Harish retweeted
Introducing Expand Fetch, a new way to scrape and crawl the web.
Your agent has never seen the web. No wonder it gets basic questions wrong.
Traditional Markdown APIs lose critical details. So we trained two System one models to change that:
Iris, a vision model that sees pages like you do, preserving tables, icons, and layouts.
X-Ray, a JSON model that uncovers the hidden data behind every page.
Every fetch also comes with a Wayback Machine. Every line links back to its source, so you can verify exactly what your agent saw.
Three products. One API.
On our benchmark of 1,094 questions across 326 challenging web pages, agents using Expand got 74% right. The next best API got 55%.
Available today at $1 per 1,000 fetches.
Try it at expand.ai
Harish retweeted
We’ve raised $85M for this moment.
Introducing Warp 2.0: The first AI Head of HR.
Every company is building AI to replace jobs. Warp is building AI to do the jobs no human should have to:
If you work in HR, I want you to spend time with the manager who needs help or building company culture people actually want to work at.
If you’re a founder, I want you to focus on signing clients or spending time with your family.
You shouldn’t have to figure out how to register state tax in California. You shouldn’t have to pay outrageous penalties because you don't know what a DE 9C is.
I want to make HR human again. Today, this is finally possible with the Warp Agent.
I’d love for you to see it in action: warp.co/agent
Harish retweeted
📦 Introducing Module of the Week: a new blog series spotlighting lesser-known Effect modules, what they do, and how they can help you build better apps.
First up: PersistedQueue 👇
effect.website/blog/module-o…
Harish retweeted
If you’re not reading the code, whether explicitly or through agentic inquiry, one or more of these is true:
○ You’re a beginner
○ Software is throwaway
○ You’re prototyping
○ You have no users / revenue
○ You’re taking on debt & risk
○ Your problems are basic
And btw. All of this is fine. But the reality is that models are still not at the “full autonomy” stage yet.
They make rookie mistakes, they go down bad architectural paths. I just had the best model in the world add a nonsensical 700ms delay to “settle” something and it told me “you’re right, I was cargo-culting” 🤨
I am on the camp that this need will diminish more and more. Most code is indeed going to be assembly-like. But we also have the global internet and software infrastructure riding on these models and narrative, and we have to respect that.
Harish retweeted
This requires a mindset shift
There will be slop, but if the code is logically correct, then its better to merge and have loops going that's responsible for de-slop'ing the code. I use GPT 5.5 to write all of the code and have a claude loop going that actively de-slop's the code.
Harish retweeted
still a wip but for those interested in cross domain agent to agent communication running on BEAM/OTP please follow along! input, feedback appreciated as well.
github.com/meshhai/atp
Harish retweeted
i’m hiring a Head of Platform, to join our leadership team and lead our cal.com/platform developer-focussed API and React SDK
you will directly report to @pumfleet and me, and work closely with Keith, our head of engineering
you need a ton of technical skills, but also go-to-market experience and interest
ex-founders preferred, but not required
must have managed small teams in the past
excellent english language skills, as it requires a lot of calls internal and externally
pls apply or repost 🥳
app.withrapha.com/job/1379?r…
Harish retweeted
This is false, but it might be a good thing if belief in it became moderately widespread, because then all the remaining programmers would be in it for love and not just for money.
Harish retweeted
Try every new technology and try them immediately. Yourself. Doesn’t mean you have to adopt or love every new product, but having an inaccurate mental model of the world can be very damaging.
