Dylan Kenney

@bbssppllvv Cool!

@dmkenney auth and we provide tools for agents such as search_screens, search_user_flow, not just instructions

Agents make ugly UIs because they've never seen good design. We've been fixing that, 2,000 DESIGN.md files from the world's best products, structured for a model to read and learn. Colors, type, spacing, layouts and more. Free. styles.refero.design

@Mappletons @photomatt No.

I don't work on reliability & scaling at GitHub, but the people who do aren't bad at their jobs. They're dealing with unprecedented scale from agents. It's easy to shit on GitHub from the outside if you're not in charge of 30X-ing capacity within a few months. Have some grace.

Guess we need to find a replacement now ☹️

@EthanDriskill Kind of a corny picture you used there… TBH looks like something AI would choose

Claude Design (with full context and brand guidelines) vs. our actual hero design. Brand beats slop every time.

@codyschneider Sounds awesome! Please send 🙏🏻

yesterday on a live stream I made an AI agent start running an SEO campaign today article 1 is on page one the agent is - researching keywords - researching articles - writing articles for target keyword based on research + a transcript on my view about the topic - publishing a new article daily another agent every 2 weeks refreshes these articles based on the live google search console data and ahrefs data improving them if you want this get below

Just filed my taxes with freetaxusa.com instead of TurboTax... way better... and cheaper

@trq212 @ns123abc You doing this for users or for your paycheck/stock?

unblocked (you and others) it honestly just sucks to be getting tagged like this when you're literally working on a Saturday trying to debug things for users- I've done so many calls this week trying to understand peoples usage the post itself wasnt bad but it leads to a lot of people piling on and feels personal but feedback taken, blocks are too broad given my role

WTF?!

@venelinkochev Sweet!

@dmkenney no, proton/simple login works just fine

pro tip: block disposable emails at signup this + cloudflare turnstile = big impact for quality signups

Icon.com is back???

@bcherny Filed a bug report in Claude Code for that session

@bcherny Getting super aggressive 400 errors API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"Output blocked by content filtering policy"}

@HVACSEO Yes I’ve received these before and also made me do a double take. Appreciated the effort & creativity

If I’m doing a mailing campaign, I’m making it stand out. This is a good example. It made me pause to read before throwing out when sorting. If it makes me pause, it’s making other people become leads

@freyafoxtv @antinertia @Meta Yeah how??

@dmkenney @antinertia @Meta Just bans you as soon as you make one? Probably your name itself is blacklisted for cyber security ban I Can fix this

i spend $1m/mo on meta and my account got banned and i get insta banned as soon as i create a new one who knows someone at @Meta? it's urgent, i need help now

@freyafoxtv @antinertia @Meta Never. Never been able to get an account

@dmkenney @antinertia @Meta You got banned before ?

@kocalars Can’t wait to see your mugshot!

YC and Delve have parted ways. I still remember the day we took our YC interview at MIT. We’re so grateful to the community and every founder friend we’ve made. We'll continue to support every young founder striving to make the world a better place.

@karunkaushik_ And which leading cybersecurity firms did you bring in?

Read the full details here: delve.co/blog/delve-set…

There’s been a lot of allegations against Delve. But we haven’t been able to share our side of the story until today due to ongoing cybersecurity and forensics investigations. Maintaining customer trust is central to everything we do. That said, we grew too fast and fell short of our own standard. To our customers, we deeply apologize for the inconveniences caused. We take these allegations seriously and have made changes: a new auditor network, free re-audits and pentests for all customers, enhanced transparency in audit communications, and more. However, we also want to set the record straight on the anonymous attacks. The evidence we have points to a targeted cyberattack from a malicious actor, not a “whistleblower.” We believe the attacker purchased Delve under false pretenses, exfiltrated internal company data, and used it to launch a coordinated smear campaign. The posts rely on a mix of fabricated claims, cherry-picked screenshots, and stolen data taken out of context. See the link in the comments for more details. Delve was built to modernize compliance. We are not going anywhere and are committed to building what's next.

@kocalars @karunkaushik_ Lies!

@karunkaushik_ our entire team has been working day and night for the past 2 years, and it's been no different the past 2 weeks as we work around the clock to make improvements for our customers❤️