agotterer

I subscribed to Kagi for a few months and really wanted to stick with it. For general web searches the results were exactly what I was looking for. It was the lack of local/location based search that kept sending me back to Google.

I used Vivaldi for many years and was a huge advocate. The problem for me was the browser got too bloated and buggy. They kept adding functionality that for me wasn’t necessary. For example: built in Proton VPN support, calendars, email functionality, notes, a game arcade. I don’t want any of that bundled in my browser. I want my browser to be lite weight.

I eventually switched to Edge a few years ago because it was nice and lite. Now I’m seeing the same pattern play out as they add copilot, shopping, and rewards programs.

What browser should I check out next? Some must haves: workspaces, vertical tabs, and chromium extension support.

Zapier also has a free product which works well - https://zapier.com/zappy

I’m a little behind on email, I’ll reply later today.

I’ll answer some of the legal right now. First, we are at every event. Not sure how much it matters legally, but we are there as hosts and to drive the feeling of community. Without us, I don’t think the community has the same feel.

We also have an unbelievably respectful and mature community. After over 70 seatings we’ve never had an incident. We also have a code of conduct document we send all new members.

Second, we setup an LLC to shield us personally from legal liability.

Third, not to say that it shields us, but the restaurants also have insurance and are a better target for a lawsuit.

We are in the US, and at the end of the day anyone can sue anyone for anything. It’s just the reality and risk of the times. It hasn’t been a problem for us yet.

My partner and I divide and conquer. He focuses on front of house and I handle the backoffice.

The process starts ~3 months before the event. We start by picking a theme or region. Then contact some restaurants that fit the criteria and pitch them the event. That kicks off the back and forth on cost and menu.

Around 4 weeks before the event we send a save the date + previous event recap email. We summarize the last event and tease the next event, without giving away the actual resturant or type of food.

Over the next week we prep the invite email and payment forms. This requires putting the dishes on our menu template, research and writing about the history of the dishes, the region, and the resturant. Some of this content also goes onto our website.

Three weeks out we send the invite, which is a lottery system. Members have 5 days to request a seat and place a credit card hold. 5 days later we run the lottery (I wrote some basic software to randomize assignment, conver the card auth to capture and release any cards that didn't get assigned a ticket). Then we send an email to everyone who got in with which night they recieved and another email to anyone who was waitlisted. Everyone is added to a spreadsheet to track.

1 week before the event we send a reminder email and a last chance to cancel before the ticket is non refundable.

At the event we play host and check each guest in and say hi to everyone. Then we give a prepared ~5 min intro about the food, restaurant, celebrate any milestone members, and make any general house keeping accounments. Our 20 club members get a branded apron.

At the event we take video and pictures. Over the course of the next 4 weeks we post dish pictures with descriptions and history of the dish on our instagram. We also make a 1-2 min recap video of the event which also goes on our instagram and website.

Separate from the actual event related work we have to manage the books, handle members emails, and review membership requests. More recently we started selling shirts, so there's a little work in managing that as well.

Honestly, I can’t think of anything I would have done differently. Each stage of our growth came with some challenges and lessons. I think we did a pretty good job of internalizing and adapting. We definitely made some mistakes along the way, but nothing I regret doing and wouldn’t do again. Every mistake and lesson taught us something.

Feel free to email me if you run into any challenges. We might have already been through it!

We’ve never paid for marketing or advertising.

- We are lucky to have a passionate community who tell others about us.

- Sometimes we do shared reels with the restaurant, which helps drive some of their traffic to our social pages and website.

- There’s a few large local Facebook food groups which have driven membership.

- The largest driver of new membership came from coverage in the region newspaper. We credit that with the transition from 1 or 2 degrees of separation to people we had no connection to.

- There’s been a few influencers who have shown up and documented their experience. We didn’t pay for it. It drove a few members, but the quality of the newspaper and Facebook group members was higher.

We negotiate a per seat all in cost with the restaurant inclusive of food, one drink, tip, and tax. We sell the tickets directly to our members and add some margin on top. Average ticket is $115.

5 days before the event we lock the head count with the restaurant. At this point the ticket is non refundable (we allow transfers). Then we pay the restaurant one lump sum. At the event the guests are only responsible for their bar tab (outside the one included drink), we don’t get a cut of that.

Sometimes we have seat minimums we need to hit and eat the cost if we are short (that rarely happens). We don’t allow ordering any other food outside of what’s on our menu.

We never intended to make money. The first dinner was with 13 of our friends. We just organized the location and menu.

From there people started to tell their friends, who told others, then the local newspaper wrote about us, and people started talking about us on Facebook food groups and posting on Instagram. The community grew very organically, we never spent a penny on marketing. Most of the original 13 don’t come anymore, and we have grown into an incredibly diverse community.

Happy to chat, email is in my profile.

Most of it goes to paying for the meal. We make around a 20% margin. Our cost to operate the business is quite low, but we do invest a lot of our personal time into it. It’s a labor of love.

