HNHacker News
TopNewBestAskShowJobs

wg0

4,941 karma · joined May 21, 2020

submissionscomments
wg0··on Claude Opus 5.5
No thanks.

I'm good with DeepSeek v4.1 set to high. It is a relentlessly "hardworking" dirt cheap model.

Told it to convert a products page (that had two different fonts based on language) from two columns layout to 5 columns on desktop and 2 columns on mobile ensuring typography is readable.

My man went into spawning sub agent which failed to drive chrome so it wrote its own chrome driver protocol server in Typescript then generated a prototype website then downloaded the images and rendered each variation in a directory taking 100+ screenshots analyzing the typography depth and then delivering detailed report and then writing the whole thing with new page layout testing it again with several dozen screenshots using its driver and then saying all good and all really was good and whole thing took 25 minutes or so (including double visual validation) because it generates token at an incredible speed.

Total cost of the above? $0.07 cents.

PS: It generates token at such a blazing fast speed that you can't recognize the words as they are being added and can't read it without scrolling and pausing even if you're Jimmy Carter.

wg0··on Grok 4.7
Who uses this model? Anyone? For what exactly?
wg0··on OpenAI's Sam Altman to Brief UN Security Council Next Week
The private equity debt time bomb is here. Then there is the bond market.

And then guaranteed bust of AI bubble. 2000 billion dollars for a single company? That too when bottom of the boat has been drilled by open weight Chinese models that are cheaper and good enough but can even be deployed locally?

In face of all that - that kind of return is not realistic.

However - good gimmick scaring UN asking for a ban on Chinese models perhaps.

wg0··on OpenJev
Important - Jev is way too different, the greatest innovation are its speed and that it is guaranteed to NOT generate a token from a given set of tokens hence you can drive state machines intelligently.
wg0··on I don't like passkeys
So where do I keep my pass keys is the problem. They are in my password manager just like another password. So what's the point of having them because effectively, the passwords in the password manager and the passkey in the password manager offer the same UX to me? Except that at least I can memorize a password by heart just in case.
wg0··on I don't like passkeys
They really are bad. Passkeys have turned out to be just another password that you cannot even memorize.
wg0··on Bend 2 and the Vibe-Coding Trap
If you have to write LAWS.bend which is pure code describing the laws then it isn't basically like those old days of writing unit tests and that too tests first hence the TDD?

So what is the unique idea here except a vibe coded compiler that generates C and everything else is handled by clang+llvm?

From README.md:

>The compiler (not kernel) is 99% AI-written and has not been fully audited yet.

Also, why the compiler is not written against and with LAWS.md so that no audit is required at all?

wg0··on Bend 2 and the Vibe-Coding Trap
Some noteworthy lines from the README.md[0]:

> - The compiler (not kernel) is 99% AI-written and has not been fully audited yet.

> - Strings are linked lists of characters, so text processing is slow.

[0]. https://github.com/bendlang/bend/tree/main

wg0··on Xiaomi Mimo 2.6 live post-training dashboard
"Stealing millennium problems" would be more complete if not accurate description. And that 99.99% of the market is not interested in solving millennium problems is the other fact.
wg0··on Xiaomi Mimo 2.6 live post-training dashboard
"Slow down this much openness in AI or we won't get our trillion dollars valuations!"

Google had this GPT long go and a wise man within Google noted:

"We don't have any maot neither does anyone else."

The AI bubble burst is guaranteed and is only delayed by IPOs.

wg0··on DeepSeek v4.1 Flash Is Now Our Best Hacking Model
DeepSeek is underrated. Basically all Chinese models are good enough for day to day coding at this point.

The 2 trillion dollar ROI on anthropic alone?

Good luck with that.

wg0··on Introducing System One Models and Jev
But the real problem in self driving isn't the decision making but object description. That is, computer vision if with cameras.

Decision making isn't that of a bottleneck I suppose.

wg0··on Introducing System One Models and Jev
Curious what your use case is if not confidential.
wg0··on Introducing System One Models and Jev
That's good.

Side note - just like most people don't need an intelligent personal assistant to manage and respond their emails and book their flights, most people also don't need smart homes. Century old toggle switches are more than enough in a 3 room apartment or 5 room house unless you have a mention.

wg0··on Introducing System One Models and Jev
Can I put it as Air Traffic Controller? With similar error rates as humans?

That would be the litmus test.

"Does not hallucinate" is not the same as "is never wrong".

So the ATC test could be the benchmark.

wg0··on CSS-Tricks in Limbo
I am concerned that what will happen to detailed technical write ups that defined much of the "technical internet space"? There used to be "CodeProject" (still is around probably) that used to have great articles on C, Windows Programming, Windows System programming and what not. Similar other sources on Web as well such as some TutPlus network.

Now with LLMs, they won't gain attention and all knowledge would be stuck in LLMs but there would be no knowledge base to train the LLMs on so... would this all collapse in a decade or two?

PS: Not anti AI rant, just a genuine open question.

wg0··on Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipher
Has anyone tried it with other models.?
wg0··on Anthropic CEO Says It's Time to Slow AI Model Advances
Then slow down your bots too please. I deployed a website last night. 10 out of 11 GB of bandwidth went to Claude bots alone with more than 90k requests.

Hypocrites hyping for the IPO.

PS: True story.

wg0··on DeepSeek launching v4.1 flash cheaper and more capable than v4 pro
What I mean is that price has been effectively halved.

During off-peak hours, the unit price is reduced from $0.007 for input cache hits to $0.003, $0.22 for input cache misses to $0.15, and $0.12 for output to $0.6

wg0··on DeepSeek launching v4.1 flash cheaper and more capable than v4 pro
DeepSeek v4 Flash with high is already a really great work horse. Reliable. But this time, not only that it is better but they are reducing the price by 50% so that's great.

I also find the DeepSeek models to be more precise than Claude models (last I used 4.7) in that I yet had not the occasion where model did something unintentional that I did not direct it to.

EDIT: Updated percentage reduction.

wg0··on Quantum battery upends the rules of charging
Not happening.
wg0··on LinkedIn CringeBot 3000
Would love to see what was it.
wg0··on US strikes $1.2B deal to pay German firm to halt offshore wind projects
Man - What exactly are these people?
wg0··on DeepSeek-V4-Flash Update
Don't know about the bench marks but I am getting Opus 4.7 level performance at fraction of cost with DeepSeek V4 Flash set to high. It is a reliable workhorse.
wg0··on SQLite in Production: Optimizing WAL Mode, Concurrency, and VFS Layers
I am obsessed with the idea of per tenant databases. But I am afraid of migrations. Has anyone tried that?
wg0··on Our position on open-weights models
Basically:

"We are in favour of 3D printers but there should be a body that tests and certifies that a 3D printer cannot print anything that can be used as weapon. Anything pointy or with a spring and recoil or... or..."

wg0··on The Kimi K3 Moment
> tied to the corrupt Trump administration that are neither the highest quality nor the cheapest

Someone is calling corrupt as corrupt. Surprising.

wg0··on SpaceX bond worth 10% less than issue price – heading for junk bond status
Is it the bond or is it the share price that also tanked below IPO level?
wg0··on Amber the programming language compiled to Bash/Ksh/Zsh
Much needed. I have hard time understanding bash.
wg0··on GLM 5.2 and the coming AI margin collapse
Everyone is declaring GLM 5.2 as something that's really a big deal.

I don't know about that but based on my own experience with Deepseek v4 Lite alone (with high effort) I have no doubt in my mind that anyone claiming such great things about GLM 5.2 must be true because Deepseek v4 already is really awesome.

← PreviousPage 5 of 34Next →