Has CC become much stupider in recent weeks, or is it me? Any anecdata out there?
People speculate somewhat seriously that Claude (especially given its French name) picked up at some point that you aren't supposed to work as hard in July and August.
Claude Code introduces specialized sub-agents
11–20 of 65 posts
Re: Claude Code introduces specialized sub-agents
#12Has CC become much stupider in recent weeks, or is it me? Any anecdata out there?
I don’t know about stupider, but definitely less reliable/available A couple days ago I was getting so many api errors/timeouts I decided to upgrade from the $20 to the $100 plan (as I was also regularly hitting rate limits as well) It seemed to fix the issue immediately. But today, the errors came back for about half an hour
It goes down usually around 1400-1500 UTC. Europeans are still awake and once the west coast joins in the fray Anthropic falls over.
Pretty rare to get a 529 outside of that time window in my personal experience, at least during the USA day.
Re: Claude Code introduces specialized sub-agents
#13So everything claude-flow¹ already does but worse (I guess?). ¹ https://github.com/ruvnet/claude-flow
That guy doesn't even understand how his own software works. Is anyone actually using this thing and putting their code into production?
Re: Claude Code introduces specialized sub-agents
#14Has CC become much stupider in recent weeks, or is it me? Any anecdata out there?
People speculate somewhat seriously that Claude (especially given its French name) picked up at some point that you aren't supposed to work as hard in July and August.
How long before we hire psychiatrists instead of engineers to debug AI
Re: Claude Code introduces specialized sub-agents
#15Has CC become much stupider in recent weeks, or is it me? Any anecdata out there?
Insert something to the tune of: “never read files in slices. Instead, whenever accessing a file, you must read a file in entirety[..]” at the beginning of every conversation or whenever you’re down to burn more credits/get better results.
A great deal of claude stupidity is due to context engineering, specifically due to the fact that it tries its hardest to pick out just the slice of code it needs to fulfill the task.
A lot of the annoying “you’re absolute right!” come from CC incrementally discovering that you have more than 10 lines of code in that file that pertains to your task.
I don’t believe conspiracies about dumbed down models. Its all context pruning.
Re: Claude Code introduces specialized sub-agents
#16Has CC become much stupider in recent weeks, or is it me? Any anecdata out there?
I feel like it’s gotten better recently
Re: Claude Code introduces specialized sub-agents
#17Earlier quoted context omitted.
People speculate somewhat seriously that Claude (especially given its French name) picked up at some point that you aren't supposed to work as hard in July and August.
How long before we hire psychiatrists instead of engineers to debug AI
Well, we could start with some ELIZA instances.
Re: Claude Code introduces specialized sub-agents
#18So everything claude-flow¹ already does but worse (I guess?). ¹ https://github.com/ruvnet/claude-flow
> IMPORTANT: Claude Code must be installed first:
> [...]
> # 2. Activate Claude Code with permissions
> claude --dangerously-skip-permissions
Bypassing all permissions and connecting with MCPs, can't wait for "Claude flow deleted all my files and leaked my CI credentials" blog post
Re: Claude Code introduces specialized sub-agents
#19I wonder if this is also a good way to create experts for specific tasks/features of a codebase.
For example, a sub-agent for adding a new stat to an RPG. It could know how to integrate with various systems like items, character stats component, metrics, and so on without having to do as much research into the codebase patterns.
Re: Claude Code introduces specialized sub-agents
#20I've made a few attempts at manually doing this w/ mcp and took a brief look at "claude swarm" https://github.com/parruda/claude-swarm - but in the short time I spent on it I wasn't having much success - admittedly I probably went a little too far into the "build an entire org chart of agents" territory
the main problem I have is that the agents just aren't used
For example, I set up a code reviewer agent today and then asked claude to review code, and it went off and did it by itself without using the agent
in one of anthropic's own examples they are specifically telling claude which agents to use which is exactly what I don't want to have to do:
> First use the code-analyzer sub agent to find performance issues, then use the optimizer sub agent to fix them
My working theory is that while Claude has been extensively trained on tool use and is often eager to use whatever tools are available, agents are just different enough that they don't quite fit - maybe asking another agent to do something "feels" very close to asking the user to do something, which is counter to their training
but maybe I just haven't spent enough time trying it out and tweaking the descriptions