Hacker News Reader

richardwon LeCun has "zero concerns" about AI wiping out humanity, recent "rogue" incidents

100% LLM’s are very unlikely to get there. They’re fundamentally not suited to thinking like we do. They work on the abstraction of what we’ve written down, which is a good trick but barely hold it together when things get hard/novel.

However, all the confident “it’s fine” votes assume we never invent a better architecture than LLM’s. Given the level of investment and race between countries, it’s not a reliable bet. It’s much, much harder to guarantee safety than it is to find ways it could go wrong.

richardwon Gemini 4 Argon

Given the spend requirements to stay on the leading edge and the speed (and with low cost) that others catch up, the economics support a fast follower model unless you get some benefit from being a pioneer. So far nobody has received a permanent benefit from being ahead.

Chinese models are barely behind the leaders. Google can catch up anytime they hit the gas. I think they’re intentionally spending less, and when this crazy race burns out they can play their cards.

richardwon Show HN: HN.watch – Videos of all Hacker News posts

https://news.ycombinator.com/item?id=49836374

Main post and comments have a few

richardwon Sonnet 5.5

API. Get significantly smarter than Haiku at lower cost than Opus.

richardwon Feature Request: Support AGENTS.md

My shorthand is builders vs extractors.

richardwon Are AI Labs Pelicanmaxxing?

And a whole universe of random tests got baked into the AI’s training data. Websites of antelopes driving trains and hammerhead sharks swinging in a tyre swing were created. It was a short while until AI became so focused on animals that it gave up competing with developers. Life became sane again.

richardwon Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

The AI labs have been subsidising. When they try turn a profit, people will move to the fast followers. The only people that won’t are those that compete on leveraging the very latest models and even then, once spend and scale goes to the cheaper providers, we’ll see deeper research from those providers too. Think “PC compatibles beat IBM, Sun, SGI eventually”.

richardwon Five US tech giants' hidden debts soar to $1.65T on opaque AI funding

If the US companies need trillions to barely beat Chinese companies spending billions, despite a multi year head start...

richardwon Grok 4.5

If I had to summarise Google’s effort it would be: stay close but let the others burn themselves out. Position for the long game until you see something worth betting the company on.

Apple similar, without the “stay close” bit.

richardwon 1.38 Millimeter Microcontroller

I made something to ping an AWS service to tell me the uptime of my internet connection. The idea was to sprinkle them around our area, connected to various home WiFi’s, and get a better triangulation of outages. Eg is whole pipe out, just one ISP etc.

I made and tested it but didn’t care enough to continue.

richardwon Marfa Public Radio Puts You to Sleep

Sean Carroll’s Mindscape for me

richardwon Claude Tag

How much do you think it’s holding them back? Market share seems to be surviving the lack of quality vs the other players.

Or possibly: they’re focusing where it matters?

richardwon John Jumper to join Anthropic

I think Google just needs to keep its foot in the door and let the other two spend their way into oblivion, channeling “AGI or die trying”.

richardwon Launch HN: Drafted (YC P26) – Models for residential architecture

The benefits were in communication and relationship arbitrage? Surely both of those can be automated over time.

This is just one aspect but it’s still useful. Many people want to see a house and say “please help me make that”. In Australia there’s a set of house patterns that reduce the overhead of just landing a design and pushing it through the admin hurdles.

richardwon Statement on US government directive to suspend access to Fable 5 and Mythos 5

There’s probably a massive Chinese bot net scraping models from within the US already. If not there soon will be.

Anthropic: your next ad writes itself. Nobody else is worth restricting.

richardwon Shall we play a game? My AI nuclear simulation

I generally accuse LLM’s of having no sense of value. The machine will make a complicated plan but entirely lose sight of eg the fact that response time matters to humans.

Not always, but enough that I consider it a thing to fire in a direction, not a thing that aims.

richardwon I think Anthropic and OpenAI have found product-market fit

I assume the bet is that as you swap humans for machines, this pays for itself. Swap entire devs and teams and frankly, managers, and you make up a lot of 5%’s fast.

If it works. And I’m not sure who is going to buy the stuff the machines produce, but shrug. Presumably some bots click ads for NFT’s that other bots generate.

richardwon How OpenAI delivers low-latency voice AI at scale

Hard problem. I find myself adding in filler to stop the thing from jabbering.

