts of the problem space, each reporting back into a doc. Then another agent synthesizes the docs into a conclusion/report.
2. Require citations. "Use these trusted sources. Cite trusted sources for each claim. Cite with enough context that it's clear your citations supports the claim, and refuse to cite if the citation doesn't support the claim."
3. Review. This lets you then fire off a subagent to review the synthesis. It can have its own prompt: look for confirming and disconfirming evidence, don't trust uncited claims. If you find it making conflation mistakes, figure out at what stage and why, and adjust your process to get in front of them.
4. Manage your context. LLM only has a fixed context size ("chat length") and facts & instructions at the front of that tend to be better hewn to than things at the end. Subagents are a way of managing that context to get more from a single run. Artifacts like notebooks or records of subagent output move content outside the context so you can pick up in a new session ("chat") and continue the work.
It's less fun that just having a chat with ChatGPT. I find that I get much better quality results using these techniques. Hope this helps! If you're not interested in doing this (too much like work, and you already have something that works), it's no skin off my nose. All the best!
Your mental model point is very true. We all had to learn how to google at some point — explaining how to use these tools to someone outside the bubble feels like explaining how googling works to someone. Much of it is intuitive understanding from experience.
My question would be how much we think the processes will change as the models do. Much advice from two years ago is no longer relevant or realistic. Where do we think it will go next?
Does anyone have a really good way to explain to their relatives and friends how using an agent is different from simply using Google? Just saying ‘fundamentally different’ doesn’t go very far; the best I’ve found is sitting down and giving a demonstration.
It’s also difficult to explain the enormous gap between frontier models and the free ones many people are accustomed to using. Is there a tangible comparison to a normie real-life ‘thing’ that anyone has used successfully?
I have no idea how to explain agents to a non-technical audience - there is SO much that can go wrong with them, it's still very much a technical power-user technology in my opinion.
ChatGPT and Claude can both execute code now, so a safe subset is to show people how to upload files there and have them do useful things with the data.
> Much of it is intuitive understanding from experience.
You’re mistaking domain expertise with tool expertise. You can’t teach a non dev how to use an LLM effectively for dev without teaching them to be an experienced dev. Once you have that knowledge, LLMs aren’t that hard to use.
I agree, Claude Code has been addictive for me too. It feels like I'm finally churning through a backlog that has been weighing on me for years (decades even). Maybe the addiction is not to Claude but to productivity, and Claude is just an enabler. (And maybe the productivity is an illusion, time will tell.)
I view Claude code same as how I used to use Jetbrains IDEs. I mean yes they are not same but even when I first learned of Pycharm pro and it's features I had this urge to make a lot of random idea apps. The landscape has changed but the solution is same. Prefer spending your time on things that give you long term happiness in any way.
The problem is it's not limited to code. I have Claude Code maintaining my Obsidian Vault, managing my Home Assistant setup via SSH, helping me buy life insurance and file my taxes and and manage my home orchard and...
Unless you are buying life insurance and filing taxes daily this seems like a good thing.
Find one thing you want to explore or research/visualize and go very deep with it... with Claude Code, it's just a tool after all. Then write a long blog post about it (yourself).
You probably aren't addicted to CC, I suspect you are just hopping from idea to idea too quickly because these new tools allow for it.
I have about six or seven backlogs full of tech debt, bugs, and other various enhancements that every team _wants_ to do, but we either don’t have the bandwidth or know-how to do right now.
I spend a lot of time at my org doing one of the following things:
1. figuring out how to onboard engineers and bootstrap them to do their own work to draw down their backlogs
2. show the team cool ideas to spark their interest or bring them from “I’m never using this useless crap AI” to “oh, wow, I never thought of that… fires up a terminal and creates own cool thing”
3. creating a backlog of other things people want to automate but never wrote down/thought through that Claude can do in short order for immediate value
I hear you! It feels like I got a new toy when I was a kid sometimes. I am a 15+ software developer, and I am not sure if I want to keep working in the same way I used to if claude code suddenly disappears one day.
I’m doing a bunch of deeply horrible ops stuff at the moment, and the ability for Claude to write the worst python script in the world and tell me which machines aren’t configured the way I think is invaluable.
you're fine. have you made any sankey charts? nsfw: https://seidt.quest/s/aella/
i am waiting for someone to surpass the original steam engine sankey diagram: https://commons.wikimedia.org/wiki/File:JIE_Sankey_V5_Fig1.p...
what. did. I. just. witness.
great question. data source: https://aella.substack.com/p/my-birthday-gangbang
the diagram is calculated with d3-sankey & rendered with imgui. you can stretch that window however you want—ok, enough.
edit: the original steam-engine sankey diagram created a far stronger emotional reaction in me. the aella chart is just more modern, i guess?
Without it you likely would have been in the same quagmire, but just slower?
It could have taken you years to realize that "oh I'm just exploring stuff and have no output".
Set an ambitious goal that is achievable using Claude Code, and focus on delivering it. Even if it doesn't turn out to be a hit, the experience of releasing it and using AI to accelerate it, will be a talking point to your 10-year-older self.
It's not framed exactly the same way, but I think this article is relevant: https://siddhantkhare.com/writing/ai-fatigue-is-real
Discussion: https://news.ycombinator.com/item?id=46934404
Link the charts! Do you think they’re awesome?
Have kids, realize there is more important stuff then claude code, lol
Jokes aside, my relationship with my wife is always top priority, kids are priority, health is priority. With those 3 I have about 2 hours per day for myself and yeah, you can use them however you like
I was on a company retreat last month. My coworker was on their phone the whole time on the bus ride over to dinner I finally looked over and it was a Claude Code session. The addiction is real.
Maybe, but I would say a much healthier one than watching tik toks or doomscrolling something else.
Exploring ideas is a form of learning,
I'm not sure if I will look back on my life and think that I know too much and didn't produce enough widgets.
I wish my other addictions were only $200/mo. Honestly. And for some, as satisfying as claude.
We're all in the same boat right now. Except for those who decry LLMs and loudly await the relevance of their artisanal coding skills to re-ascend. :)
IMO, There are worse things to be addicted to. At some point you’ll outgrow it.
Tokens per day
Listen, If you truly want help you've made the first step by realising what's wrong, but you won't get help here.
This community is obsessively pro-AI. Asking here is the equivalent of asking the guy who has sat at the slot machine next to you for the past three hours if he thinks you have a gambling problem. Of course he's going to say "no" or try to justify it, to do otherwise would be to admit to himself that he has a problem.
I don't have advice for you, other than to look up what gambling, drug, or alcohol addicts do. The path to recovery for all addiction is long and painful, but it can be done. Good luck.
[dead]