Hacker News Reader

brianjkingon Amateur armed with ChatGPT solves an Erdős problem

GPT 5.5 Pro is not available to any plan outside of ChatGPT Pro ($100 or $200) tier or the API as far as consumer access.

brianjkingon Bring Your Agent to Teams

Bring back Glitch the game! https://en.wikipedia.org/wiki/Glitch_(video_game)

brianjkingon Bring Your Agent to Teams

lol, I love that their first example is bringing Slack content into Teams. It's like they've completely forgotten if I have Slack, there's 0 way I'm going to have Teams open if I can avoid it at all.

brianjkingon Workspace Agents in ChatGPT

So this only works for Team/Enterprise accounts? No Pro?

brianjkingon Cursor 3

I've been using Codex since before ChatGPT (the OG version) and CC since launch. For me personally - Claude Code with Opus/Sonnet generally has better taste, more personality in interactions, and is more willing to just do the work. Paired with skills, LSPs, linters, and hooks, it works very well. I think of the two like this:

Claude Code with Opus/Sonnet is the L7 senior engineer still gunning for promotion. Hasn't hit burnout, hasn't been ground down by terrible teams yet. Capable and willing to get their hands dirty. Codex (the harness) with GPT-5.4 or 5.3-codex is fantastic but terse. Some of the UX frustrates me. I want a visual task list. That said, Codex as a harness is phenomenal. Think of it as the senior EM / CTO-in-waiting who won't write new code without complaining and nitpicking for hours. But they'll thoroughly tear your code apart and produce a plan you can execute yourself or pass to Claude Code.

Both are great, and so is Factory Droid. Also worth checking out Compound Engineering from Every.to if you haven't.

brianjkingon Om Malik – 'Astound'ed. Google Flips Its Fiber to PE

I guess I can stop being upset about no longer having access to Webpass anymore and being back in the Comcast handcuffs.

brianjkingon Schedule tasks on the web

Does GLM-5 have multimodality or are they still wanting you to load an MCP for vision support?

brianjkingon LLM Architecture Gallery

I'm getting that trying to load the content at all, text included.

brianjkingon You can turn Claude's most annoying feature off

This is one of my favorite features. That's my second favorite, I enjoy reticulating iirc.

brianjkingon 19 States approved permanent daylight saving time

Uniform time act of 1966 prevents this being set at the state level outside of remaining forever in standard time.

brianjkingon 19 States approved permanent daylight saving time

Until this goes away or a federal bill passes, nothing will change: https://en.wikipedia.org/wiki/Uniform_Time_Act.

This only allows states to choose to switch or to remain in "standard time", there's not an option to remain in "savings time".

brianjkingon The First Fully General Computer Action Model

Very exciting, great work to you and the team. Will there be any APIs available for commercial use or open source access?

What's the plan on that front?

brianjkingon OpenAI should build Slack

Butterfield should bring Glitch back, that's for sure.

brianjkingon GLM-5: Targeting complex systems engineering and long-horizon agentic tasks

Pretty damn great bird, tbh.

brianjkingon Qwen3-Coder-Next

TFW 48gb M4 Pro isn't going to run it.

brianjkingon Show HN: Vibium – Browser automation for AI and humans, by Selenium's creator

Director.ai uses Stagehand, which is made by Browserbase.

brianjkingon Fara-7B: An efficient agentic model for computer use

Correct, this only works in the browser w/ Playwright as far as I can tell from a quick test.

brianjkingon Claude Opus 4.5

Care sharing some of your sub-agent usage? I've always intended to really make use of them, but with skills, I don't know how I'd separate these in many use cases?

brianjkingon Claude Opus 4.5

They also reset limits today, which was also quite kind as I was already 11% into my weekly allocation.

brianjkingon Show HN: RowboatX – open-source Claude Code for everyday automations

LOTS! Sometimes for quick file system organization, creating Claude skills, deep document analysis.

Anthropic published a doc or two about this too, here's one of them: https://www-cdn.anthropic.com/58284b19e702b49db9302d5b6f135a...

brianjkingon Gemini 3

It is so impressive that Anthropic has been able to maintain this pricing still.

brianjkingon Gemini 3

Google has always done this.

brianjkingon AI World Clocks

This is an awesome benchmark. Officially one of my favorites now. Thank you for making this.

brianjkingon Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

Does this allow me to use Claude Code as the orchestration harness with GLM 4.6 as the LLM along with other LLMs? Seems so based on your description, thanks for the link.

brianjkingon A stateful browser agent using self-healing DOM maps

I couldn't load the article. I was getting a nginx error initially. I'm able to view now. I think they were getting a bit squeezed.

brianjkingon A stateful browser agent using self-healing DOM maps

Is this able to load for anyone?

brianjkingon Gemini 3.0 Pro – early tests

I must say that I loved the idea of a tardigrade riding a surfboard. You're welcome.

Granted not an SVG, but still awesome.

https://imgur.com/a/KsbyVNP

brianjkingon Addendum to GPT-5 system card: GPT-5-Codex

Their massive increase in token processing since Veo3 and nano banana have been released would say otherwise...

Or we're all just used to eating things we don't like and smiling.

brianjkingon Addendum to GPT-5 system card: GPT-5-Codex

Wait, this wasn't what I was experiencing. Did something change in gpt-5-codex or was that your normal experience?

brianjkingon Addendum to GPT-5 system card: GPT-5-Codex

Hey now, let's not forget it. They also have:

- all the lobbyists - all the money