Kelsey Petrich

Late night sesh with the Hark agent team; I'm so excited for the potential here p.s. we have some exciting tomorrow morning @hark_labs

Today I'm excited to share that Hark has raised $700M at a $6B valuation When I use these AI models today, they feel basic. They should be able to listen and talk naturally, understand vision, retain persistent memory, and become deeply personalized over time. They should be able to see the world, interact with it, and take action To build that future, the capital we raised today will be used to: → scale our GPU infrastructure → accelerate future AI model development → grow the Hark team from ~70 to 200 engineers → design and build the next generation of AI hardware The Series A round was led by Parkway Venture Capital with participation from NVIDIA, Align Ventures, AMD Ventures, ARK Invest, Brookfield, Greycroft, Intel Capital, Prime Movers Lab, Qualcomm Ventures, Salesforce Ventures, and Tamarack Global At Hark, we are building the most advanced personal intelligence in the world. Intelligence that begins to think like you and sometimes, ahead of you to offload your mental workload

@r00k @the_transit_guy Shovels.ai - not sure if this will help you at all but they have an enormous dataset of permits.

@the_transit_guy If you work for a building department that thinks this is a worthy goal, drop your email on this page and I will build this with and for you. tensecondpermits.com

Objectively, the highest-impact use case for AI is automating code compliance and permitting. You should be able to propose a townhome development and find out if it’s code and zoning compliant within 60 seconds.

@aarondfrancis Happy birthday 🎈

My kids made me so many presents for my birthday today! I got an old pair of socks, three of their stuffed animals, my glucose tabs that I couldn't find for a while, and some kids' books. Best birthday!

@aarondfrancis 🙏

In case you didn't already know, @krpetrich keeps my entire work life together with duct tape and bailing wire and I couldn't do it without her

@jasonlbeggs @aarondfrancis @n_haberkamp 😂

@aarondfrancis @n_haberkamp But we all know @krpetrich is holding you together with all the duct tape she has

It took me a couple to times to understand that he said "I've been building Solo" not "I've been building solo" But it wouldn't surprise me if both statements are true

It did run a close modal action that forced closed it after so many attempts of just trying one by one. I've changed the modal handling since and a more pure solution for handling the survey modal. Here's some of the output from the current version where it's trying the different survey options based on what answers make sense. I'll try to post another video later this weekend after I make some more improvements. [page] serene-frangipane-7fd25b.netlify.app/step2?version=3 | 40 elements | 2 modals [planner] Turn 10 [observation] Two stacked, nearly identical survey modals exist. Scrolling the top modal reveals its own enabled Submit button (e_39) after selecting the correct option; earlier disabled Submit (e_28) was a decoy or from the upper section. [action] click({"eid":"e_39"}) [reasoning] 1) Objective: dismiss the topmost survey modal first. 2) After scrolling, the option 'The right choice' (e_33) is now checked and a Submit button (e_39) appears enabled for this modal. 3) Submitting s [result] ✓ click

@krpetrich Hey there is one issue, did it dismiss the correct answer selector modal? Is skipping it allowed?

For fun, I tried to get close to a generalized browser agent for this challenge. So far it’s working with planning → reasoning → primitive browser actions, without any hardcoded knowledge of the specific pop-ups/traps in the challenge. Video below is sped up for brevity. If I keep going, the next improvements are speed + better training + robustness. cc: @adcock_brett

Agreed! It's way too slow right now. I'm trying to see if I can get the agent to just work through the challenges at a slower rate first and then add in some performance improvements. Right now the agent does one action at a time, so I'm hoping I can start doing multiple agents at once to really speed things up especially on modals.

@krpetrich I have this too, but looks like you need another 3-4x speedup. Winning the 30 levels in around 10-15 minutes has been pretty easy but getting under 5 minutes is still hard Good luck

Tried my agent on another website. And it reasoned about what to do!!

Before Solo, I’d constantly stop one project, cd into another folder, and start it up again. Not anymore with Solo!

@adcock_brett x.com/krpetrich/stat…

Solve this in under 5 minutes and I’ll offer you $500k/year in cash plus several million in equity I'm building a Computer-Use team, goal is to use computers better than humans No experience or PhD needed Instructions: 1. Solve all 30 challenges on this website in under 5 minutes: serene-frangipane-7fd25b.netlify.app 2. Feel free to use any tools or vibe code it. Provide us a zip folder with instructions on how to run the agent and reproduce your results, as well your run statistics 3. The agent should be able to solve all the challenges, use browser, and provide overall metrics around time taken, token usage and token cost. Your agent must solve this challenge in under 5 minutes Email your response: agents@brettadcock.com If you have any questions about this challenge, feel free to email us

@aarondfrancis @claudeai @saradietschy @allenwalton @RoxanaCodes So fun!!

The Unofficial @ClaudeAI Meetup was a smashing success! @saradietschy and I are gonna do it again in a bigger space next time, so keep your eyes peeled.

Respectfully, as a daughter, the highest calling is your dad texting “my freezer door bracket broke” and you immediately start measuring things like a NASA engineer. And now he has a replacement bracket.

@adamwathan nicoleweberdesign.com

Who's the best logo designer out there that can help me with a project I want to launch next week? 🙈

@slaFFik @aarondfrancis Hey - We just enabled iDEAL as a payment method. Hope that helps!

@aarondfrancis Sorry for bothering, but I still don't see it. Using iDEAL would make my invoicing/taxation so much easier :(

They say AI is the end for developers. They say the job market is gone. They say learning to code is pointless. I don’t buy it. I think we're just getting started.

@TylerCLaprade @aarondfrancis That's a great idea! Are you creating any Sentry issues manually or just responding to issues Sentry automatically creates?

@krpetrich @aarondfrancis x.com/TylerCLaprade/…

After this quick back-and-forth with @aarondfrancis at 10am this morning from a bug I DM’d him, I had an “aha”. I need to hook my bug reports and change requests into his agent loop, not his inbox.

@yasinkavakliat @aarondfrancis Nice! Is it scoped to a specific Claude project? I think we do want to maintain some gatekeeping so Aaron can decide what to address vs not. He's the owner of the architecture/app running, so I don't think we want me having full access to trying to make changes either.

@aarondfrancis Just add Claude to Slack and Kelsey can prompt it directly

Manual QA -> Slack command -> Sentry -> Claude. Dream come true.