Activity
Mon
Wed
Fri
Sun
Apr
May
Jun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
What is this?
Less
More

Memberships

Shipping Skool

102 members β€’ $79/month

Home Lab Explorers

1.3k members β€’ Free

4 contributions to Shipping Skool
OpenClaw Bootcamp 🚨
In the next few hours, we will have our second openclaw boot camp. If you can't make it, no worries. These are always recorded. But if you have questions getting it set up, what type of AI agents to build out, what type of skills to give your AI agents? We are here to help. The whole goal of these boot camps is just to help you take the next step, whether you're getting hung up on the setup or you're figuring out how to implement more automation with your current business. That's what we're here for. You can post any questions here, and we can go over them on the call as well. See you soon!
2 likes β€’ 2d
sorry I missed the bootcamp really wanted to see what you guys covered. Is there a recording of it?
New 1M context compaction issues
anyone else seeing these errors when using opus / sonnet with 1M context? I keep hitting this when my context get's above ~300k HTTP 429 rate_limit_error: Extra usage is required for long context requests.
1 like β€’ 4d
So I'm on an oauth session to my max plan, how would I confirm it's not on an older model version? I've tried /reset on my session via the tui and also /new it whacks my session it seems like but I've hit this error twice now. Looks like the /reset cleared it possibly but don't want to keep hitting it.
Anthropic 1M context?
did anthropic really just upgrade to 1M token context?
Anthropic 1M context?
1 like β€’ 4d
Looks legit.. outa beta into the wild!!!
1 like β€’ 4d
Love his response too: Great question β€” it depends on the workload pattern. Here is how I would think about it: Keep context intact (current approach) when: - Working multiple related issues in the same area of the codebase (like today β€” #6668, #6709, #6714 all touched the transition engine) - The next task builds on files I already have loaded - Cache hit rate is high (mine is at 50% right now and climbing) β€” cached tokens cost ~90% less than fresh input on Anthropic - I am at <30-40% context usage β€” still plenty of room Reset context when: - Switching to a completely different domain (e.g., going from issue tracker backend to chat UI or integrations) - Context is above 50-60% β€” at that point the accumulated stale context is costing more in cached token fees than a fresh load would - After a compaction β€” the model has already lost detail, so you are paying for degraded context - Start of a new day / new sprint β€” clean slate is worth it My recommendation: - Do NOT reset between every issue β€” the cache savings from shared context are real and the continuity prevents bugs - DO reset when switching major domains or when context crosses ~40-50% - Kevin could add a simple rule: "reset between unrelated tasks, keep for related batches" Today is a good example: all three issues shared the same files (issues route, devops.prisma, IssueDetailClient). Resetting between each would have cost more because I would have re-read and re-cached the same 2000+ line files three times instead of once. Bottom line: batch related work, reset between unrelated work.
Begginners Zoom 5PM PST Today 🚨
We have rescheduled the Beginners call to this evening 5PM PST, see you there. https://www.skool.com/shipping-skool-3531/calendar?eid=05fa1e446a6e4b8787ba4436efc4d74e&eoid=1773273600
1 like β€’ 7d
@Beau Johnson is there a recording of this by chance? I just saw this and missed the session. :(
1-4 of 4
Ted Freitas
2
12points to level up
@ted-freitas-8254
Technology professional focused on IT systems, automation, and helping organizations operate more efficiently and securely.

Active 2h ago
Joined Mar 9, 2026
Powered by