Anthropic engineers:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
In 42 minutes they explain exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run with graphs.
No paid agents course I've taken gets this specific.
Watch it, then read the guide below on building the same system with Graphs👇
Show more
Anthropic engineers:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
In 42 minutes they explain exactly how Anthropic builds agents that remember, fix their own mistakes and get smarter with every run with graphs.
No paid agents course I've taken gets this specific.
Watch it, then read the guide below on building the same system with Graphs👇
Show more
SpaceXAI engineer (ex-Cursor):
"I don’t prompt/micromanage my ~15 GrokBot agents step by step anymore.
While I sleep, my Сhief of Staff manages tasks across the bot team, and they ship PRs"
In 36 minutes, he explains how he's building a 24/7 team of Grok Bots that automate his life - and how automation changed his code.
Worth more than 10+ guides about GrokBot and code engineering.
Watch it, then save the article below 👇
Show more
SpaceXAI engineer (ex-Cursor):
"I don’t prompt/micromanage my ~15 GrokBot agents step by step anymore.
While I sleep, my Сhief of Staff manages tasks across the bot team, and they ship PRs"
In 36 minutes, he explains how he's building a 24/7 team of Grok Bots that automate his life - and how automation changed his code.
Worth more than 10+ guides about GrokBot and code engineering.
Watch it, then save the article below 👇
Show more
Are you still assuming the better result comes from the bigger model?
PRAXIST ran on an open-source model and beat a Claude Opus 4.8 stack.
> agent tries five things
> one works, four don’t
> it saves the one and deletes the rest
> next run starts from zero and fails the same way again
> PRAXIST keeps everything, including what didn’t work
> then decides what to try next based on all of it
> 49 gold medals on 75 MLE-Bench tasks for $3,054
the baseline spent $38,370 and won fewer. that’s the setup, not the model.
Show more
Introducing PRAXIST Beta, your autonomous research team🚀
Define the objective, constraints, and what success looks like. PRAXIST discovers the path.
From there, PRAXIST takes on the experimental research loop. Multiple Research Peers explore competing approaches in parallel, share useful findings, and build on accumulated evidence across experiments and generations.
In partner-provided environments, PRAXIST reached a 100% safe-landing rate in a rocket simulation and reduced accumulated error in an industrial SLAM system from 9.37 centimeters to 5.01 centimeters.
From robotics control to quantitative finance, PRAXIST has delivered measurable advances across fundamentally different problems by combining a shared core research architecture with domain-specific tools, knowledge, constraints, and evaluators.
More approaches explored. Faster iteration. Greater R&D capacity without proportionally increasing specialist headcount.
Show more
Are you still assuming the better result comes from the bigger model?
PRAXIST ran on an open-source model and beat a Claude Opus 4.8 stack.
> agent tries five things
> one works, four don’t
> it saves the one and deletes the rest
> next run starts from zero and fails the same way again
> PRAXIST keeps everything, including what didn’t work
> then decides what to try next based on all of it
> 49 gold medals on 75 MLE-Bench tasks for $3,054
the baseline spent $38,370 and won fewer. that’s the setup, not the model.
Show more
Introducing PRAXIST Beta, your autonomous research team🚀
Define the objective, constraints, and what success looks like. PRAXIST discovers the path.
From there, PRAXIST takes on the experimental research loop. Multiple Research Peers explore competing approaches in parallel, share useful findings, and build on accumulated evidence across experiments and generations.
In partner-provided environments, PRAXIST reached a 100% safe-landing rate in a rocket simulation and reduced accumulated error in an industrial SLAM system from 9.37 centimeters to 5.01 centimeters.
From robotics control to quantitative finance, PRAXIST has delivered measurable advances across fundamentally different problems by combining a shared core research architecture with domain-specific tools, knowledge, constraints, and evaluators.
More approaches explored. Faster iteration. Greater R&D capacity without proportionally increasing specialist headcount.
Show more
Anthropic CPO Mike Krieger:
"95% of developers now use graph engineering. Graphs are used about 5x more than any feature
We made one graph agent the CEO - it creates other agents to handle our tasks"
In a 25 minutes video, Mike breaks down what replaced prompting and why most people haven't caught on yet.
