barishnamazov

Why is this 404 page shared by a fresh account getting upvotes? Might as well be a social experiment...

https://archive.is/PHIPi

Sigh, I'd still have preferred a basic HTML page with hand-written succinct information instead of this crap verbosity.

You are probably confusing it with a sliding window problem. RMQ [0] is about finding the minimum value in given arbitrary subarray.

[0] https://en.wikipedia.org/wiki/Range_minimum_query

You shouldn't be using JSON for things that'd have performance implications.

Nobody really buys 8gb sticks anymore, so selling 2x8gb isn't economically great. Also, there are more factors than just density in RAM pricing, but it really depends on the vendor and chip layout design.

How is this different than kysely + kysely-codegen (or hand-made types)?

https://archive.is/Meaxn

What matters less is the mechanical knowledge of how to express the solution in code. The LLM generates code, not understanding.

I think it's the opposite -- if you have a good way to design your software (e.g., conceptual and modular), LLM will generate the understanding as well. Design does not only mean code architecture, it also means how you express the concepts in it to a user. If software isn't really understood by humans, I doubt LLMs will be able to generate working code for it anyway, so we get a design problem to solve.

I'd personally rethink about applying some advice in that section. Here's my take.

Time-boxing AI sessions.

Unless you are a full-time vibe coder, you already wouldn't be using AI all the time. But time boxing it feels artificial, if it's able to make good and real progress (not unmaintainable slop).

Separating AI time from thinking time.

My usage of AI involves doing a lot of thinking, either collaboratively within a chat, or by myself while it's doing some agentic loop.

Accepting 70% from AI.

This is a confusing statement. 70% what? What does 70% usable even mean? If it means around 70% of features work and other 30% is broken, perhaps AI shouldn't be used for those 30% in the first place.

Being strategic about the hype cycle.

Hype cycles have always been a thing. It's good for mind in general to avoid them.

Logging where AI helps and where it doesn't.

I do most of this logging in my agent md files instead of a separate log. Also after a bit my memory picks it up really quickly what AI can do and what it can't. I assume this is a natural process for many fellow engineers.

Not reviewing everything AI produces.

If you are shipping in an insane speed, this is just an expected outcome, not an advice you can follow.

You are taking to simonw, surely Claude have given him free super fast unlimited token access to nightly version of Claude 5.1 Opus.

(just joking, your posts are great, Simon!)

This write-up has good ideas but gives me the "AI-generated reading fatigue." Things that can cleanly be expressed in 1-2 sentences are whole paragraphs, often with examples that seem unnecessary or unrealistic. There are also some wrong claims like below:

The Hacker News front page alone is enough to give you whiplash. One day it's "Show HN: Autonomous Research Swarm" and the next it's "Ask HN: How will AI swarms coordinate?" Nobody knows. Everyone's building anyway.

These posts got less than 5 upvotes, they didn't make it to home page. And while overall quality of Show HN might have dropped, HN homepage is still quite sane.

The topic is also not something "nobody talks about," it's being discussed even before agentic tools became available: https://hn.algolia.com/?q=AI+fatigue

Not directly related but can't read the text on my phone. It's too thin, maybe you could increase the font weight a bit?

Also discussed here: https://news.ycombinator.com/item?id=46686273

I foolishly sat in 8.821 [0] while at MIT thinking I could make sense out of quantum gravity. Most of the math went over my head, but the way I understand this paper, it’s basically a cosmic engineering fix for a geometry problem. Please correct me if necessary.

String theory usually prefers universes that want to crunch inwards (Anti-de Sitter space). Our universe, however, is accelerating outwards (Dark Energy).

To fix this, the authors are essentially creating a force balance. They have magnetic flux pushing the universe's extra dimensions outward (like inflating a tire), and they use the Casimir effect (quantum vacuum pressure) to pull them back inward.

When you balance those two opposing pressures, you get a stable system with a tiny bit of leftover energy. That "leftover" is the Dark Energy we observe.

You start with 11 dimensions (M-theory) and roll up 6 of them to get this 5D model. It sounds abstract, but for my engineer brain, it's helpful to think of that extra 5th dimension not as a "place" you can visit, but as a hidden control loop. The forces fighting it out inside that 5th dimension are what generate the energy potential we perceive as Dark Energy in our 4D world. The authors stop at 5D here, but getting that control loop stable is the hardest part

The big observatiom here is that this balance isn't static -- it suggests Dark Energy gets weaker over time ("quintessence"). If the recent DESI data holds up, this specific string theory solution might actually fit the observational curve better than the standard model.

