Brahim

Curiosity.

[Thariq @trq212]

very weird thing happening rn

technical people are sad, they think their skills are now useless

non-technical people are desperately wishing they were more technical so they could use agents better

[Salesforce @salesforce]

AI agents can fail quietly
Costs can keep climbing

And you might not know until customers are already affected

Agent Fabric brings more control:
→ Evaluate continuously for quality issues
→ Trigger predefined interventions when quality drops
→ Cap spend before requests exceed budget

If your agents are live, evaluate them live

[Addy Osmani @addyosmani]

https://t.co/4Hfk0dYIBI

[DeepSeek @deepseek_ai]

🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!

Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.

🔗 https://t.co/JGAik1kgk0

1/4

[Kai Lentit (e/xcel) @KaiLentit]

Hyperoptimized Engineer.

[Elon Musk @elonmusk]

Turns out the future does have flying cars

[Evan You @evanyou]

We literally got flying cars before GTA6.

[Wes Bos @wesbos]

Tesla please, we just want a van

[@levelsio @levelsio]

Software is dead

It's now the era of personal software and everyone just builds what they need whenever they need it I think

[Amir Salihefendić @amix3k]

We spend $20m+/year improving Todoist with some of the world's most skilled people. And we are probably much more proficient with AI than most vibe coders.

People greatly underestimate how hard it is to create truly great products. It's like food: many people can cook, but not at a Michelin level.

[Kirill @kirillk_web3]

Boris Cherny built Claude Code. In 11 minutes he explains why the new Opus models need less prompting than anything before them.

and why your old detailed prompts are now working against you.

here's the part nobody is talking about:

> long instructions don't make the model smarter anymore.
> old prompt templates just add noise.
> his own team cut most of the Claude Code system prompt.
> he suggests deleting your CLAUDE.md every few months to see what the model can do without it.

most people are still prompting like it's 2025.

the model got smarter. the prompts didn't.

watch it below ↓

[Philipp Berner @philippberner]

I love how AI is solving the world's problems!

[Zain Javaid @zainmfj]

Introducing Core, The Personal Al Computer

The most powerful technology humanity has built should belong to you

Order today: https://t.co/tlNxSu5B5C

[Stray Yids @Stray_Yids]

@allenpark Nobody needs these big ass monitors in the age of ai. Laptop and sometimes (mostly for meetings) a single external monitor is enough.

[Brahim @brahimagentic]

@steipete Man that’s the weakness of a vibe coded project, we’re guided by the instant dopamine rush

[Brahim @brahimagentic]

Image each one get one or two of these autonomous agents, the web is not prepared!

[OpenAI Developers @OpenAIDevs]

OpenAI DevDay roll call

Where are you joining us from, and what are you building?

[Brahim @brahimagentic]

Those are colored Grok Bots, right ?

[OpenAI Developers @OpenAIDevs]

72 hours to OpenAI DevDay.

We’ve been building. Time to show our work.

[Elon Musk @elonmusk]

I really felt the AGI profoundly this time

[DHH @dhh]

It takes a while to build the confidence, but there's no future where you're manually reviewing every line of agent code. Not much acceleration in that. You need adversarial agent reviews, you need automated testing, and maybe you spot check. That's it. From prompt to production!