HNHacker News
TopNewBestAskShowJobs

richardw

4,197 karma · joined March 1, 2008

Made https://hnrepos.com/
submissionscomments
richardw··on 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.

richardw··on 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.

richardw··on 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.

richardw··on 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

richardw··on 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?

richardw··on Sabotaging projects by overthinking, scope creep, and structural diffing
That’s how I do side projects.
richardw··on 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 :)

richardw··on 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.

richardw··on 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.
richardw··on 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

richardw··on 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.

richardw··on 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.
richardw··on 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.

richardw··on 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

richardw··on 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

richardw··on Facebook is cooked
Every so often my YouTube logs out and I’m exposed to the view a “random visitor” would see. Instantly visible because it’s filled with stupid content and sexual provocation.

I manage the shit out of FB and YouTube. You need to block a few things so it stops testing a few segment ideas.

richardw··on Show HN: VOOG – Moog-style polyphonic synthesizer in Python with tkinter GUI
Got a friend who is in the high frequency trading industry and uses both Java and C#. I asked about GC. Turns out you just write code that doesn’t need to GC. Object pools, off-heap memory etc.

It won’t do the absolute fastest tasks in the stack quite as well but supposedly the coding speed and memory management benefits are more important, and there’s no GC so it’s reliable.

richardw··on AI makes the easy part easier and the hard part harder
> I view LLMs akin to a dictionary

…If every time you looked at the dictionary it gave you a slightly different definition, and sometimes it gave you the wrong definition!

richardw··on GitHub Agentic Workflows
Totally. Surely the IDE’s like antigravity are meant to give the LLM more tools to use for eg refactoring or dependency management? I haven’t used it but seems a quick win to move from token generation to deterministic tool use.
richardw··on Software factories and the agentic moment
It’s a $90k engineer that sometimes acts like a vandal, who never has thoughts like “this seems to be a bad way to go. Let me ask the boss” or “you know, I was thinking. Shouldn’t we try to extract this code into a reusable component?” The worst developers I’ve worked with have better instincts for what’s valuable. I wish it would stop with “the simplest way to resolve this is X little shortcut” -> boom.

It basically stumbles around generating tokens within the bounds (usually) of your prompt, and rarely stops to think. Goal is token generation, baby. Not careful evaluation. I have to keep forcing it to stop creating magic inline strings and rather use constants or config, even though those instructions are all over my Claude.md and I’m using the top model. It loves to take shortcuts that save GPU but cost me time and money to wrestle back to rational. “These issues weren’t created by me in this chat right now so I’ll ignore them and ship it.” No, fix all the bugs. That’s the job.

Still, I love it. I can hand code the bits I want to, let it fly with the bits I don’t. I can try something new in a separate CLI tab while others are spinning. Cost to experiment drops massively.

richardw··on France dumps Zoom and Teams as Europe seeks digital autonomy from the US
Great. There’s no reason why all countries don’t start preferring locally or regionally developed software. Of course interoperability is always a thing but there needs to be another option between “one company” and “everyone host your own instance”.
richardw··on Nvidia Stock Crash Prediction
I’m sad about Grok going to them, because the market needs the competition. But ASIC inference seems to require a simpler design than training does, so it’s easier for multiple companies to enter. It seems inevitable that competition emerges. And eg a Chinese company will not be sold to Nvidia.

What’s wrong with this logic? Any insiders willing to weigh in?

richardw··on Claude Cowork exfiltrates files
Debian. Linux. Http protocol.
richardw··on To those who fired or didn't hire tech writers because of AI
It has no sense of truth or value. You need to check what it wrote and you need to tell it what’s important to a human. It’ll give you the average, but misses the insight.
richardw··on Don't fall into the anti-AI hype
I’ve recently created many Claude skills to do repeatable tasks (architecture review, performance, magic strings, privacy, SOLID review, documentation review etc). The pattern is: when I’ve prompted it into the right state and it’s done what I want, I ask it to create a skill. I get codex to check the skill. I could then run it independently in another window etc and feed back to adjust…but you get the idea.

And almost every time it screws up we create a test, and often for the whole class of problem. More recent it’s been far better behaved. Between Opus, skills, docs, generating Mermaid diagrams, tests it’s been a lot better. I’ve also cleaned up so much of the architecture so there’s only one way to do things. This keeps it more aligned and helps with entropy. And they’ll work better as models improve. Having a match between code, documents and tests means it’s not just relying on one source.

Prompts like this seem to work: “what’s the ideal way to do this? Don’t be pragmatic. Tokens are cheaper than me hunting bugs down years later”

richardw··on Nvidia to buy assets from Groq for $20B cash
This is smart as hell. I’ve long wondered how they’d combat ASIC’s without diluting their own benefits. This gives them a bit more time to figure out the moats, which is useful because Groq was going places. This juices Groq’s distribution, production, ability to access a wider range of skills where necessary.

I expect China to want to compete with this. Simpler than full-blown Nvidia chips. Cue much cheaper and faster inference for all.

richardw··on Comptime – C# meta-programming with compile-time code generation and evaluation
Not terribly niche. All config that isn’t environment-specific and is used in inner loops or at startup. It’s even got a test for serialised values so can be used to speed your case up:

https://github.com/sebastienros/comptime/blob/main/test/Comp...

But you need to be sure you won’t want to change without compiling.

richardw··on It's ~2026 –. ChatGPT still doesn't allow email change
Or phone number. My phone is linked to one in another country. I’ve been here for 3 years.
richardw··on A Vibe Coded SaaS Killed My Team
There is enough to read between the lines. Dilbert manager has bought into a barely competent app (that they think replaces humans) in a panic because costs. They’ll learn more lessons over the next year, if they survive. The author might be a bit emotionally charged right now and is writing between some lines as they help migrate. Once they have some emotional distance they might write the fully clear article you’d like.
richardw··on Anthropic Rides an Artificial Wave
They probably used Claude because that way they don’t get blocked as fast. Websites trust Claude more. And why not use the foreign tools against themselves at presumably discounted rates (see AI losses) rather than burn your own GPU’s and IP’s.

1000’s of calls per second? That’s a lot of traffic. Hide it in Claude which is already doing that kind of thing 24/7. Wait until someone uses all models at the same time to hide the overall traffic patterns and security implications. Or have AI’s driving botnets. Or steal a few hundred enterprise logins and hide the traffic that is presumably not being logged because privacy and compliance.

← PreviousPage 2 of 34Next →