Author | Lightnews

Ian Bicking

Ian Bicking

@ianbicking.org

600 followers 850 following 670 posts

Software developer in Minneapolis. Working with applications of LLMs. Previously: Mozilla, Meta, Brilliant.org

Posts Media Videos Starter Packs

Ian Bicking @ianbicking.org · 1d

I don't really resent the rate limits, the underlying cost is real. But mostly I'm surprised that at $20/mo (and on the "auto" model setting) Cursor will happily grind for hours every day. And honestly I prefer its results for most coding tasks. (In this case I'm using Claude Code for non-code)

Ian Bicking @ianbicking.org · 1d

I didn't think I was even using Claude Code that much, and I hit a rate limit. The rate limit also blocks me from using the normal Claude chat interface, which is an interesting choice. OpenAI's Codex similarly conked out fairly early with a rate limit, meanwhile Cursor keeps going and going...

Ian Bicking @ianbicking.org · 2d

I'm not sure I understand the likely impact of at large seats...? I can imagine a bias towards higher-turnout voting segments. Is it more than that?

Reposted by Ian Bicking

Python Software Foundation @python.org · 3d

TLDR; The PSF has made the decision to put our community and our shared diversity, equity, and inclusion values ahead of seeking $1.5M in new revenue. Please read and share. pyfound.blogspot.com/2025/10/NSF-...
🧵

The official home of the Python Programming Language

Ian Bicking @ianbicking.org · 5d

I'm kind of enjoying watching it and trying to reconstruct the surreal tesseract world it embodies.

But I guess what strikes me is how banal the game is. The environment isn't any richer for the AI. Filled with stuff, but just a different kind of background noise.

Ian Bicking @ianbicking.org · 7d

The chatlog, in all its messiness, is a core part of what's happening. It holds the not-yet-actionable information. It holds context, history. It's fully situated, including being situated in a user/assistant relationship. It's unclear what analog exists for a text adventure.

Ian Bicking @ianbicking.org · 7d

Now an LLM can solve that issue pretty well, but what does it parse into? Really there's two things being created by the system: the action and the chatlog. In the context of the chatlog you can parse "change that to eight thirty" into a concrete action.

Ian Bicking @ianbicking.org · 7d

If you say "set an alarm for 8 o'clock" and there's some {action: "createAlarm", time: "8:00"} structure you can create, then you're good. If you say "change that to eight thirty" and there's no structure to parse that into, then there's no parser that can make that work.

Ian Bicking @ianbicking.org · 7d

When I was working on voice assistants pre-LLMs I felt the same problem. The parser was only a small part of the problem. You can recognize more phrases, but the only phrases that could matter are the phrases for which some internal target structure existed.

Ian Bicking @ianbicking.org · 7d

But a better parser isn't that interesting because there's only a couple things a player can do at any moment to advance the game. You can make infinite LLM-backed easter eggs, but that gets old fast.

Ian Bicking @ianbicking.org · 7d

A lot of people think briefly "wouldn't it be cool to hook an LLM up to a text adventure to parse the input," hoping to solve a real (but minor) problem when the game can't interpret a valid command because it isn't formatted correctly.

Ian Bicking @ianbicking.org · 7d

It appears to be freedom because you can't see the map of possible actions. Anything you type _could_ work. This makes the game feel open but it's an illusion, your mind imagining freedoms you have not yet pursued; but also you cannot pursue them.

Ian Bicking @ianbicking.org · 7d

In practice I don't think text adventures offer much freedom. You can't dream up new ways to solve puzzles. Picking up and dropping inventory items is not a deep system. Determining the correct verb to use can be a puzzle of its own, but it's not freedom.

Ian Bicking @ianbicking.org · 7d

I was reading this post talking about the great things about text adventures, and it got me thinking about parsing and representation... entropicthoughts.com/the-greatnes...

Specifically from the question: do text adventures really give players a lot of freedom?

The Greatness of Text Adventures

entropicthoughts.com

Ian Bicking @ianbicking.org · 7d

Watching the kids write fractions by hand on a Chromebook trackpad made me feel somehow complicit

Ian Bicking @ianbicking.org · 11d

I think pushing it further means explicit thinking about memory formation, consolidation, updating, reinforcing surprise and disposing of unsurprising/inferable memories, and so on.

Which is all very fun to think about!

Ian Bicking @ianbicking.org · 11d

Should AI prescribe medication for mental health? If someone says yes I will guess it’s 50/50 that they are just an edgelord trolling the question.

Ian Bicking @ianbicking.org · 11d

Like there was a free wellness benefit of Therapy Lite at a previous job, and I tried a couple sessions. AI could absolutely beat that experience right now, hands down. Having a human who embodies a pamphlet on CBT and mindfulness is not hard to beat.

Ian Bicking @ianbicking.org · 11d

At this exact moment? Surely no, and if they answered otherwise I’d suspect they were interpreting the question differently than me. “In some cases, right now?” - probably many would say yes, and due to the ambiguity of that language it’s an easily defensible position.

Ian Bicking @ianbicking.org · 12d

In the small parking lot behind my house one of the employees always parks in the same place, with the placards “if you’re going to ride my ass at least pull my hair” and “bimbo on board” very visible in her back window. I admire the confidence!

Ian Bicking @ianbicking.org · 13d

It feels very Jurassic Park, like I can hear the literal plot arc that in this case concludes in the Titan disaster

Reposted by Ian Bicking

Ian Coldwater 👻🌿 @lookitup.baby · 13d

If you want to give yourself nightmares about the Titan submersible disaster, this audio from the meeting where OceanGate fired the whistleblower bringing up safety concerns is Some Shit

Ian Bicking @ianbicking.org · 14d

In the end I kind of get MCP but mostly am eh. I can understand what excites other people, but it doesn’t seem THAT exciting. Maybe I’m not thinking of it the right way.

Ian Bicking @ianbicking.org · 14d

Well, I do understand, but only because I can appreciate how much you can skip by using MCP. And there are other features in MCP (not supported by ChatGPT) that would improve this. But still…

I do not understand memory systems built on MCP. That must be soooo slow.

Ian Bicking @ianbicking.org · 14d

Everything is so slow! I usually use GPT Thinking so I guess I’m ok with (even prefer?) slow responses. But it’s like a super slow single threaded app, like 1970s terminal slow, only slower. I don’t understand the excitement to build on it, really…