Our biggest cost center is when we guarantee a minimum number of seats and come up a little short. Doesn’t happen often, but when it does it eats into the margin fast.

I think there’s quite a few reasons people come. I’m just going to bullet some of them out in no particular order:

- We do the work to find the restaurant and curate a menu, story, and theme. E.g., we might go to an Indian restaurant and focus the event on only the southern regional dishes.

- Many times we have dishes that are off menu specially for our event.

- Sense of community. We have quite a few regulars who have gotten to know each other. In 2025, 45 people reached their 20th or 30th event with us. Since we take over the whole restaurant there’s a little more freedom in how the space is used. Lots of new friendships have been forged.

- When you go to a restaurant with a friend or small group, you can only order so much. We’ve had events with upwards of 25 different bites. There’s really no better way to sample everything the restaurant has to offer.

- There’s a few people who say their partner are picky eaters, so they come to our event each month to have the opportunity to be a bit more adventurous. It’s an incredibly diverse group with a lot of different reasons to attend.

A friend and I host a monthly dinner club for people interested in ethnic cuisine. We work with a single restaurant each month to create an 8-12 course all inclusive price fixe menu. The food is served family style and is authentic to the region we are hosting. We typically host the dinners on a Tues or Wed when the restaurants in our region aren’t too busy and could use the extra business.

Since 2023 we’ve been to 44 restaurants. In 2025 we served 1,099 guests and generated $126k in revenue.

https://www.deadchefssociety.com/

My interpretation was slightly different than yours. I read it as if they have no issue going to work and being paid to be a developer. However, they didn’t want to feel like they needed to constantly be leveling up and working towards the next rung on the ladder. Many companies have written or unwritten rules about leveling up or being pushed out and they screen for people hungry to grow. The author doesn’t seem interested in that trajectory.

I suppose in other industries this isn’t always expected. For example, you can easily be a mid-level accountant for your entire career without the company or industry expecting you to be on track to be their next CFO.

Maybe the author should be looking at medium/big non-tech companies that have been around a long time, have aging codebases, and aren’t innovating in the same way as as big tech or startup. I suspect they might find developers who have been there for many years and are pretty complacent.

Same here. I tried to build a super simple iOS App in antigravity and I was out of quota before it finished. The whole thing was a couple of files and a few hundred lines of code.

In 2023 a friend and I started a monthly dinner club with the goal of eating around the world without getting on a plane. We gather once a month at a restaurant on Long Island for a meal focused on a theme or region of the world. The meals are around 10+ courses and include a drink. We work with the restaurant to craft a menu that is as close to authentic to the region as possible.

Our first dinner was with 13 friends and has since grown into a group of just about 1,000 members. Last year we generated around $140k for local restaurants on off nights (dinners are on Tues and Wed when business is slow).

Now we are working on evolving into more of a lifestyle brand for people who love food. I'm currently working on our clothing line and new site, which we quietly launched a few days ago (there's still a few odds and ends to finish): https://www.deadchefssociety.com. Would love any feedback!

I use the main Claude code thread (I don’t know what to call it) for planning and then explicitly tell Claude to delegate certain standalone tasks out to subagents. The subagents don’t consume the main threads context window. Even just delegating testing, debugging, and building will save a ton context.

I replied to a similar discussion in April 2023 (https://news.ycombinator.com/item?id=35567822#35568411) about a dinner club a friend and I host in our free time.

We work with a single restaurant each month to create a 10-20+ course all inclusive price fixe menu. The food is served family style and is authentic to the region we are hosting. We typically host the dinners on a Tues or Wed when the restaurants in our region aren’t too busy and could use the extra business.

Here’s the 2024 update (I haven’t run the year to date cumulative numbers yet):

* Grew to over 900 members

* Hosting 2 seatings per month

* Served 1,300 guests

* Generated $140k revenue

I thought I read that best practice was to start a new session every time you work on a new feature / task. That’s what I’ve been doing. I also often ask Claude to update my readme and claude.md with details about architecture or how something works.

As for /compact, if I’m nearing the end of my context window (around 15%) and are still in the middle of something, I’ll give /compact very specific details about how and what to compact. Let’s say we are debugging an error - I might write something along the lines of “This session is about to close and we will continue debugging in next session. We will be debugging this error message [error message…]. Outline everything we’ve tried that didn’t work, make suggestions about what to try next, and outline any architecture or files that will be critical for this work. Everything else from earlier on in this session can be ignored.” I’ve had decent success with that. More so on debugging than trying to hand off all the details of a feature that’s being implemented.

Reminder: you need context space for compact, so leave a little head room.

I wonder how much of this had to do with the context window size? Gemini’s window is 5x larger than Cladue’s.

I’ve been using Claude for a side project for the past few weeks and I find that we really get into a groove planning or debugging something and then by the time we are ready to implement, we’ve run out of context window space. Despite my best efforts to write good /compact instructions, when it’s ready to roll again some of the nuance is lost and the implementation suffers.

