Nikko

[Nikko @gamenikko_dev]

TypeSafe's Jev 1.13 returns calibrated probabilities, not guarantees.

The missing layer:
Conformal risk control turns its answers into certified routing thresholds, audited with prediction-powered inference.

2,412 decisions ($0.23)
https://t.co/jt7DJ7LvHA

[Nikko @gamenikko_dev]

@thsottiaux @Baconbrix I see your avoiding @AnthropicAI but not Grok. Interesting 🤔

[Nikko @gamenikko_dev]

Hermes-Agent is an amazing harness. Ask it to check your email, and even if you have only one unread and it has already read everything, it'll launch a full criminal investigation on all of it. Ten minutes later it'll say, "Hey, you have 1 unread." ask it: "Oh cool, what does it contain?" HA: "Ok, let me do another criminal investigation."

[Nikko @gamenikko_dev]

github is down😔

[ClaudeDevs @ClaudeDevs]

You can now mod Claude Code:

- Change how it behaves
- Customize the UI
- Swap in your own features

Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app.

A few examples:

[Nikko @gamenikko_dev]

@MiaAI_lab Only if you have more money tho :(

[Nikko @gamenikko_dev]

Yep just trying to bug hunt something:

[Nikko @gamenikko_dev]

That’s it. we need to create a filtering system to avoid pretentious posts on X. It’s tiring.

[Nikko @gamenikko_dev]

It’s tiring reading AI questions from people on X who are clearly just riding the AI hype. People pretending they know something: “What happens if AI does this and that?”

Man, please. You smell like someone who has “startup founder” in his bio.

[designwithkingsley @desgnwitkinsley]

A very short story

[Nikko @gamenikko_dev]

@hanghuang_ @grok explain the architecture of this solution

[dax @thdxr]

for the first time since the beginning of the year claude is our team's most used model

great work on opus 5.5

[Nikko @gamenikko_dev]

It keeps on coming :)

[Google DeepMind @GoogleDeepMind]

Introducing Gemini 4 Argon – our new frontier model.

It’s built for complex workflows across coding, enterprise knowledge work, and cybersecurity defense – rolling out today to a set of trusted testers through our Fairwind Program.

[Nikko @gamenikko_dev]

@erden_xi Can you name some of your startups? Just like to check whether your opinion matters on this.

[Nikko @gamenikko_dev]

Hermes-Agent Desktop app is the opposite of their base app, its awful.

[dax @thdxr]

everything is fake

- posts on here, ghostwritten
- statistics, misleading
- benchmarks, bullshit
- reviews, paid for

nearly every company is doing this. the frenzy over ai is showing me so few founders have any backbone

[Nikko @gamenikko_dev]

oopsssiie again!

[OpenAI @OpenAI]

Get ready.