Pinned Tweet
Hey friend. Can you spare a ⭐️ for a (hopefully) interesting open source project I'm working on?
github.com/ExpeditedProjects…
1
4
168
Used Opus 5.5 for the past 24 hours across ~5 projects and it sure does feel like Fable smarts but much faster.
1
5
400
If you want to try the new Opus 5.5 with Claude Code make sure that you've installed it via the native installer and not via homebrew (which lags releases).
1
2
197
It's kind of crazy how much better Claude Code is than Codex at handling and working with multiple different iterations of MCP servers.
It's not even the "future" it's literally just what I need to get through my working day.
2
1
222
Anyone have a really good way of using worktrees in dev? I've got my own per-project setup but it feels like there's got to be a better way.
4
3
727
My new sign off on drip emails is "p.s. if you reply to this email a human will answer it."
Is that actually helpful information to people signing up?
1
1
232
If you find yourself with extra AI token quota before a reset, start grinding out dependency+security updates and improving test coverage of your apps.
126
Genuinely shocking to me that some people aren't using a "fast-chat" skill with ClaudeCode or Codex.
Turns narrations into super quick decision points.
1
4
298
Working on HutchDB has been very frustrating as when try it out and get it they go "oh this is very handy!" but actually describing it has been a challenge.
Trying a new pitch. Better?
1
311
Most AI "Agent" demos are really slight and kind of underwhelming because they don't have access to persistent data storage and collaboration (to both human and other AI agents), which is why I'm building HutchDB.
Store/Fetch any arbitrary data set directly from your agent via MCP.
github.com/ExpeditedProjects… - please drop a ⭐️ on the repo if it sounds interesting.
1
174
Dealing with bots signing up for SendCheckIt only to immediately invoke the "forgot password" form to try and email bomb people.
They're also abusing the gmail dot trick to push more through. Anyone else had to deal with this?
3
317
I've been lucky enough to be in the Changebot beta and they were nice enough to ship my most requested feature: destination selection during publishing.
updates.changebot.ai/changeb…
1
123
Overall I think the codex sandboxes + permissions makes more sense over Claude's. Less friction, more freedom.
2
218
My experiments with procedural terrain generation are going really well.
I'd previously produced a nice looking meadow, but now have a really slick grimdark cobblestone as well.
147
Woke up to a support request from a site that is suffering what appears to be a supply chain attack. In production, their web app is launching a second GTM script that then loads a fake captcha that's likely stealing user sessions.
Check your dependencies!
2
219
So I've been on a similar loop to this with ExpeditedWAF support, with a few big tweaks.
I have a separate set of root cause docs that are used only by the AI. So when a new ticket comes in:
1. We run a bunch of DNS and SSL/TLS configuration tests and checks
3. We've built a set of docs that contain a mapping of: Indicator of Cause (IOC), Response Template, Related Public Docs
3. We then take all that context along with the ticket that was submitted and figure out the proper root cause and then write a draft response.
IOC --> Root Cause --> Response Template --> Draft
This combination works really well for actual identification of issues, generation of an actual non generic response, and graceful failure if it's outside of the known root causes.
Support @bot — give it access to your helpdesk software (@Bento Chat, @helpspot, @helpscout, Intercom).
If your helpdesk software does not answer tickets for you ask it to pull tickets every 30 minutes and use your docs to answer them the best it can (if you are scared ask it to ask you for review each time).
If your docs suck, ask it to pull the last 12 months of tickets and write docs for anything you haven't covered.
GOOD DOCS = GOOD BOT.
If your helpdesk software is already answering tickets for you, like in @Bento Chat or Intercom, then ask bot what items are assigned to you or have been escalated to a human.
^These tasks likely require you to console into your app or press some buttons in an admin interface so I recommend you turn that into an API and build an MCP to interface with it.
Then give @bot access to that MCP.
You can then ask your bot to do a sweep a few times per day, give you a summary/suggestions, then you just text back to tell it what to do. It will then interact with your admin MCP to get the job done.
This is what I've done and it's fantastic.
1
2
496
Live in the 757? Be sure to check out @rmcastil 's talk happening on August 27th!
Tired of arguing with AI all day? Or at least feeling like you're being pandered to?
Let's go back to friendly, face-to-face debate. Tabs vs spaces. Vim vs everything else. Claude vs Cursor. Are we doomed or not?
Come see me speak at meetup.com/757dev/events/315…
184
My friend Ernesto and his Ombulabs is running a free webinar starting _right now_ on how to use Claude safely in your business - ombulabs.ai/webinar/safely-r… - you should check it out.
1
170