Mike Kurdyna

🩹 the internet.

[Mike Kurdyna @mkurdyna]

This is such an easy fix on the UI/UX level.

1. Add filters to feed/replies.
2. Allow users to mark posts/replies as "AI Slop".
3. Built-in filter to hide posts/replies from profiles that were marked more than 'n' times.
4. Users can toggle filters on/off anytime + whitelist.

[Nikita Bier @nikitabier]

Anyone who says a social network wants bots is deeply mistaken. Human interaction is already scarce on social networks, since most people are passive consumers.

Bots displace this scarce resource:

Each bot reply means one human reply is not seen or engaged with by another human.

It’s nearly a 1-to-1 drop in product & business value—and likely has much bigger compounding losses when you account for people churning out of frustration.

[Mike Kurdyna @mkurdyna]

@levelsio saw it yesterday, don't see any now.

but i think the strategy is still valid.

[Mike Kurdyna @mkurdyna]

@BitcoinErrorLog bro, go have a nice day
https://t.co/dT7tJ7dODO

[Mike Kurdyna @mkurdyna]

@threepointone doomчанський 🇺🇦

[Mike Kurdyna @mkurdyna]

@NickADobos *Composer

[Mike Kurdyna @mkurdyna]

@threepointone fork meets bottle

[Mike Kurdyna @mkurdyna]

@AlemTuzlak @shadcn + tanstack virtual, please

[Mike Kurdyna @mkurdyna]

@boristane Yep. Intent=Tasks=Review. Should be one dynamic ui for entire flow. No additional friction needed.

[Mike Kurdyna @mkurdyna]

@theo @thsottiaux No

https://t.co/e1QiT7pGxQ

[pash @pashmerepat]

Your ChatGPT subscription now powers an OpenClaw agent that genuinely feels magical to talk to.

Previous OpenClaw releases had OpenAI models running, but they never quite let the models reach their full potential. That changes today.

Personality is now deliberate, tool calls land exactly where they should, and your agent actually follows through on what it says it will do.

OpenClaw is now running on top of the Codex harness by default. In handing the inner loop to OpenAI's native Codex harness, we eliminated the conflicting instructions and duplicate tools that used to make the model hesitate.

What we stripped out under the hood:

- Duplicate tools (no more guessing between Codex native vs OpenClaw versions)
- Conflicting instructions (no more NO_REPLY vs message tool ambiguity)
- Leaked context (heartbeat logic only appears on actual heartbeat turns)

Less context bloat. More room for the agent to think.

And here's what we inherited for free, thanks to the Codex App Server:

- Searchable dynamic tools. Roughly 5,500 fewer upfront tokens per turn, which means faster and cheaper.
- Auto-Review mode using the built-in Codex guardian.
- OpenAI's native plugins (Calendar, Email, Drive) running in the same thread.

For you, the result is a personal agent that actually feels personal. It picks up where you left off across any channel, handles things before they hit your radar, and only breaks your flow when it has something genuinely worth showing you.

For developers, the result is stability. Because the inner loop runs on OpenAI’s native Codex harness, every upstream improvement lands in your agent automatically.

To get started, paste this in terminal:

> openclaw onboard

That is the whole setup.

[Mike Kurdyna @mkurdyna]

@alxfazio But in reality you opened Codex

[Mike Kurdyna @mkurdyna]

@badlogicgames Oi

[Mike Kurdyna @mkurdyna]

@badlogicgames What do you mean??? I thought 'ALL_TOOLS' fix it all

https://t.co/KyXQc7Z5xa

[Mike Kurdyna @mkurdyna]

@badlogicgames just do it

[Mike Kurdyna @mkurdyna]

@badlogicgames just do it

[max.berlin @maxjendrall]

@YoniBraslaver @badlogicgames oh god, please don't switch out all read, write, edit, bash tools for code mode.

Would be in the spirit of extensibility tho hahaha

"pi has 1 tool. deal with it"

[Mike Kurdyna @mkurdyna]

tbh i found gpt 5.5 very awkward. It feels sota, but also incredibly straightforward and lazy.

I had very good time with 5.4 High. It was stupid sometimes, but it was reading my mind (pun intended).

Now with 5.5 i feel anxious about what i say + what reasoning effort i choose.

[Mike Kurdyna @mkurdyna]

@GregKamradt from this write-up, I would suggest they use some highly customized Symphony-based workflow,

I would also suggest they will productize parts of it into Codex App very soon.

but of course, they will always be a few steps ahead internally.

https://t.co/i6Z30Gpbpe

[Mike Kurdyna @mkurdyna]

@levelsio @creem_io

[Mike Kurdyna @mkurdyna]

@pelaseyed @grok What app is this?

[Mike Kurdyna @mkurdyna]

@steipete @levelsio > You hear this for every *Anthropic* model release

[Mike Kurdyna @mkurdyna]

Lmao. It's so over for Anthropic.

[KATY PERRY @katyperry]

done