Hacker News Reader

ximengon Ask HN: Best option for hosted agent in 2026?

Open Hands (https://openhands.dev/) looks like it’s similar to what you want.

Is for me in Claude Code

https://github.com/bluesky-social/atproto/discussions/3363 - maybe this one?

What’s the plan for this? Sharing with a specific group (DM, group chat, feeds from people you follow) are critical to social media.

ximengon Conbini Wars – Map of Japanese convenience store ratios

Yes - hard to see e.g. city labels on the map under all the pie charts.

ximengon FUSE is All You Need – Giving agents access to anything via filesystems

I’ve been doing this recently and for the basics agents had no problem with the API apart from the weird behaviour of shared drives needing a special flag to handle them. This could probably be mapped to a file system in a way that wouldn’t trip up an agent, but at the expense of losing the Google drive specific functionality. A trade off, not much better or worse per se, but with the added complexity of the FUSE layer.

ximengon FUSE is All You Need – Giving agents access to anything via filesystems

LLMs can handle Google drive perfectly well with a service account, including the Google drive specific quirks through the API. It could be helpful to expose via a file system rather than a custom API if you wanted a different interface than Google already provides, but this wouldn’t be driven by the limitations of the LLM.

ximengon In-progress Call causes Screen Flickering

I complained about the communications around this issue a few weeks ago, and bcherny popped up in the comments with an explanation of what they were doing. Now there’s a fix with a great explanation of the background to this bug and future directions from chrislloyd.

ximengon Anthropic acquires Bun

It seems the default is node (despite the project docs saying to use bun and all example script documentation using bun). It will use bun if told, but there’s definitely nothing saying to use node and it uses that anyway.

ximengon Anthropic acquires Bun

I use bun in a project but Claude Code always uses node to run throwaway scripts. Maybe they can persuade it to use bun as part of this acquisition?

ximengon Claude Opus 4.5

With less token usage, cheaper pricing, and enhanced usage limits for Opus, Anthropic are taking the fight to Gemini and OpenAI Codex. Coding agent performance leads to better general work and personal task performance, so if Anthropic continue to execute well on ergonomics they have a chance to overcome their distribution disadvantages versus the other top players.

ximengon Claude Opus 4.5

It’s a pretty arbitrary y axis - arguably the only thing that matters is the differences.

ximengon WorldGen – Text to Immersive 3D Worlds

Compare https://odyssey.ml/ another text conditioned world generator

ximengon AI is killing privacy. We can't let that happen

Meanwhile… connect to fastcompany.com and see:

Do you consent to these personal data processing activities by us and our 1,666 partners?

ximengon GPT-5.1: A smarter, more conversational ChatGPT

The screenshot of the personality selector for quirky has a typo - imaginitive for imaginative. I guess ChatGPT is not designing itself, yet.

(Update - they fixed it! perhaps I'm designing ChatGPT now?!)

ximengon Yann LeCun to depart Meta and launch AI startup focused on 'world models'

Thanks for the reply (and for Claude Code!). I've seen improvement on this particular issue already with the last major release, to the extent that it's not a day to day issue for me. I realise Github issues are not the easiest comms channel especially with 100s coming in a day, but occasional updates on some of the top 10 commented issues could perhaps be manageable and beneficial.

ximengon Yann LeCun to depart Meta and launch AI startup focused on 'world models'

https://www.startuphub.ai/ai-news/ai-research/2025/sam-altma...

Like the new spin out Episteme from OpenAI?

ximengon Yann LeCun to depart Meta and launch AI startup focused on 'world models'

If Claude Code is Anthropic’s main focus why are they not responding to some of the most commented issues on their GitHub? https://github.com/anthropics/claude-code/issues/3648 has people begging for feedback and saying they’re moving to OpenAI, has been open since July and there are similar issues with 100+ comments.

ximengon OSMAnd vs. Organic Maps

They have a really nice feature I haven’t seen elsewhere to find a circular walking/cycling/ski route of a certain length. Useful to get ideas on where to go if you have some time for a walk or ride in an area you’re not entirely familiar with.

ximengon Cursor CLI

https://github.com/anthropics/claude-code/issues/1091

Here for Claude

ximengon I couldn't submit a PR, so I got hired and fixed it myself

If you are following a route in Google maps in Apple CarPlay you can’t search in the map without cancelling the navigation. So you need to use another phone or another maps app.

ximengon I couldn't submit a PR, so I got hired and fixed it myself

How about allowing you to use Google maps while navigating without two phones or opening Apple Maps as well?

ximengon Ask HN: Cursor or Windsurf?

Cursor offers this too - open different tabs in chat and ask for different changes; they’ll run in parallel.

ximengon LibreLingo – FOSS Alternative to Duolingo

Skritter is good for stroke order

ximengon AI Horseless Carriages

ChatGPT estimates a user that runs all the LLM widgets on this page will cost around a cent. If this hits 10,000 page view that starts to get pricy. Similarly for running this at Google scale, the cost per LLM api call will definitely add up.

ximengon Paris said au revoir to cars. Air pollution maps reveal a dramatic change

Just like the promise of EVs to replace the exhaust from ICE cars is seen as a win.

ximengon Google is winning on every AI front

Google aren’t interested in <1bn USD businesses, so it’s hard for them to build anything new as it’s pretty guaranteed to be smaller than that at first. The business equivalent of the danger of a comfortable salaried job.

ximengon Dow plunges 2,200 points, Nasdaq enters bear market

AI centric argument:

The policy indicates trade, traditional partnerships, and traditional financial metrics are less important for the administration. It is largely symbolic rather than analytically worked out - the direction is more important than the details.

This is consistent with the economy being radically altered by robotics and AI. Comparative advantage in labor costs is becoming irrelevant, so a large part of the justification for trade disappears.

Wealth is being further concentrated into those with existing assets, as the negotiating position of labor becomes weaker. It is less important to maintain partnerships when you can do everything yourself.

Recession becomes less important than pushing hard for leadership in AI. Deepseek’s model release had a huge impact on the values of leading US firms. With AI traditional measures of the economy become significantly less relevant.

ximengon Is XYplorer really written in VB6?

https://photodemon.org/ is a photo editing tool written in VB6

ximengon Satellite powered estimation of global solar potential

https://www.transitionzero.org/products/solar-asset-mapper perhaps