I also think it spends most of its iq on sounding good rather than thinking about the problem. “Yeah absolutely I can see why you’d like to…” etc. This is likely because it’s on a timer and maybe voice is more expensive to process? Text responses spend more time on the task.

richardwon The Social Edge of Intelligence: Individual Gain, Collective Loss

Not sure if you remember this chess game. 1 man vs 50000. Quite an amazing outcome.

https://en.wikipedia.org/wiki/Kasparov_versus_the_World

richardwon The AI industry is discovering that the public hates it

> The easiest way would be a straight tax on AI usage, and using that tax to pay a universal basic income

Problem for jobs is that there are 200 countries and all the earnings will go to a few. Universal basic income for everyone? Or just the US?

Who gets to keep their house locations in a new fair world? The person whose parents bought in the right place 50 years ago? Who pays the money these models earn, if nobody clicks ads or does a job? What is income for if we don’t work and can just ask the AI for everything we want?

What happens when the super smart AI comes up with “better” (more fair, consistent, etc) answers than you think you have to questions like the above? What if they end up socialist? Do we force it (and invite risk it escapes and fights us for the greater good) or give in to the presumably more thorough reasoning?

richardwon Sabotaging projects by overthinking, scope creep, and structural diffing

That’s how I do side projects.

richardwon Amiga Graphics Archive

The cost between an A500 and a VGA-enabled PC in 1987 ($699 vs $3500-ish?) would have put them in such different categories and customer segments that they would rarely interact.

I remember seeing a PC one of the rich kids brought to boarding school in 1990 and realising it was just crisper than my A500. The PC’s in the school lab were all green and orange screens with one colour CGA, so this was quite a surprise. Still took me some time to accept reality :)

richardwon Claude Code Routines

I’m moving away from Claude for anything complicated. It’s got such nice DX but I can’t take the confident flaky results. Finding Codex on the high plan more thorough, and for any complicated project that’s what I need.

Still using Claude for UX (playgrounds) and language. OpenAI has always been a little more cerebral and stern, which doesn’t suit those areas. When it tries to be friendly it comes off as someone my age trying to be a 20-something.

richardwon Pretext: TypeScript library for multiline text measurement and layout

I did ~this in the 200X’s for a C# todo list, not nearly as polished but it was still So Much Work. Filed under things that should just work already.

richardwon Unsloth Studio

Daniel is a very impressive guy. Well within the realm of “fund the people not the idea” that YC seems to do. Got a few bucks from them and probably earning from collaborations etc. Odds of them not figuring out a business model seem slim.

https://www.ycombinator.com/companies/unsloth-ai

richardwon Claude March 2026 usage promotion

I have this as a skill Claude created to run the rest. It mentions each skill in turn, see below. It’s not deterministic but it definitely runs each skill and it’s raised a bunch of issues, which I then selectively deal with. Where I can, once an issue is identified, I make deterministic tests.

Text includes:

Invoke each review/audit skill in sequence. Each skill runs its own comprehensive checks and returns findings. Capture the findings from each and incorporate them into the final report.

IMPORTANT: Invoke each skill using the Skill tool. Each skill is independently runnable and will produce its own detailed output. Summarize findings per skill into the unified report format.

4. Architecture Health

Invoke: Skill(architecture-review)

Covers: module boundaries, cross-module communication, dependency direction, infrastructure layer rules, hexagonal architecture compliance.

5. Security Health

Invoke: Skill(security-review)

Covers: hardcoded secrets, SQL injection, authorization, HTTPS, CORS, input validation, authentication patterns.

richardwon Claude March 2026 usage promotion

$200, over December it was doubled. I tried my best in between family time and friends to burn a hole in it. Never got near doing so.

richardwon Claude March 2026 usage promotion

I found that when I have “infinite” tokens my behaviour changed. 3-5 tabs so I’m not waiting, free side quests, huge review skills over whole codebase, skills that wrap 10 other skills. It’s like going from expensive data to uncapped.

I think these token doubles are there to kick you into a abundance mindset (for want of a better term) so going back feels painful. Stop counting tokens, focus on your project and the cost of your own time.

richardwon OpenAI raises $110B on $730B pre-money valuation

“In December, Gemini traffic increased by 28.4% month-over-month, while ChatGPT traffic decreased by 5.6%”

https://www.businessinsider.com/openai-chatgpt-vs-gemini-web...

"What's you number one piece of hiring advice?"

"Hire for slope, not Y-intercept. This is actually my number one piece of life advice."

-@sama, who I’m generally a big fan of. But the job is now harder

richardwon Tesla registrations crash 17% in Europe as BEV market surges 14%

And China is likely to do to Tesla robots what they’ve done to the cars. I assume the bans will be incoming, because the US can’t have millions of Chinese kung fu robots sitting about pouring tea, waiting for critical mass.

https://youtu.be/gfJTX1Y0ynM