this is so good ! Great idea, not going to use it a lot but great concept

yeh no thank you very much, I would rather not join your company but you can interview my bot if you like.

technically you can ask chatgpt to return the same result by asking it to filter by year

Why as user I should get excited for ai features? Why are they selling ai so much, show me what it solves ? Nothing

$799 for this ?

We switched from jir to linear, what a fresh starts !

100% on point, classic case of drinking ai cool aid and killing what users wanted

The thing is they make the correct diagnoses of Arc's issues [1], but then instead of addressing them and doing the hard work of building a great product, they took the easy way out and started another greenfield project. How often has that ever been a good decision?

1 - https://browsercompany.substack.com/p/letter-to-arc-members-...

> How often has that ever been a good decision?

It got them acquired, so certainly it worked for them this time.

> doing the hard work of building a great product

How often has that ever been a good decision?

You're assuming that Dia is what Atlassian wanted in this acquisition, and nothing else. We don't know what things would look like if they had continued developing Arc.

Almost every successful company has got there by grinding away on hard problems. No one launches a product and gets endless growth for free. Not to say that Arc would have definitely succeeded, but to date it's been a lot more successful than Dia.

> You're assuming that Dia is what Atlassian wanted in this acquisition

I thought it was an acquihire.

They wanted Arc. The founders and others at Atlassian loved Arc. I am sure Dia is allowed to continue until it doesn’t work. Which it wont.

> How often has that ever been a good decision?

The migration to OSX or all Windows upgrades certainly payed off for those companies.

I don't think this is a good comparison. There are many startups that have succeeded developing good products, but very few that could match the success of Apple.

You missed the point, he is saying after a point vibe coddling simply doesn’t work because llms are hitting a ceiling

can someone explain like I am five?

A website owner can publish their website's capabilities or data as "tools". AI agents and LLMs like ChatGPT, in response to user prompts, can consult these tools to figure out their next actions.

Example:

1. An author has a website for their self-published book. It currently checks book availability with their database when add to cart is clicked.

2. The website publishes "check book availability" and "add to cart" as "tools", using this MCP-B protocol.

3. A user instructs ChatGPT or some AI agent to "Buy 3 copies of author's book from https://theirbooksite"

4. The AI agent visits the site. Finds that it's MCP-B compliant. Using MCP-B, it gets the list of available tools. It finds a tool called "check book availability", and uses it to figure out if ordering 3 copies is possible. If yes, it'll next call "add to cart" tool on the website.

The website here is actively cooperating with the agent/LLM and supplying structured data. Instead of being a passive collection of UI elements that AI chatbots have to figure out based on UI layouts or UI captions, which are generally very brittle approaches.

Example:

You have google docs and CMS open in 2 tabs

1. Ask to take your google doc and add it to the CMS

2. MCP tool takes the data from Google docs

3. MCP tool to convert text to CMS item

4. MCP tool to insert that CMS item

With the above you can view unique UIs for each stage as well, such as generating a table with CMS fields before accepting.

I have totally opposite experience working on large ds at uber

Would you elaborate?