Laura Roeder (@lkr) header
Laura Roeder (@lkr) profile picture

Founder at @byPaperbell, Exited MeetEdgar Anti-hustle poster child I blog at https://teapawt.org/t.co/1RWo9V0MJd 🇬🇧

Brighton, England
Joined April 2008
Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)Photo by Laura Roeder (@lkr)
I couldn't figure out why I've never seen this Turns out it isn't on teams accounts A team account has definitely made it easier to get ai usage across our team - for example we made a customer data lookup plugin that our CS team can access But I'm gonna have to go back to a standalone account as my daily driver and just pay for both, it's too annoying being behind on all the features
We've made some big updates to Projects in Claude Code! In a project, Claude coordinates your tasks across parallel threads. The coordinator is now much more proactive. It answers your questions in the project chat and gives you updates on the status of your ongoing threads.
5
17
7,108
Know how its impossible to search X articles? But a lot of them actually contain super useful breakdowns? Grokbot solves this! I have a specific X research agent Like when I was curious about @wickedguro's X article strategy it researched it for me finding all the actual articles, and other companies potentially running the same playbook
4
8
1,114
ok thought I was really good at having claude try absolutely everything but this never occurred to me
I would suggest everyone to try and and make a new font using Claude it works so fucking good and u don't need to pay for commercial fonts anymore maybe i should drop a tutorial/skill on this
1
9
1,807
I don't give grokbot access to my email, instead I created its own assistant gmail account to use This account is able to access my calendar the way a human assistant would (you could also give it delegate email access though I have not) I use a gmail with a version of my name so that it can send emails as me without getting dismissed as an ai bot I also have rules set up in my email to auto-forward certain types of emails to it, like anything from my kids school The account initially got banned from gmail pretty soon after I created it - I appealed and told gmail it was an account for my personal assistant to use, and it was reinstated and has been fine since Sometimes its annoying have to fwd specific emails to it instead of it just being able to read any email, but so far its worth it to me for the security peace of mind
4
10
1,624
omg what if claude actually moderated the meeting??? actually start on time, tell Jim he already made that point 10 minutes ago, tell Sarah no one is talking about that, tell Tom to stick to the goddamn point GLORIOUS
Introducing Claude Meetings: add Claude to your team’s video call and it builds docs, whiteboards, and other artifacts with you while you’re still talking. Starting to roll out in beta on Team and Enterprise plans.
12
6
1
166
20,552
also true for grownups I hate that the standard length workout class is an hour, it truly does not need to be that long
Four kids now from age 12 to 2. My biggest regret is underestimating how rapidly they can develop skills with even 5-15 minutes a day of focused effort. School makes you think a reasonable learning period is one hour. That is way too long. Even 5 minutes stacks up quickly.
3
9
1,451
if you're a heavy ai user your workflows likely have these kinds of problems at this point remember to keep improving them
1
7
1,477
my current dumbest ai process is my CTO and I email each other messages copy pasted from our respective claude codes (when claude is working something and needs answers / work done from dev) whats the simple fix for this?
40
1
2
22
9,362
makes total sense to anyone who has set foot in a don quijote store
I will never understand why Asian UI is so noisy, distracting and simply ugly
1
10
1,980
truly one of the weirdest aisles to foreigners coffee creamer ISNT EVEN A PRODUCT IN THE UK
125
16
11
1,648
181,174
ok I'm gonna start sharing grokbot of the day first a simple one that any parent should have mine is called "school stuff" school emails get auto forwarded to grokbot and it adds things to my calendar
9
1
1
17
1,310
Laura Roeder retweeted
There's also no reason to emulate massive organizations when you're small. The scale is off, the lessons are wrong, the insights don't fit. If you're interested in following a groove, find a fresh one that's closer to your size, not a huge one in dried mud.
59
23
9
343
49,423
The ease of migration is definitely a huge risk to SaaS now Migrating all of our complex, trigger based email automation to a new platform used to be a project that was too prone to disaster to consider Now I know AI would do an excellent job of it in one day
7
1
23
1,680
Just came across MadeThis it's like a "run your whole business with AI tool" I have a hard time believing these will last, it just seems like anyone willing to undertake the learning curve and who actually wants to use one will very quickly just use chat/claude instead I know most people have much less AI willingness, but it seems like you have to have a LOT to adopt something like this in the first place, so why not go straight to the source Am I wrong?
2
1
4
870
I don't understand getting pitches for something I just said I already solved Like I mentioned on here I gave my grokbot its own email (before that was a native thing so its now even MORE solved) So I now regularly get DMs saying that have a saas that gives grok its own email
9
9
1,384
Where's the AI for when I forward an alert to someone on my team with the "just making sure you got this too"
663
Catch 22: If Anthropic cures Autism, what happens to Anthropic?
Anthropic CEO: “If today we look at things like cancer, Alzheimer’s, heart disease, mental illness. These will be relics of the past in. I think, less than a decade. I believe that the company which gets the risks right will also be the company that has the license to operate that society trusts and society believes can build the benefits in the right way. I think if we do this right, we can create an age of miracles where humanity is able to solve problems that have eluded us for millennia. We have to make sure that all the risks, all the ways that things can go wrong with this technology, we very carefully address those risks as we bring the benefits, and as we have a viable business at the same time”.
131
199
27
6,966
248,533