Hacker News: mstank

New comment by mstank in "Why are coding agents so dumb?"

mstank — Sat, 10 Oct 2026 05:16:05 +0000

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

New comment by mstank in "Why are coding agents so dumb?"

mstank — Fri, 09 Oct 2026 20:39:10 +0000

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.

New comment by mstank in "MCP was always a bad idea?"

mstank — Sun, 20 Sep 2026 20:34:34 +0000

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

New comment by mstank in "MCP was always a bad idea?"

mstank — Sun, 20 Sep 2026 20:31:43 +0000

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.

New comment by mstank in "The LLMentalist Effect (2023)"

mstank — Sun, 20 Sep 2026 13:24:17 +0000

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

New comment by mstank in "Chat-based Large Language Models replicate the mechanisms of a psychic's con"

mstank — Sun, 20 Sep 2026 13:17:15 +0000

It sounds like LLMs were pretty useful to them…

New comment by mstank in "Chat-based Large Language Models replicate the mechanisms of a psychic's con"

mstank — Sun, 20 Sep 2026 13:14:34 +0000

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

New comment by mstank in "No Man's Sky Cosmos"

mstank — Wed, 09 Sep 2026 17:57:31 +0000

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.

New comment by mstank in "No Man's Sky Cosmos"

mstank — Wed, 09 Sep 2026 16:07:10 +0000

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.

New comment by mstank in "Anthropic researcher says more than 10% chance AI "could kill all humans""

mstank — Wed, 09 Sep 2026 15:29:06 +0000

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.

New comment by mstank in "FDA approves first in class targeted therapy for metastatic pancreatic cancer"

mstank — Wed, 26 Aug 2026 21:04:59 +0000

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.

Ask HN: Where to learn software engineering fundamentals?

mstank — Sun, 16 Aug 2026 09:15:14 +0000

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?

Comments URL: https://news.ycombinator.com/item?id=49318324

Points: 14

# Comments: 7

New comment by mstank in "Software Engineering fundamentals matter more"

mstank — Sun, 16 Aug 2026 09:12:19 +0000

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?

New comment by mstank in "The Iran War Is a Whole New Level of Quagmire for the US"

mstank — Sun, 16 Aug 2026 06:47:58 +0000

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

New comment by mstank in "Astronauts describe persistent 'observer' sensation after 6 month missions"

mstank — Tue, 28 Jul 2026 01:06:19 +0000

Your comment lead me down a rabbit hole of space micromanagement. OSTPV (onboard short-term planner viewer) is the software they use to basically schedule every minute of your space flight. Basically every day someone from earth decides what you do, when you eat, when you exercise and will make changes in realtime.

Great read here with a video of someone using the actual software: https://blogs.esa.int/iriss/2015/09/09/playing-with-playbook...

New comment by mstank in "Inkling: Our Open-Weights Model"

mstank — Thu, 16 Jul 2026 02:25:09 +0000

Do you think American companies will secretly distill frontier models to build open weight ones?

New comment by mstank in "Green card seekers must leave U.S. to apply, Trump administration says"

mstank — Sat, 23 May 2026 06:04:07 +0000

They obviously know how unpopular this is, or else they wouldn't be releasing on a Friday night. This is so unimaginably disruptive, I wonder who inside the administration is suggesting this.

New comment by mstank in "GitHub is investigating unauthorized access to their internal repositories"

mstank — Wed, 20 May 2026 00:27:29 +0000

Is it just me or is this happening way more frequently in the last 4 or 5 months? Coincidently around the same time the models got a lot more capable?

New comment by mstank in "AI is too expensive"

mstank — Tue, 19 May 2026 17:06:21 +0000

I think the opposite is true. To dethrone the top tech company, you need to be able to spend much less than them, at higher efficiency and faster growth. Google didn’t catch up to Microsoft and Apple by spending more, they caught up by developing business lines and flywheels that were much more capital efficient.

If it’s a spending game, the incumbent has a huge advantage.

New comment by mstank in "Can you stop beans from making you gassy?"

mstank — Sat, 25 Apr 2026 21:39:09 +0000

I always found it I eat them consistently, they would make me less gassy. But only after a couple of weeks.