mstank

This is the standard claim by the Vucic regime and his media, still haven't seen any evidence. Please share if you have any.

Built the same hooked into Linear and using cloudflare sandboxes running actual Claude code / codex harnesses. Works incredibly well with latest gen models.

I used to relate to this article quite a bit. In the last 3-4 months, not so much. I've found that the latest models -- Opus 5.5, Astra, etc. juggle multiple tasks, delegate exceptionally well and are very good at working independently.

I still occasionally have issues with open-weight models, but the frontier labs have solved the above for most use cases.

Well, think of the near-future when tokens are so cheap that they’re not worth to meter.

Exactly this. It’s a very effective way to integrate your app into Claude/openai.

I was anti-MCP at one point when it was eating up a substantial amount of context in Claude code. That’s largely been fixed now.

From my perspective, they are a great way to wrap an API for agent consumption. I can see a future where every major commercial or service website (think airline websites) have an MCP your agent can use to check flight status, rebook, or check you in.

Just realized this was written in 2023. Can’t believe how wrong we were about AI back then.

It sounds like LLMs were pretty useful to them…

This is a strange newsletter post. It’s harping against AI but seems AI-written itself.

Its ultimate conclusion:

“I’ve come to the conclusion that a language model is almost always the wrong tool for the job.

I strongly advise against integrating an LLM or chatbot into your product, website, or organisational processes.”

Seems so obviously biased that I can only understand it with the context that the writer is trying to sell their book for €35

I assume as well. I’m concerned that it’s in development hell. Sean mentioned that they’ve been working on it for 7 years.

In hindsight I think the great thing about NMS was that it shipped in such a raw state and they continually improved it based on community feedback.

I have faith though —- they know a lot more from building NMS and managing the community. They absolutely know what a good game feels like.

Spent a lot of time in this game… The team is excellent and they ship incredible ambitious work.

I really wish they would just focus 100% on Light No Fire.

I’ve yet to see a rational argument for how we go from super intelligent LLMs to human extinction or extermination.

I understand that some smart people are worried about it. I just haven’t come across a believable or understandable argument.

My mom was diagnosed with borderline stage-4 pancreatic cancer. Fortunately she had an aggressive surgeon willing to do a Whipple procedure, and survived almost 4 years after a 4-6 month prognosis.

We were incredibly lucky to even have that time with her. Pancreatic is one of the worst cancers someone can get — both for survival and quality of life.

I’m very happy to see that we’re finally making meaningful progress on treatment.

I have an open question for software engineers out there:

As someone that has never studied CS but has written basic code most of my life (accelerated now with AI), where is the best place to learn software engineering fundamentals?

If anything, Iran has proved that is what they should be doing right now.