HNHacker News
TopNewBestAskShowJobs

zwaps

5,491 karma · joined June 26, 2017

submissionscomments
zwaps··on Ask HN: Did we witness the "Trinity moment" for AI?
It will not. We are unable.
zwaps··on Home alone: Remote work, isolation, and mental health
In UK and Spain, computer engineers earn the median income?
zwaps··on Ferrari Luce
“Sound waves are captured from electro-mechanical vibration in the axles“

Finally! Electronic sound is fine if it is the actual sound of the car instead of some fake recording of a v8

zwaps··on Omarchy Is Not A Distro
The author is so close. “decades of debian and it never got any traction. Why?“

Yeah! What a mystery. What could make people install omarchy or pop os over debian, arch or gentoo?

What could possibly be the reason

zwaps··on Omarchy Is Not A Distro
Omarchy!! shipping a window manager with defaults and or a terminal with a config - what an unspeakable sin.

Linux should be hard and shitty and it should break all the time! What is this newfound obsession with distros that just works and have some great setups and defaults.

Where do we end up if you can just close your laptop lid or copy paste with the same key or or or if even… gasp… the theme is automatically applied across all apps?

DHH? More like literal devil.

No sir! Let me write a blogpost post haste!

zwaps··on OpenAI and Government of Malta partner to roll out ChatGPT Plus to all citizens
Well the business model of Malta is being a tax evasion haven and access port for oligarchs.

That’s quite a difference to most other European countries, although not all.

zwaps··on Best "Brain" for Agents Is Just Versioned Folders of Markdown Files
The way this argues against its own premise is really ChatGPT like. This happens when you ask it writing about something that isn’t actually true. Which again is funny because as an AI consulting company you should have expertise to know what you want to weite about

But good news, this company also has a free ebook. I am sure it is fantastic.

zwaps··on Best "Brain" for Agents Is Just Versioned Folders of Markdown Files
This reads like an AI writing to a point an author wants to make without there being evidence.

It is completely incoherent. Apparently we just need markdown and git, but also a knowledge graph and pgvector which accounts for most of the performance.

We don’t need semantic search, because we use… hybrid search (semantic search plus bm25)???

Really bad look for an AI consulting company this.

zwaps··on Googlebook
The second feature shown in this global launch is ... widgets. Like, Windows Vista widgets. And then, I could also open phone apps but not on my phone but on my computer (because I'd want to do that) and then the remaining feature is file sync.

I am just lost. I wanna watch a documentary on how this kind of thing gets thought out and made and approved by a lot of people and then comes to being annouced as an actual hardware product.

zwaps··on Launch HN: Voker (YC S24) – Analytics for AI Agents
Maybe as a comment, you really put weight on intent classification. I am not sure why. For it to work, you are gonna need my expert domain input. And given that, I feel like the classification bit is basically solved. I wonder a bit why this is the feature you seem to put front and center (e.g. screenshots)
zwaps··on Launch HN: Voker (YC S24) – Analytics for AI Agents
how so? genuine question
zwaps··on Launch HN: Voker (YC S24) – Analytics for AI Agents
For instance, I have intent classifiers running on my traces and most tools offer some sort of analysis agents or API so it's claude sdk and go.

Maybe let's take Langsmith. Now I know my gripes with that product. How do you see it? What do you add, specifically?

zwaps··on Google broke its promise to me – now ICE has my data
If only the US would follow its laws or constitution
zwaps··on Show HN: I built a tiny LLM to demystify how language models work
I like the idea, just that the examples are reproduced from the training data set.

How does it handle unknown queries?

zwaps··on Cursor 3
Yes and no. In principle you are right.

In practice, Claude is trained on its harness and the subscription is priced to best competitors such as Cursor.

This is also why Cursor tries to finetune oss models. Otherwise its performance in the CC flavor of AI coding will just be that bit worse

zwaps··on Cursor 3
Nobody is saying your workflow is wrong, it may even be better. However it is not how people use Claude Code or what its attraction is.

What you mention as advantages and features is not something CC users use or require.

On the other hand, Claude is trained on its harness (all but confirmed by Anthropic) so CC is likely just a bit better at its level of abstraction than in cursor. And at the end, you can’t yet best the subscription.

zwaps··on Qwen3.6-Plus: Towards real world agents
The US under Trump is politically and strategically almost identical to China, and can be trusted about the same.

