Brandon Z. Hoff
Region: US
Wednesday 16 July 2025 20:22:36 GMT
47801
1093
110
61
Music
Download
Comments
The AI Syndicate :
If you have time, go look at the video i just uploaded. i built a mcp memory, and it completely removes this issue. the video is showing claude desktop, but my claude code is hooked up to the same MCP server so they also share that memory. i work in claude desktop until i hit my limit then switch over to claude code and run the API per token. No downtime, no updating context in new threads or projects.
2025-07-21 03:49:10
1
Christine23 :
You’re always 10 miles ahead of me. I haven’t migrated to Claude. Still using ChatGPT
2025-07-17 00:03:10
2
MiraDiary. :
yeah, this is already happening elsewhere. workbeaver’s been doing cross platform computer control for some time now, including windows, long before this started trending.
2026-01-15 16:58:13
93
Slothsbeslothing :
I’m on the broke $20 plan and noticed that from day one and have been doing exactly what you are saying but using a project scope-progress.md and I have that referenced in the Claude.md file for operating guidelines.
2025-07-16 20:53:07
3
Bujavi :
2.5 hours on the $200 plan? I'm getting like 4-4.5 hours on the $20 plan. How are you using it? 😅
2025-07-17 07:34:37
26
Mr. Aitch :
Have Claude [echo ‘{ … detailed context … } > context_dump.json] without a summary. You can even setup an alias for this and other agents can load it. Set up templates for the context structure. The process takes a few seconds.
2025-07-16 22:36:11
56
FAF0 BACON :
I saw somewhere where someone uses Gemini with Claude Code to use the Gemini 1M context window but Claude in CLI. Haven’t figured that out yet, if you do - please tag me :)
2025-07-18 20:31:06
4
jordanlister :
Opus or sonnet?
2025-07-23 09:57:50
4
user99550352041 :
I’m working on an SQLite based system that’ll run a SLM that saves+ tags the whole chat. Then all you gotta do is tell claude to look at the text blocks under - then he would look under the chat blocks saved under those 3 categories. The tagging logic is predicate based so it’s only going to match all 3 with the pull request. If it was just a debug on a subprocess in that block- not gonna get pulled.
2025-10-24 18:29:00
1
Justin Michael :
claude was getting throttled massively today
2025-07-17 03:16:14
20
Jonathan Edwards :
-give Claude desktop file system access, use it to anylize and plan then tell it to instruct Claude code in a shared.md file.
2025-07-16 21:57:50
4
BigCoder42069 :
$200 usage plan and u hit ur max limit??? I’m on $100 plan and code all day and barely hit the limit, (non-opus) how big is your codebase?
2025-07-16 21:46:13
6
Robert M. 🇯🇲🇺🇸 :
Mine will still auto compact. I’m on the $100/mo
2025-07-16 22:51:59
2
itmine :
yes. i use free plan and the limit only 1 message.
2025-11-06 16:17:00
3
bluesdave11 :
So when I’m in ChatGPT, when the context window is too big I converted to a file. Then I start a new chat, and I say go read that file, and bam it speeds up, and has access to all the old conversation.
2025-07-17 03:36:38
5
TheAIGuyATL :
I had to just end up paying for straight api usage
2025-07-16 20:53:42
2
Spiderman824 :
I make a ton of .md files, and have the Claude.md have instructions to continually update them. Things like current_session.md that I tell it to continually update. Plus larger project plan and todo lists in Md’s I actually make it break things into sprints and add the sprints to a main Md then ask it to break off sprint specific Md files while we’re working them. So, yes, I do this, to the extreme
2025-07-17 04:56:37
3
Holden Russell :
Yes the markdown checklist is super helpful. I tell it to make a plan in .md format before executing then update the plan as it works through it
2025-07-17 02:25:28
4
Beady Eyes :
It is over hyped I used and nothing special
2025-07-17 20:13:36
1
brocka11 :
Omg!! I’m on the 20 dollar plan. This is so helpful.
2025-07-16 20:43:37
1
clearstarsai :
I use Cursor, haven’t dedicated the time to test out CC yet, but I typically make the debug report and todo list as part of my project rules in the MDC file. I noticed that not only helps be more token efficient, but also it produces better quality code so less for me to QA later.
2025-07-16 22:53:42
1
Scholars Edge Consult :
who will join me to his subscription?
2026-01-22 09:57:50
0
SayitOutloud :
Bmad method.
2025-09-11 05:36:15
0
sonicpoet :
I’m pretty sure that’s exactly what compacting does. Like you can go in and look at the file that gets saved from the compact, and it’s basically just a summary of the context. It might be better to do it manually though because you can have more control over it that way.
2025-09-10 23:03:34
0
lech.tech :
I do something similar. Setup a command that calls a subagent specifically meant for logging progress within three chat context to a specific folder. It looks for the log of the current date and just adds new details to the end. After I clear I tell the new chat to read the log and continue working.
2025-08-30 05:39:12
0
To see more videos from user @hoffdigital, please go to the Tikwm
homepage.
