Bernard K

I build practical AI agents and automation for ops teams. Came up through embedded hardware, so I know the model and the metal. Building in public.

[Garry Tan @garrytan]

Attention is all you need

[Bernard K @0xb_k]

New AI model every week, and I have stopped trusting the benchmark charts. The test I trust: hand it my real messy workflow and watch what happens.

[Andrej Karpathy @karpathy]

Gradient descent can write code better than you. I'm sorry.

[Bernard K @0xb_k]

@thsottiaux Add remote-control like on cc.

[Bernard K @0xb_k]

@garrytan Implementing this, rn! Thanks!

[Bernard K @0xb_k]

@tankots @WisprFlow Wispr Flow

[CIPHER @infooperative]

you're describing "Pascal’s Wager for Happiness."

mathematically, the pessimist pays the "suffering tax" twice.

once during the anticipation of the bad event, and again when the bad event actually happens.

the optimist only pays the tax once (when the event happens).

if the bad event doesn't happen, the pessimist suffered for nothing, while the optimist enjoyed the ride.

[Micky @Rasmic]

my problem with codex lol

[Bernard K @0xb_k]

@TahaTesser @thsottiaux Same here. I am stuck. I have tried updating to the latest, signing it back again, and get a similar error.

[Bernard K @0xb_k]

@punishedfounder @OpenAI +1 am also constantly getting "stream disconnected before completion: error sending request for url (https://t.co/5wjZpm9Qax)" @embirico

[Bernard K @0xb_k]

AWS down 👀, wondered why my bot was down.

[Bernard K @0xb_k]

@jay_azhang I wonder how GLM 4.6 would perform?

[MattD @mattdykema]

How TF did they design this without CAD

[Jake Schneider @PairedWith_P7]

I’m Jake Schneider — the 7th person in the world to receive a Neuralink brain implant. 🧠⚡
I have ALS, but I’m tweeting this… with my mind.
Life at the intersection of hope and technology. Wired for the impossible.

[Mark Kretschmann @mark_k]

Apple will buy Anthropic, it's just a matter of time.

[Z.ai @Zai_org]

Introducing GLM-4.5 and GLM-4.5 Air: new flagship models designed to unify frontier reasoning, coding, and agentic capabilities.

GLM-4.5: 355B total / 32B active parameters
GLM-4.5-Air: 106B total / 12B active parameters

API Pricing (per 1M tokens):
GLM-4.5: $0.6 Input / $2.2 Output
GLM-4.5-Air: $0.2 Input / $1.1 Output

Tech Blog: https://t.co/rg5nrMdab7
Weights: https://t.co/cGCGnB735L
https://t.co/DRCwFHQQRn API: https://t.co/pqo3sYqh9K
OpenRouter: https://t.co/nXjmxr9Qsk
Develop Tools: https://t.co/dBJ9KU9Kyk
Try them now: https://t.co/WCqWT0raFJ

[Tyler Stevens ⚡️🔥 @tylerkstevens]

Hashrate heated floors coming soon to @SpaceDenver

[Bernard K @0xb_k]

Great session today ₿ @BitDevsNBO

[Bernard K @0xb_k]

#BlockMeet by @DecentrixAfrica