News for hackers. Stuff that matters.

red_hare

Re:Kimi K3.1 Pro and K3.1 Pro Highspeed on Friday October 23, 2026 @02:22PM (#50213303)
> When evaluating the Intelligence Index, it generated 150M tokens, which is very verbose in comparison to the median of 87M.

So their base price is 1/5th of Opus 5.5 per token, but if you want "highspeed" it's 2x that and then I guess it generates 2x the number of tokens as well?

That might suggest that Opus is competitively priced after all.

Re:Rust off Rails: The opinionated web stack for the AI era on Wednesday October 21, 2026 @01:11PM (#50184336)
It reminds me of when everyone was trying to build their own frontend framework. Like "neat, I agree with this in concept, but I don't trust your code or you to maintain this project"
This feels right. It fits the "Assembly to C" style transition of abstraction in that we're going from "code to design of code."

A question I've been struggling with, however, is what are the artifacts that live at this level? Are they design docs? Are they standardized? If I read your design docs, will I understand the code or do I need to "decompile" (use a coding agent to explain) to get back to this level of abstract for me to edit it?

Re:Tesla Roadster on Friday October 16, 2026 @04:39PM (#50124321)
No windshield wiper?
Re:Suicide rates highest ever among middle-aged men on Friday October 16, 2026 @12:19AM (#50114028)
You've clearly never asked Claude for help with plumbing.

It's a humbling reminder that not all fields of knowledge application are verifiable in post-training.

Re:Terence Tao: Math 2.0 [pdf] on Sunday October 11, 2026 @10:25PM (#50050581)
What's your opinion on SynthID Bio? Are you worried about a future where medicine has DRM built-in?
For a local non-coding agent, instruction following and tool use are the most important gains
The difference makes a lot of sense to me.

The phones are watches are primarily sold on annual leases through carriers. And no one is buying them for the chips, it's all camera and form factor.

The macs, on the other hand, can more easily swap between chips in manufacturing. And the form factor is pretty static. So Apple, in a race to have the best chip in the field at any given time, is just releasing them as soon as they're ready.

I agree the whole "m5 max > m6" is confusing, but I think they figure only the nerds who learn the specifics are going to care anyway.

As someone who teaches AI at a university, understanding the basics of how the LLM works is really invaluable to understanding where and how they'll be applied.

You're right that it's probably a little too in the weeds, but it's also a nice clear and fun objective that teaches you the basics. Like building a TODO list in JavaScript to learn webdev or a Gameboy emulator in C++ to learn how a CPU works.

Re:How Bluesky draws its logo on screenshots on Monday August 17, 2026 @08:02PM (#49339394)
I can't help but respect the dev's self-awareness
When you give those resources to your coding agent, do you give them URLs? Or work with local versions?

I've found a lot of success pointing claude at locally downloaded docs over llms.txt URLs but not sure how to scale the pattern for a bigger project.

Re:Ask HN: What are you working on? (August 2026) on Sunday August 09, 2026 @07:25PM (#49237308)
I'm in the process of planning an indoor-outdoor wedding in NYC so I made a little weather history explore tool

https://12seasons.nyc/explore/

15 years of mouse-free professional programming and never in my life have I touched these.
Re:Kenji/Serious Eats – 30-Min Pressure Cooker Pho Ga on Saturday August 01, 2026 @08:48PM (#49140032)
Anyone else catch that he wrote this on an 11-inch MacBook Air (2016 at latest)?
Re:Marimo Now Runs in PyCharm on Saturday July 25, 2026 @12:01AM (#49044402)
What I like about Marimo notebooks over Jupyter:

1. They're just a python file so they work with python editors

2. There's no hidden state

3. I can import from them

4. I'm not accidentally committing base64 encoded image output anymore

Re:Marimo Now Runs in PyCharm on Friday July 24, 2026 @11:58PM (#49044392)
huh, I was doing this but without the feature. This is neat!
I think the trick to using libraries like this is to not go all in on them. Applying these effects to every element would be garish.

But for a single like button, an effect slider, or magic search bar? It would be be a lovely touch.

Just 25 years too late to be used to design Jelly World

https://neopets.fandom.com/wiki/Jelly_World

I agree. We're seeing more variants of "RAG" that aren't semantic at all (e.g. coding agents or simple memory systems that feed summary indexes directly into context).

I think, over time, it's going to become a SQL / NoSQL sort of divide. There will be the right kind of RAG for the job and lots of forcing the wrong kind because the developer doesn't understand the nuances.

Re:Show HN: QR code renderer in a TrueType font on Wednesday July 01, 2026 @02:44PM (#48751442)
Wow. This is so freaking cool.
I say this with a lot of love: The vibecoded applications in your demo reek of AI slop design.

This isn't a critique of your product. It's just that the a beige-orange theme, the pill components, and the left-border highlight give me that visceral reaction as reading a paragraph littered with em dashes and "not X but Y." It makes me take you less seriously.

Cool demo otherwise.

Apt for self-hosting
Re:Slate EV truck starts at $24,950 on Wednesday June 24, 2026 @09:56AM (#48659912)
Oil changes aren't the best example. They're pretty easy to do at home for basically everything and filters are pretty standardized.

But car batteries, brake pads, tire pressure sensors are all becoming increasingly software-locked in. We're lacking open standards for this stuff.

Re:The truth about being a manager on Tuesday June 23, 2026 @02:09PM (#48648932)
Why does AI want to stress me with that cup about to fall off the desk
Re:Steam Machine on Monday June 22, 2026 @01:37PM (#48633239)
Eh, it was the exact same system for the Switch 2 and no one I know waited more than a week for theirs.

Given it requires a Steam login of a certain age to register, I suspect this is just to limit the scalpers.

Re:Ask HN: What is the job market like? on Thursday June 18, 2026 @02:44PM (#48589674)
> pause for 5 seconds between responses

I'm sure I'm not the only one, but I've gotten so aggressive about monitoring for this. I do most interviews zoomed in on the candidate's eyes and I rubric on how they "thought" through the problem, not just the results.

Thankfully the interview tools are catching on as well and now tracking this like browser focus, number of monitors, window size, and sending notifications when any of those change.

This is an insane take.

Also wrong, gay marriage had 60% support before Obergefell v. Hodges.

Re:Chuwi Minibook X: the netbook we deserve on Monday June 01, 2026 @01:11PM (#48359687)
I have one of these. Basically dead with modern MacOS but runs Linux Mint XFCE really well.
Re:MCP Is Dead on Friday May 29, 2026 @11:59PM (#48332411)
OpenAI API also supports defer_loading https://developers.openai.com/api/docs/guides/tools-tool-sea...

And it's not actually necessary for it to exist at the API level. It's a pattern. Making it API-side is just an optimization.

To do it client-side: 1. Define a single tool, tool_search 2. List the names of your deferred tools in context (or tool_search's description) 3. When tool_search is called, match the query against the tool names (or names + descriptions) 4. Append the matched tool def to the context in a new <system>-esque tag

Claude Code (as of the leak) does this client side. You can even see the custom matching function and A/B tests about whether to include the descriptions.

Whether or not that tool definition comes from MCP or a local definition is kind of beside the point.

Re:MCP Is Dead on Friday May 29, 2026 @11:47PM (#48332354)
+1

Its crazy that people are still discussing this. It's ancient history. Deferred tool loading, large contexts, and prompt caching have made 2026 completely different from 2025.

Also, the "CLI saves token" debate really falls apart when step one of using the CLI is running "--help". The problem remains: if knowing how to call the thing isn't in parametric memory, it has to be in context.

Older »