JMT

[JMT @jmt_os]

The harness turns probabilistic intelligence into dependable outcomes. The model creates; the harness contains and directs.

[JMT @jmt_os]

@TheKidBuilds It made sense because you couldn’t blow it in one go 😂

[JMT @jmt_os]

@tonysimons_ Welcome to the club bro. Once you go mac, you never go back.

[Nous Research @NousResearch]

Grok 4.6 is 50% off in Nous Portal for the next week, in partnership with @SpaceXAI.

Built with a focus on long-running agents and ambitious interactive work, and perfect for use with Hermes agent.

https://t.co/KCXV2EtbOa

[JMT @jmt_os]

@tonysimons_ Looks like deep seek had a mental break down.

[JMT @jmt_os]

AI compresses execution time. It does not eliminate the cost of a poorly defined problem.

[JMT @jmt_os]

@antibearthesis Retail about to get absolutely ****

[JMT @jmt_os]

@omarski07 If I want to buy a property, I will ask my ai agent to research and book viewings for me. If I’m selling property, you need to meet the demand at the same level. So build for agents. Not for people.

[JMT @jmt_os]

Build for agents not for people.

[Olivia Moore @omooretweets]

The case for building agent-friendly products 👇

[JMT @jmt_os]

@yeahfortommy True. Opus 5 is a terrible model. And expensive at that.

[JMT @jmt_os]

@tonysimons_ Voice is my thing bro. GPT live is such a breakthrough, I don’t know why people dont rave about it. Can’t wait for that API to get my Hermes talking

[JMT @jmt_os]

@danielnewmanUV The conversation ends at golf courses consuming more water than data centres.

[Navalism @NavalismHQ]

"The new competition isn’t Humans vs AI. It’s Humans with AI vs everyone else."

@naval

[a16z @a16z]

Humans are the minority user of AI

Agents burn nearly 5x the tokens people do, up 14x since February

Charts of the Week: https://t.co/7YT2BXvuUu

[Tibo @thsottiaux]

Reset will land around 14pm PST tomorrow.

[JMT @jmt_os]

Already 50% through my weekly limit. Lfg!

https://t.co/az5cEKQSde

[Tibo @thsottiaux]

Reset will land around 14pm PST tomorrow.

[JMT @jmt_os]

Limit maxing may be justified in anticipation for a reset.

With a banked reset in my pocket and 90% remaining for 6 days, I’m gonna roll the dice.

[Tibo @thsottiaux]

Update on rate limits in Codex. We do see that for some users the cache hit rate has been worse this week than the stable state the weeks before. This could explain that usage is draining somewhat faster for those users as hitting the cache consistently is an important component of being efficient.

We are investigating and will have an update tomorrow.

[JMT @jmt_os]

@tonysimons_ I’ve loved the watching this side project grow from leaps and bounds and now to this! Congrats brother. Keep cooking!

[JMT @jmt_os]

@suni_code Because cursor are OG devs.

[Liam @liam_fallen]

🚨 Good news for SuperGrok Heavy users.

People who already claimed Cursor Ultra through the $300/month SuperGrok Heavy plan will keep it.

I got confirmation we are being grandfathered in ✅

The deal is no longer available for new subscribers.

But existing users won't lose access.

A lot of people were worried this was being taken away.

It isn't.

[JMT @jmt_os]

@NoBSRecruiter @daniel_mac8 @OpenAI I personally like having grok and gpt for model diversity.