Sabitlenmiş Tweet
Jeremy Carter
6.2K posts

Jeremy Carter
@Jer_Car
Love to learn. Fascinated by AI. Building stuff.
Birmingham, AL Katılım Kasım 2010
315 Takip Edilen1.3K Takipçiler

Jeremy Carter retweetledi

@claudeai what's the solution to claude desktop randomly switching to cmd + enter to send instead of just enter?
English

@WisprFlow Using airpods on a mac mini bc there's no microphone. Lots of lag when I start new dictation. Any way around this?
English

@Shpigford @openclaw That's awesome. Did it make recordings of the calls that you could listen to?
English

another 🦞 use case: one of our cars got sideswiped and now needs some repair work done.
there are dozens of places within a few miles of us, but figuring out which one to go to for an estimate required some effort. effort that i just offloaded entirely to hank (my @openclaw instance).
things hank did:
* google searched for the top rated repair shops closest to our house
* called all of them to get lead times on repair work and find out if an appointment is required for an estimate
* ranked them by lead times + distance + ratings
* saved all the info in a notion doc (location, contact info, ratings, lead time, appointment requirements)
all i did was give it about 3 sentences of instructions and then i went and did other things while it chewed through the job over the course of about 10 minutes. the calls alone were a massive time-save as it did them in parallel.
so. freaking. cool.
English

I think Greg is spot on with this list. There's really not a lot of areas that won't be affected by AI, some for the better some for the worse. Interested to see how it plays out.
GREG ISENBERG@gregisenberg
English

CRITICAL: EVERYONE USING CLAWDBOT SHOULD RUN THIS PROMPT RIGHT NOW:
By default, the 2 best Clawd memory features are turned OFF
Running this 1 prompt will immediately stop your AI from getting confused in between compactions/sessions:
Prompt:
"Enable memory flush before compaction and session memory search in my Clawdbot config. Set `compaction.memoryFlush.enabled` to true and set `memorySearch.experimental.sessionMemory` to true with sources including both memory and sessions. Apply the config changes."
Here's what you enabled by running that prompt:
Memory Flush: Your AI automatically saves everything important to a file right before its context gets wiped, so nothing slips through the cracks.
Session memory search: Your AI can search through every conversation it's ever had with you, even ones it no longer "remembers."
Boom, your ClawdBot memory is now 10000x better
English

@AlexFinn Running into constant rate limits from Anthropic (30k/min). Requires me to wait 60 seconds before sending multiple messages. I have to be missing something, it's nearly unusable. Do you have a recommendation?
English

I keep seeing this really stupid post: “I tried ClawdBot and there are NO good use cases”
Let’s put this to rest
Then 7 most life changing ClawdBot use cases I’ve implemented (so far):
• Overnight coder. Every night Clawd builds 1 app using Claude Code that it thinks will improve your workflow based on your conversations
• Based on every conversation you’ve ever had with your Clawd, get a daily research report explaining 1 relevant topic spoken in the voice of a professor
• Headless Notion. No need to go through 100 folders to write or find notes. When you have something you want to remember, just text your Clawd and it will auto store and organize it for you
• Personal CRM: based on every email, text, or DM you have, create a database of your contacts and all your messages. Continuously update automatically. Take AI notes and create follow up tasks
• Automatic assistant: take a look at my todo list every day (I use Things 3) and see what tasks you can just do automatically for me
• X trends follower: connect to the Grok API and continuously monitor trends in your specific niche. When one presents an opportunity for an app, build it automatically
• Content researcher: Clawd looks at all your content channels, finds your direct competitors, then continuously monitors them, texting you directly when they post content that performs significantly better than normal
If you don’t find any of these use cases life changing then you are using the internet wrong
English

@JarredKenny @openclaw What's your monthly API spend look like running 3 of these? And are you on a higher Anthropic tier or just standard Tier 1? Trying to figure out if my rate limit issues are config problems or just need to spend more to unlock better limits
English

@Shpigford @cathrynlavery @openclaw I have 3 running. 1 Chief of Staff and 2 developers. Me and the COS shape work and plan it in beads, the other 2 work it. They all coordinate in beads and in Slack.
English





