Sabitlenmiş Tweet
adi
4.5K posts
adi
@adidoit
@socratifyai - Career Skills Agent | Get that job. Get promoted. Get ahead | ex @McKinsey
Toronto, Ontario Katılım Aralık 2008
6.2K Takip Edilen542 Takipçiler
super useful.
i need a 200x claude plan though. 20x isn't enough for max
Boris Cherny@bcherny
I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most. Here goes.
English
I've been using plug-ins a ton internally. I have about 58 automations and 30 plug-ins and I've automated everything except the part where I have to come up with ideas and talk to people
OpenAI Developers@OpenAIDevs
We're rolling out plugins in Codex. Codex now works seamlessly out of the box with the most important tools builders already use, like @SlackHQ, @Figma, @NotionHQ, @gmail, and more. developers.openai.com/codex/plugins
English
ngl i have a lot of tests like this that look at skills for relevance testing...
Malte Ubl@cramforce
Test your SKILL.md Now that code is free, you can just test things. Here is Chat SDK's chat-skill.test.ts github.com/vercel/chat/bl… - Does the inline TypeScript compile? - Do the mentioned paths references into node_modules/ exist when you pack the repo with npm? - Does it list all built-in adapters that exist in the repo? - Does it list all community adapters listed in the docs? - Etc.
English
adi retweetledi
An interesting point from @raffi about the dangers of handing over too much of our critical thinking to the tech we use. theatlantic.com/magazine/2026/…
English
Definitely recommend people do agentic-ventures.com/elite-ai-assis… if you're interested in agentic engineering.
Every session teaches you practical ways to actually build software with agents (not as easy as "vibe coding" makes it sound)
English
this chart is great.
from a token consumer perspective we're early in the Blackwell wave while Vera Rubin is already shipping
We should expect at least a couple more big capability jumps in LLMs and reasoning easily in the next 12 months.
adi@adidoit
I've been saying for a while the valuations of firms like $NVDA seems way to low even at $4.5T considering the AI Factory ramp and incoming inference demand. The market is skeptical of exponential demand materializing and unit margins in face of open source but the "models are commodities" people are oversimplifying how power users behave IMO Blackwell GPU trained models just came out. The next jump in model capability could be when 1GW data-centers start cohering and training runs complete
English
@thsottiaux app suggestions
+ sometimes it gets too slow even with just 2 threads
+ automations page right now cant scroll down on mac (seems like a bug)
+ allow me to add icons to label sessions (e.g., colors)
English
I've been saying for a while the valuations of firms like $NVDA seems way to low even at $4.5T considering the AI Factory ramp and incoming inference demand.
The market is skeptical of exponential demand materializing and unit margins in face of open source but the "models are commodities" people are oversimplifying how power users behave IMO
Blackwell GPU trained models just came out. The next jump in model capability could be when 1GW data-centers start cohering and training runs complete
Stratechery@stratechery
Agents Over Bubbles Agents are fundamentally changing the shape of demand for compute, both in terms of how they work and in terms of who will use them. They're so compelling that I no longer believe we're in a bubble. stratechery.com/2026/agents-ov…
English
this was the one that made me scaling pilled.
still not quite over how big a jump that was...
historic release.
Greg Brockman@gdb
happy birthday gpt-4
English
This was utterly insane back then.
And now totally commoditized...
Three years is an eternity.
Romain Huet@romainhuet
Happy 3rd birthday GPT-4! 🎂 Watching @gdb turn a hand-drawn sketch into a working website was the moment it really clicked for me. You could feel programming changing in real time. Three years later, we’re living in that future with Codex.
English
