@katibmoe You made it sound like you are opensourcing the actual auth code but all you did was opensourcing the tool info which were already present in each apps documentation
English
Deepak Sangle
187 posts
Deepak Sangle
@_deepakss_
Building something exciting, YC S23, IIT K CSE graduate
Katılım Ocak 2021
270 Takip Edilen33 Takipçiler
Introducing One.
The simplest way to connect and monitor AI agents to hundreds of apps.
And we’re open-sourcing the world’s largest integration database powering it: 47,000 agentic actions across 250+ apps.
RT + comment “One” for access & 1M free API requests/month.
English
@tibo_maker No one does brand deals on such ai accounts dude. No sane person buys things either. There is no particular audience just random people subscribing to it just because it’s funny. Only monetisation strategy is ads
English
in just 9 days, this TikTok account hit 3m followers
posting AI fruit characters on Love Island
every single episode gets 10m+ views. total: 300m views, 23m likes
and here's the thing nobody's saying out loud: this is a monetization engine
3m followers = brand deals, merch, digital products
the creator is already building an audience that will buy whatever they sell next
the best part is that anyone can replicate this exact playbook
the format is simple:
- pick a concept people already love (reality TV, drama, nostalgia, etc)
- make AI characters do human things
- drop episodes daily
- let the algorithm do the rest
this is exactly what Revid is built for, by the way
English
@khushiirl IMO its equally worse than other AI reviewers. It didn’t killed any such startup and probably won’t
English
Wake up guys… Claude just wiped out half the SaaS market again
Claude@claudeai
Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.
English
People be claiming this features killed startups which have specialized in only code reviewing. What a joke
Claude@claudeai
Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.
English
@cryptopunk7213 Even with this, humans still need to review the PR. AI cant find bugs that humans can. Whatever time it reduced, other AI reviewers also reduced it.
English
this is fucking ridiculous lol - anthropic just killed a $50B industry with a single feature (again):
- companies pay $50K a year to scan their code for vulnerabilities.
- anthropics Code Review does it for you in minutes for a fraction of the cost.
- deploys multiple agents to hunt for bugs in your code. internal results show its amazing (84% hit rate on 1000+ line code base)
for comparison: anthropic cost = $15-25 PER review, trad competitor cost = $99+
complete fucking no brainer. watch the appsec stocks react to this one
Claude@claudeai
Introducing Code Review, a new feature for Claude Code. When a PR opens, Claude dispatches a team of agents to hunt for bugs.
English
Makeable's demo video is out!!!!
It lets you
- Add recipes from instagram / tiktok / youtube or any random website in one click.
- Add them to your meal plan
- Auto generate complete grocery list
- After shopping, move them to your pantry automatically or using our Barcode scanner
- And the best part, use Voice AI to instantly get any help cooking
youtube.com/watch?v=51NKkH…
#Shipyard2026 @RevenueCat
YouTube
English
AppSumo's giving away a Claude + Mac + Lovable Stack 🔥 #giveaway
kingsumo.com/g/1glqwjm/the-…
English
Anthropic had 16 AI agents build a C compiler from scratch. 100k lines, compiles the Linux kernel, $20k, 2 weeks.
To put that in perspective GCC took thousands of engineers over 37 years to build. (Granted from 1987 - however) One researcher and 16 AI agents just built a compiler that passes 99% of GCC's own torture test suite, compiles FFmpeg, Redis, PostgreSQL, QEMU and runs Doom.
They say they "(mostly) walked away." But that "mostly" is doing heavy lifting.
No human wrote code but the researcher constantly redesigned tests, built CI pipelines when agents broke each other's work, and created workarounds when all 16 agents got stuck on the same bug.
The human role didn't disappear. It shifted from writing code to engineering the environment that lets AI write code.
I don’t know how you could make the point AI is hitting a wall.
English
Goodbye Heroku, you changed the world for the better.
I wrote about Heroku back in 2022 if you want to relive their story: leerob.com/heroku
Heroku@heroku
Heroku is transitioning to a sustaining engineering model focused on stability, security, reliability, and support. Heroku remains an actively supported, production-ready platform, with an emphasis on maintaining quality and operational excellence rather than introducing new features. We know changes like this can raise questions, and we want to be clear about what this means for customers. There is no change for customers using Heroku today. Customers who pay via credit card in the Heroku dashboard—both existing and new—can continue to use Heroku with no changes to pricing, billing, service, or day-to-day usage. Core platform functionality, including applications, pipelines, teams, and add-ons, is unaffected, and customers can continue to rely on Heroku for their production, business-critical workloads. Enterprise Account contracts will no longer be offered to new customers. Existing Enterprise subscriptions and support contracts will continue to be fully honored and may renew as usual. Why this change We’re focusing our product and engineering investments on areas where we can deliver the greatest long-term customer value, including helping organizations build and deploy enterprise-grade AI in a secure and trusted way.
English
@adxtyahq its so slow man, everytime i need to do something I close the tab and reopen again
English
@housecor ikr! For me, the major downside of using claude code was it wasnt intuitive to see the diffs, and when I am not videcoding, I cant trust AI so this kind of diff is perfect.
English
Using Codex today instead of Claude Code.
I like how concise the output is.
I can easily do diffs by just expanding next to each impacted file. And the diffs are nicely code colored, so I don't feel like I need to jump into an IDE.
English
@RhysSullivan Off topic but you can enforce security even after disabling RLS in your application itself. It’s actually a better way to do that so you don’t get vendor lock in to supabase
English
the first vibe coded app i've actually dug into had no RLS rules and all their customer data exposed
be very careful about what you're signing up for / using these days, people don't know what they're doing
Rhys@RhysSullivan
i can't deal with vibe coded ai slop man we've got this incredible technology that most people have no idea how to use correctly
English
@GergelyOrosz Postgres has timestamp with time zone as a data type. Just use that and render the data based on local time zone in FE
English
Dates remain an amusing challenge in software.
Got a complaint from a customer that they bought a subscription at 6pm their time on the 31st Jan… but got a receipt with the date as 1 Feb. This is wrong - and they are right!
But from the server’s POV, the date is right!
English
English
@MichaelThiessen Why would you have to leave your IDE when there is in built terminal
English
Switching to neovim now so I don't have to leave my IDE and can edit files with syntax highlighting.
English