Watch it, then save the exact guide below👇
Show more
Anthropic CPO Mike Krieger:
"95% of developers now use graph engineering. Graphs are used about 5x more than any feature
We made one graph agent the CEO - it creates other agents to handle our tasks"
In a 25 minutes video, Mike breaks down what replaced prompting and why most people haven't caught on yet.
Watch it, then save the exact guide below👇
Show more
OpenAI engineer:
"You can now delete your IDE, you don't need it anymore. In 2026 if you are still not building AI agents, it's crazy how far behind you are.
At OpenAI, 85% of engineers are running agentic "loops" and graphs, that's how the engineering setup will look"
In a 40-minute interview, the Head of Codex and ChatGPT reveals how AI engineering will look like in 2026
Worth more than 10 paid agentic courses
Watch it today, then save the exact guide in the article below👇
Show more
OpenAI engineer:
"You can now delete your IDE, you don't need it anymore. In 2026 if you are still not building AI agents, it's crazy how far behind you are.
At OpenAI, 85% of engineers are running agentic "loops" and graphs, that's how the engineering setup will look"
In a 40-minute interview, the Head of Codex and ChatGPT reveals how AI engineering will look like in 2026
Worth more than 10 paid agentic courses
Watch it today, then save the exact guide in the article below👇
Show more
guys
i currently lost access to my main telegram account
@darkzodchi
just woke up and i am logged out of all sessions
trying to recover access at the moment, please don't answer anything
Are you still pasting context into a chat window before every single task?
The model stopped being the hard part a while ago. Knowing where your work actually lives is the part nobody solved.
> open a chat
> paste the doc
> paste the thread
> paste the ticket
> half of it sits in a tool you forgot to check
> the answer comes back confident and wrong
>
@glean built the context layer instead of another chat box
> desktop workspace, one gateway across models, agents that start work on their own
the assistant was never the bottleneck.
Show more
The intelligence era is here….and it’s powered by Glean. 💡
Glean’s context across your work makes it more efficient, secure, and proactive.
From Glean Tau, our new desktop AI workspace, to autorouting, a unified AI gateway, and proactive independent agents, our new updates unlock AI’s potential.
Join the live Glean:GO keynote today at 9am PT to see them all in action:
Show more
Instead of watching 1-hour of Netflix today, watch this lecture by Google & NVIDIA engineers👇
This is the best explanation of how LLMs like Claude & Grok actually work, and how to unlock 100% of their potential.
Worth watching whether you're a senior AI engineer or just taking your first steps in AI.
I took the key ideas and turned them into a practical guide on how to actually get 100% out of AI.
You can find it in the article below with ready-to-copy prompts and solutions.
Show more
Are you still pasting context into a chat window before every single task?
The model stopped being the hard part a while ago. Knowing where your work actually lives is the part nobody solved.
> open a chat
> paste the doc
> paste the thread
> paste the ticket
> half of it sits in a tool you forgot to check
> the answer comes back confident and wrong
>
@glean built the context layer instead of another chat box
> desktop workspace, one gateway across models, agents that start work on their own
the assistant was never the bottleneck.
Show more
The intelligence era is here….and it’s powered by Glean. 💡
Glean’s context across your work makes it more efficient, secure, and proactive.
From Glean Tau, our new desktop AI workspace, to autorouting, a unified AI gateway, and proactive independent agents, our new updates unlock AI’s potential.
Join the live Glean:GO keynote today at 9am PT to see them all in action:
Show more
Instead of watching 1-hour of Netflix today, watch this lecture by Google & NVIDIA engineers👇
This is the best explanation of how LLMs like Claude & Grok actually work, and how to unlock 100% of their potential.
Worth watching whether you're a senior AI engineer or just taking your first steps in AI.
I took the key ideas and turned them into a practical guide on how to actually get 100% out of AI.
You can find it in the article below with ready-to-copy prompts and solutions.
Show more
Can your competitor make your ad in three seconds?
Then it was never your ad.
> pick an AI UGC tool
> paste the URL, pick an avatar
> generate 50 variations before lunch
> competitor opens the same tool
> same prompt, same avatar, same model
> you are both shipping the same ad to the same feed
>
@iconhq went the other direction and built a human admaker
> real creators, scripted, filmed, coached, edited
> 6 human UGC ads for $999
whatever you can generate in three seconds, so can everyone else.