[0] https://ocw.mit.edu/courses/8-821-string-theory-and-holograp...

Ah, you meant I overestimate the quality of people, not underestimate. I think that really depends. I have worked with some amazing people :-)

Low quality engineering is always visible to outside. Low quality engineers using LLMs won't get any better.

This must be the fifth article I have read today (mostly from the home page of HN) that has "Enter X" where X is what they are promoting.

You clearly underestimate the quality of people I have seen and worked with.

I'm not sure what you're referring to. I didn't say anything about capabilities of people. If anything, I defend people :-)

And yes guard rails can be added easily.

Do you mean models can be prevented to do dumb things? I'm not too sure about that, unless a strict software architecture is engineered by humans where LLMs simply write code and implement features. Not everything is web development where we can simply lock filesystems and prod database changes. Software is very complex across the industry.

I'm a believer that LLMs will keep getting better. But even today (which might or might not be "sufficient" training) they can easily run `rm -rf ~`.

Not that humans can't make these mistakes (in fact, I have nuked my home directory myself before), but I don't think it's a specific problem some guardrails can solve currently. I'm looking for innovations (either model-wise or engineering-wise) that'd do better than letting an agent run code until a goal is seemingly achieved.

The turkey is fed by the farmer every morning at 9 AM.

Day 1: Fed. (Inductive confidence rises)

Day 100: Fed. (Inductive confidence is near 100%)

Day 250: The farmer comes at 9 AM... and cuts its throat. Happy thanksgiving.

The Turkey was an LLM. It predicted the future based entirely on the distribution of the past. It had no "understanding" of the purpose of the farmer.

This is why Meyer's "American/Inductive" view is dangerous for critical software. An LLM coding agent is the Inductive Turkey example. It writes perfect code for 1000 days because the tasks match the training data. On Day 1001, you ask for something slightly out of distribution, and it confidently deletes your production database because it added a piece of code that cleans your tables.

Humans are inductive machines, for the most part, too. The difference is that, fortunately, fine-tuning them is extremely easy.

I assume this is satire, but that aside -- many of my friends who entered into big tech as new grads with "unlimited pto" are indeed very hesitant to take it. They are worried that it'd affect how their managers see them. The same idea with showing up before your manager and leaving after they leave.

Likely it was an expired domain. I have seen this trend happen quite a bit with semi-popular domains, e.g., International Olympiad in Informatics 2019 official website, ioi2019.az

I'm gonna silently hope that this means we'll suddenly have extremely cheap GPU and RAM selling out in 2027. Hardware prices have gotten out of hand.

I was hoping to see some discussion about how to relieve the pressure in my back. Damn AI terms these days.

FYI, back raises have been really helpful.

Calling a Polymarket dashboard a "Bloomberg Terminal" is doing a lot of heavy lifting here.

The value of a Bloomberg Terminal isn't the UI (which is famously terrible/efficient); it's the latency, the hardware, the proprietary data feeds, the chat network, and the reliability.

Building a React frontend that fetches some JSON from an API in 2 hours is impressive, sure, but it’s not the hard part of fintech. We need to stop conflating "I built a UI that looks like X" with "I rebuilt the business value of X."

"I wrote 0 lines of code. I reviewed 0 lines of code."

This is the part that terrifies me. Generating code has never been the bottleneck; understanding it has. If you aren't reviewing the code, you are effectively introducing a black box into your stack that you are responsible for but do not understand.

While on point, I like the patterns Effect is introducing, but I have already been using them pre- and post-AI for a long time now (especially in TypeScript). It's not an innovation. We shouldn't be surprised when LLMs are better at working on robust code bases with modular design.

Nice to see a fully free app without ads. Curious, do you plan to keep it that way and make no money from Indy?

I use a self hosted HedgeDoc with Fail2Ban to deal with this. A cheap VPS + Coolify makes life so much better.

Separately, be cautious of people putting illegal content on your platform.

I have worked in software for much less than 20 years, yet I have quickly realized the same. There has been many occasions in many different settings that I have brought up a society-related problem and it simply got ignored in the conversation.

Also easily tells me the system prompt (whereas it's harder to get it from chatgpt chats).

https://gist.github.com/BarishNamazov/0324464a52cfb963f86b56...