Hacker News Reader

airstrikeon Kimi Work

it's pretty great for coding because the CLI provides the model with all the context it needs and with a way to verify the result of its actions via linting, compiler messages and program output

the rest of "work" doesn't have that luxury

airstrikeon Jelly UI: Soft-body physics for native HTML form controls

No, compiz was awesome

airstrikeon Kimi Work

Models need richer context to do well. They also generally need a verifier, but better context is already an improvement. So to fix it, you need to rethink UIs to be agent-first.

I'm not saying Kimi Work and its peers are entirely useless. I'm just saying they're a hack that puts a pretty low upper limit on agent capabilities and speed.

airstrikeon Kimi Work

> Says who.

Says everyone who's not using this stuff. It's an empirical argument. Is anyone actually using this for work? How long has it been since Cowork was released?

It's such an inadequate tool for work it reeks of SF hubris to think you can just slap a chat input box onto a PC and replace 90% of white collar jobs.

airstrikeon Kimi Work

That's precisely the problem.

People are building UI/UX for a paradigm that is so utterly new that they miss the mark entirely.

Everyone defaults to a big chat input because that's all they know. It's the expectation, so it's safer, faster, and cheaper to not deviate.

It's also wrong and bad for work.

airstrikeon Setting up your spare Mac for Claude Code to control, a step-by-step guide

I'm open minded, I just haven't seen evidence to the contrary. Speaking as someone who's spent an ungodly amount of time in claude code

airstrikeon Kimi Work

Still a chat interface, so definitely not an "AI Desktop".

Also this was released about a month ago

https://tech.yahoo.com/ai/meta-ai/articles/moonshot-ais-kimi...

airstrikeon China's open-weights AI strategy is winning

yeah, I'm surprised I had to scroll this far to see this

everyone else seems to be thinking the quote is about AI-assisted coding but I read it as the model being used within the product itself

airstrikeon China's open-weights AI strategy is winning

Hmm if you assume the 80% is uniformly distributed between successful and unsuccessful startups/companies, which by default you should, then yeah, your proposed statement is true.

Data would be needed to argue the 80% skews unsuccessful

airstrikeon Setting up your spare Mac for Claude Code to control, a step-by-step guide

I started my post with "it seems to me" precisely because I haven't decided that I know best.

airstrikeon Fake food delivery site for the dopamine

OK, this actually worked as advertised. I feel dopamined.

I just wished the delivery took longer and there was a payment process that longer than an instant. Could have a saved card on file that you could use.

airstrikeon Setting up your spare Mac for Claude Code to control, a step-by-step guide

> This workflow alone is immensely powerful, and takes alot of burden off the team.

ITSM those unsupervised workflows are essentially an attempt at purported productivity in the near term at the expense of meaningful incremental long term burden for teams.

The only ostensible benefit is in the eyes of the AI-psychotic tinkerer, who knows no better, or in those of the clout-chasing developer farming likes on their LinkedIn posts.

airstrikeon What AI did to stackoverflow in a graph

This isn't really a bell curve.

airstrikeon Why do AI company logos look like buttholes?

Ironically, yes.

airstrikeon Codex starts encrypting sub-agent prompts

it is 100% the argument being made, but you can't see it just yet

airstrikeon Codex starts encrypting sub-agent prompts

idk about you but I'd rather not be murdered regardless of who the perpetrator might be

airstrikeon Apple sues OpenAI, accuses ex-employees of stealing trade secrets

you should probably seek mental help and read them this specific thread to cut to the chase instead of paying for 10 sessions

airstrikeon Postgres rewritten in Rust, now passing 100% of the Postgres regression tests

Terribly, but just because any two people suck at basketball doesn't mean a third person must suck too.

airstrikeon Mapping homes you can buy from the US government for <$100k

Well, yes, I have in fact always dreamed of owning an abandoned house in Flint, MI

airstrikeon The Revenge of the Philosophy Majors

and famously doesn't require a degree

airstrikeon Resetting Xbox

It's also really hard to buy studios and hope to catch future lightning in the proverbial bottle.

Past performance is no guarantee of future success.

airstrikeon It's not about physical vs. digital games, it's about ownership

It's a stretch rather than a point.

airstrikeon It's not about physical vs. digital games, it's about ownership

Hear, hear! One of the best comments I've read in over a decade on this site

airstrikeon Artificial Adventures

> I used claude code, codex, and pi. Both claude code and codex feel like hot garbage. Codex sometimes hits 100% cpu after I close the terminal I was using it in and stays there until killed. Claude code will say things like 'press escape to cancel this dialog' but when I press escape it leaves the dialog open and interrupts claude instead. The behaviour of both changes from day to day.

> Pi works. I haven't used it heavily enough to have opinions about the design, but it feels like a regular piece of software instead of a fever dream with unit tests. All three are heavily vibe-coded, so I'm curious what the pi folks are doing differently to maintain some baseline level of code quality.

sadly, Anthropic has mistaken the quality of their model for the quality of their tools, so they force their subscribers to stay with their inferior client lest they wish to pay API prices, which I don't understand why anyone would

airstrikeon Pint in England

HN auto edits some clickbaity/tropey titles in submissions.

Submitters have a grace period of several minutes to edit them back to anything they want, which will not get autocorrected, but many fail don't. They may not realize it or be too lazy to care, we'll never know. (Personally, I think anyone who considers themselves a "hacker" would at least try to bypass such a primitive system, but I digress...)

Some HNers complain every time that happens, gleefully oblivious to the countless other times the autoedit feature works as advertised.

airstrikeon What ORMs have taught me: just learn SQL (2014)

It's 2026. CPU goes brrr. It's absolutely trivial compared to the query execution time.

airstrikeon What ORMs have taught me: just learn SQL (2014)

And Django makes it ridiculously easy to write those raw queries in SQL directly so it seems like you're getting lots of mileage from the ORM without giving up anything

airstrikeon What ORMs have taught me: just learn SQL (2014)

The difficult parts are just literally a raw SQL string so how is that any harder?

airstrikeon What ORMs have taught me: just learn SQL (2014)

The correct SQL query will be more performant than what? The correct ORM call will build the same correct SQL query.

ORM is ultimately SQL

airstrikeon Reality has a surprising amount of detail (2017)

There are two reasons.

First, reality is continuous whereas the digital world is discrete.

Second, data in the real world is many orders of magnitude more detailed than what we're able to model with today's computers.