Show more
3 months ago, I sold my 1st company, Skio, for $105M cash.
Now my 2nd company, Icon, just raised $30M to launch something the world has never seen.
For $1000, we make 6 human creator ads (no AI, 100% real).
We find creators, ship products, write scripts, & edit videos.
It's risk-free:
- Full refund if you don't love your ads.
- You don't pay until you review 6 scripts.
- Unlimited human revisions.
Today, Icon introduces the world's first Agency.
We're not building a normal agency:
- We bought a $12M domain.
- We're backed by Founders Fund and OpenAI + Google DeepMind leaders.
It’s impossible to hire a creative team like ours for even $30K/mo:
- Creative Directors who've worked with $100M brands (IM8, Obvi, Ridge). They update our format library daily based on winning ads (street interviews, skits, & 20+ more).
- 12+ scriptwriters with $80M in Meta adspend.
- 200+ in-house editors who've edited 100K ads.
One more thing...
We're giving away our internal Google Drive with 1000 winning ads that have driven $100M+ in revenue.
You can make $100K copying these ads if you know what you're doing.
Want the Google Drive?
1. Retweet this post.
2. Comment "icon".
3. DM me this post’s link & I'll DM you back with the Google Drive.
[Bonus] Get 3 free human creator ads if you do the above and we end up working together.
Show more
Can your competitor make your ad in three seconds?
Then it was never your ad.
> pick an AI UGC tool
> paste the URL, pick an avatar
> generate 50 variations before lunch
> competitor opens the same tool
> same prompt, same avatar, same model
> you are both shipping the same ad to the same feed
>
@iconhq went the other direction and built a human admaker
> real creators, scripted, filmed, coached, edited
> 6 human UGC ads for $999
whatever you can generate in three seconds, so can everyone else.
Show more
3 months ago, I sold my 1st company, Skio, for $105M cash.
Now my 2nd company, Icon, just raised $30M to launch something the world has never seen.
For $1000, we make 6 human creator ads (no AI, 100% real).
We find creators, ship products, write scripts, & edit videos.
It's risk-free:
- Full refund if you don't love your ads.
- You don't pay until you review 6 scripts.
- Unlimited human revisions.
Today, Icon introduces the world's first Agency.
We're not building a normal agency:
- We bought a $12M domain.
- We're backed by Founders Fund and OpenAI + Google DeepMind leaders.
It’s impossible to hire a creative team like ours for even $30K/mo:
- Creative Directors who've worked with $100M brands (IM8, Obvi, Ridge). They update our format library daily based on winning ads (street interviews, skits, & 20+ more).
- 12+ scriptwriters with $80M in Meta adspend.
- 200+ in-house editors who've edited 100K ads.
One more thing...
We're giving away our internal Google Drive with 1000 winning ads that have driven $100M+ in revenue.
You can make $100K copying these ads if you know what you're doing.
Want the Google Drive?
1. Retweet this post.
2. Comment "icon".
3. DM me this post’s link & I'll DM you back with the Google Drive.
[Bonus] Get 3 free human creator ads if you do the above and we end up working together.
Show more
Google engineer, Jeff Dean:
"You can delete your IDE at this point, you don't need it anymore. In 2026 if you are still not building AI agents, it's crazy how far behind you are.
At Google, 85% of engineers are running agentic "loops" and graphs, that's how the engineering setup will look"
In a 40 minutes, an ex Google engineer with 26 years of experience reveals how AI engineering will look like in 2026.
Worth more than 10 paid agentic courses.
Watch it today, then save the exact setup in the article below👇
Show more
Google engineer, Jeff Dean:
"You can delete your IDE at this point, you don't need it anymore. In 2026 if you are still not building AI agents, it's crazy how far behind you are.
At Google, 85% of engineers are running agentic "loops" and graphs, that's how the engineering setup will look"
In a 40 minutes, an ex Google engineer with 26 years of experience reveals how AI engineering will look like in 2026.
Worth more than 10 paid agentic courses.
Watch it today, then save the exact setup in the article below👇
Show more