yshamrei

Will there be a battle? =)

I think Chris Olah is obviously a huge enthusiast of his work and sincerely believes that what he is building will benefit humanity. At the same time, he is influenced by his environment and goals. He dreams that new technologies will invent something that significantly improves the lives of people who do not even care about these technologies.

I also think Pope Leo XIVs probably does not deeply understand new technologies and AI in general. But his role is to be cautious about anything that could potentially be used against humanity’s interests. And honestly, despite the good intentions of inventors, nobody can predict how humanity will ultimately use these technologies. AI is already using in wars. And in general, the Church has historically been cautious about progress in almost any form.

What definitely unites both Chris Olah and Pope Leo XIV is faith. Faith in their goals and ideals.

Won’t we face an economic decline if we continue reducing the work week even further?

It looks very promising! Is there any plan to implement a ralph-loop inside?

In 2026, the number of mobile applications in the App Store and Google Play increased by 60% year over year, largely because entry into the market has become much easier thanks to AI.

I would like to go back to 2009 =) The world was definitely simpler, and Bitcoin was cheaper =)

I can’t even imagine why Anthropic would need Atlassian. Atlassian doesn’t even have an MCP server built in—you have to set up an external one.

And Anthropic could build something just as good using its own tool with blackjack and hookers. (In fact, forget the park!(с))

There are two issues:

- To build a centrifuge in space of sufficient size, you need to solve the problem of delivering a large amount of materials to orbit, because it has to be hundreds of meters in diameter at least.

- Such a centrifuge will create a gyroscopic effect, and the station will quickly become very difficult to control.

My three rules:

- A delay of more than one month without justification = immediate suspension of service.

- If the service was suspended due to non-payment, next collaboration only continues with full prepayment for the next month.

- Transfer of intellectual property and copyrights only after final payment.

good code do not earn money =)

Isn’t any flight into space risky? I doubt that the first flights were safer than this one.

It’s getting more and more addictive! I’ve already launched 53 plans, and there are more than 40 ahead!

It has already consumed so many of my tokens that it would be enough to rebuild a small town.

My personal recommendations:

- Enabling parallel Codex review in the settings significantly improves quality, but increases Claude token usage by about 30%, because they often argue about style rather than substance.

- I enabled the use of maximum-capability models. This significantly increased costs, but also improved quality. - From the very start of a project, make sure to give an instruction to cover the entire codebase with all types of tests (from units to e2e tests).

- Plans can be executed in one “batch” sequentially if they do not conflict with each other—just ask Claude to write a script.

- After each plan, make sure to run all tests and migrtions.

- After each batch of plans, do a deployment and manual visual testing. Otherwise, something that breaks once will cause further issues down the line.

- One-way Telegram integration is useless—knowing that something ran or failed does not really help.

- It adds Claude as a co-author in Git. This is not a problem for me, but it might be worth disabling for others.

- With each next plan, the cost keeps increasing because the solution becomes more complex.

- Splitting the system into microservices is the only way to handle the multiplied growth in complexity and cost.

- It can write not only code, but also texts and templates. I just haven’t tried images yet.

It’s impossible to stop!