I’m looking forward to testing if that’s solved by the larger Gemini context window.

Microplastics was only one of my concerns. Their “why” page does a good job explaining the benefits. https://weddellwater.com/pages/why-duo

Agreed, already on it! I put Wedell Water filters on all of our shower heads and we have a filtration system for our kitchen sink water. I’d love to get a whole home water filter at some point.

Thanks, I hadn’t considered the plastic on the pepper grinder. Guess I’ll be looking for a new pepper grinder as I continue my pursuit of removing plastic and dangerous chemicals from the kitchen. So far the pans, tupperware, and cooking utensils have all been replaced.

While not food, another not so frequently talked about plastic exposure could be clothing dryer vents pushing materials from synthetic clothing into the air. It’s likely less of a problem than the rubber tires on our cars making their way into the air. But it was something that occurred to me while cleaning out the dryer vent this past weekend.

Many news organizations use https://securedrop.org/. How is CoverDrop different/better?

Supported outlets: https://securedrop.org/directory/

Not all paid plans, just Max. Pro doesn’t get access to Claude Code.

they can't be aware of the latest changes in the frameworks I use, and so force me to use older features, sometimes less efficient

This is where collaboration comes in play. If you solely rely on the LLM to “vibe code” everything, then you’re right, you get whatever it thinks is best at the time of generation. That could be wrong or outdated.

My workflow is to first provide clear requirements, generally one objective at a time. Sometimes I use an llm to format the requirements for the llm to generate code from. It then writes some code, and I review it. If I notice something is outdated I give it a link to the docs and tell it to update it using X. A few seconds later it’s made the change. I did this just yesterday when building out an integration with an api. Claude wrote the code using a batch endpoint because the steaming endpoint was just released and I don’t think it was aware of it. My role in this collaboration, is to be aware of what’s possible and how I want it to work (e.g.. being aware of the latest features and updates of the frameworks and libraries). Then it’s just about prompting and directing the llm until it works the way I want. When it’s really not working, then I jump in.

I appreciate your thoughts and definitely share some of your sentiments. But don’t underestimate the value and importance of continuing to be a creative.

Something I’ve been thinking about lately is the idea of creative stagnation due to AI. If AI’s creativity relies entirely on training from existing writing, anrchitecture, art, music, movies, etc., then future AI might end up being trained only on derivatives of today’s work. If we stop generating original ideas or developing new styles of art, music, etc., how long before society gets stuck endlessly recycling the same sounds, concepts, and designs?

I’m excited about the space and intend to keep an eye on you guys. I actually gave the opened source version of browser-use a try last week and ran into two problems:

The first, it refused to correctly load the browser tab and would get stuck in a loop trying. I was able to manually override this behavior for the purpose of prototyping.

The second, it hallucinated form input values. I provided it strict instructions on how to fill out a form and when it didn’t know what to do with an address field, it just wrote 123 Main St instead of not being able to complete the form.

The thing I really want and haven’t found in any of the browser agents I’ve tried, is a feedback loop. I don’t personally know what the final format looks like. But I want to know that what I expected to happen inside the browser, actually happened, and I want it to be verifiable. Otherwise I feel like I'm sending request into a black hole.

This a neat project and an impressive collection. I’m curious, if shes hosting streaming listening party shows is she obligated to pay royalties?

HouseAccount (https://houseaccount.com/)| Senior Product Manger | Full-time | NYC Hybrid or Remote | $165k-$215k + equity

HouseAccount aims to disrupt the $500 billion home service industry by revolutionizing and digitizing the homeowner experience. We (and our customers) firmly believe that the future of the home service industry lies in embracing technology to replace outdated and inefficient phone calls, manual scheduling, non-digital payments, and costly paper-based processes.

Founded by an experienced executive team that have been founders or exec team members at Seamless ($GRUB), Slice ($1B+ preIPO), OLO ($OLO), SinglePlatform ($TRIP), Constant Contact ($CTCT), and Good Uncle ($ARMK).

Apply: https://job-boards.greenhouse.io/houseaccount/jobs/444340400...

HouseAccount (https://houseaccount.com/)| Senior Product Manger | Full-time | NYC Hybrid or Remote | $165k-$215k + equity

HouseAccount aims to disrupt the $500 billion home service industry by revolutionizing and digitizing the homeowner experience. We (and our customers) firmly believe that the future of the home service industry lies in embracing technology to replace outdated and inefficient phone calls, manual scheduling, non-digital payments, and costly paper-based processes.

Founded by an experienced executive team that have been founders or exec team members at the following companies: Seamless ($GRUB), Slice ($1B+ preIPO), OLO ($OLO), SinglePlatform ($TRIP), Constant Contact ($CTCT), and Good Uncle ($ARMK).

Apply: https://job-boards.greenhouse.io/houseaccount/jobs/444340400...