And then, compared to China, the US acts overtly hostile: threatening us with war, starting a war in order to collapse energy supplies outside of the US. Opportunistic beyond even China, much more hostile.

Will the US even be a democracy in two years? Is it now?

Nah man, balancing between China and the US is the only thing a smaller country can do in order not to be crushed

zwaps··on Qwen3.6-Plus: Towards real world agents
They claim SOTA but are beaten by last gen Opus om every metric?

This one seems weird

zwaps··on Cursor 3
My man, have seen the Sonnet 4.6 tho
zwaps··on Cursor 3
Let me give this a shot:

Cursor was the tool you use to pair program with AI. Where the AI types the code, and you direct it as you go along. This is a workflow where you work in code and you end up with something fundamentally correct to your standards.

Claude Code is the tool you use if you want to move one abstraction layer up - use harness, specs, verifications etc. to nail down the thing such that the only task left is type in the code - a thing AI does well. This is a workflow where the correctness depends on a lot of factors, but the idea is to abstract one level up from code. Fundamentally, it would be successful if you don't need to look at code at all.

I think there is not enough data to conclusively say which of these two concepts is better, even taking into account some trajectory of model development.

I do feel that any reason I have for installing Cursor is that I want to do workflow 1, rather than workflow 2. Cause I have a pretty comprehensive setup of claude code (or opencode, or whatevs) and I think it does everything you list here.

So, as a product engineer, you probably wanna mention why it matters that Cursor UI allows you to edit files with auto-complete.

zwaps··on Cursor 3
Claude Code is where you move up one abstraction layer. Almost everyone using it productively has spend a lot of time working on their harness, ensuring that everything is planned out and structured such that all that is left is really type in the code. This typically works without error. Before that, you interact a lot via Claude Code in whatever abstraction you feel is right.

That's basically it. You can review changes afterwards, but that's not the main point of Claude Code. It's a different workflow. It's built on the premise: given a tight and verifiable plan, AI will execute the actual coding correctly. This will work, mostly, if you use the very best models with a very good and very specific harness.

Cursor, same as Copilot, has been used by people who are basically pair programming with the AI. So, on abstraction down.

I have no idea what is better, or faster. I suspect it depends at least on the problem, the AI, and the person.

zwaps··on Cursor 3
I like cursor and its workflow as a tool, but I do wonder whether moving to cloud (I mean for lots of the cool features) will work. Yes we all GET Cursor has to make money. No one is fooled what this is about. It's also fine, the video and screenshot thing is great.

However, is this really a moat?

zwaps··on Anatomy of the .claude/ folder
This really doesn’t pan out in practice if you work a lot with these models

And also we know why: effective context depends on inout and task complexity. Our best guess right now is that we are often between 100k to 200k effective context length for frontier, 1m NIHS type models

zwaps··on Turkish Coffee? Since the 16th Century, It's in the Water
Monarchic customs are always a great source for optimized procedures and best practices, because in these places marginal costs don't matter, people get assigned to particular knowledge areas and the assumption is that quality does matter.
zwaps··on We indexed the Delve audit leak: 533 reports, 455 companies, 99.8% identical
This site also has no identifiable contact information whatsoever, making it likely illegal in many places
zwaps··on Books of the Century by Le Monde
Honestly, American lists are the same. Every decent English speaking author, plus some selections of other languages.

Any national worlds book list, and this explicitly includes US and UK lists, are heavily skewed and I mean ridiculously so

zwaps··on The happiest I've ever been
Not to contradict your conclusion but many countries definitely have an extreme shortage of new humans
zwaps··on Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)
He said why, he wanted to open source it with the mentioned exception.

I think there are also licenses that do that, and revert to full MIT after some time, but the author decided to roll their own.

What’s the problem with that? He can license it however he wants and the reason he mentions is perfectly valid tbh

zwaps··on Show HN: Sgai – Goal-driven multi-agent software dev (GOAL.md → working code)
Depends on the language no? Works in German
zwaps··on Americans are destroying Flock surveillance cameras
it's wild to me that Americand accept a private company plastering their town with surveillance cameras, given you know, everything

Additionally, that you draw the line at sharing that juicy data with law enforcement. I mean sure, yeah, but even before that, sharing essentially all your movement data with some company because...?

← PreviousPage 2 of 34Next →