Pinned Tweet
Absolutamente recomiendo usar Cache Control en Claude Code
Probablemente uno de los Mods que te ahorrará la mayor cantidad de tokens y ayudará a mantener tus sesiones activas por mucho más tiempo
Añade esta barra para la caché de 5 minutos de Claude y envía notificaciones para ayudar a mantener la caché activa
Comando de instalación:
npx claude-code-templates@latest --mod observability/prompt-cache-control
we rewrote our serving setup twice last year just because we switched GPUs
SGLang now runs on NVIDIA, Intel and Amazon's own Trainium chips
i want that year back
🤝 Paid partnership
2,000+ people. Two days. The first SGLang Summit.
Together, we announced SGLang v1.0, released Miles v0.2, and launched the SGLang Consortium with nine founding members: @nvidia, @AMD, @intel, @Google, @Meta, @thinkymachines, @Cloudflare, @modal, and @radixark.
SGLang is now used by 332 organizations. At Meta, it powers production inference for products serving billions of users. Teams from Modal, Cloudflare, LinkedIn, and others shared their production lessons.
Across 90+ technical talks and six hands-on workshops, the community explored what comes next for inference, reinforcement learning, and AI agents.
To everyone building, deploying, and contributing: thank you for making this possible.
Explore the announcements, engineering lessons, and moments from SGLang Summit 2026 in the link below.
Stefan Friedman retweeted
2,000+ people. Two days. The first SGLang Summit.
Together, we announced SGLang v1.0, released Miles v0.2, and launched the SGLang Consortium with nine founding members: @nvidia, @AMD, @intel, @Google, @Meta, @thinkymachines, @Cloudflare, @modal, and @radixark.
SGLang is now used by 332 organizations. At Meta, it powers production inference for products serving billions of users. Teams from Modal, Cloudflare, LinkedIn, and others shared their production lessons.
Across 90+ technical talks and six hands-on workshops, the community explored what comes next for inference, reinforcement learning, and AI agents.
To everyone building, deploying, and contributing: thank you for making this possible.
Explore the announcements, engineering lessons, and moments from SGLang Summit 2026 in the link below.
Stefan Friedman retweeted
nvidia, amd and intel agreeing on something is the real announcement here
🤝 Paid partnership
2,000+ people. Two days. The first SGLang Summit.
Together, we announced SGLang v1.0, released Miles v0.2, and launched the SGLang Consortium with nine founding members: @nvidia, @AMD, @intel, @Google, @Meta, @thinkymachines, @Cloudflare, @modal, and @radixark.
SGLang is now used by 332 organizations. At Meta, it powers production inference for products serving billions of users. Teams from Modal, Cloudflare, LinkedIn, and others shared their production lessons.
Across 90+ technical talks and six hands-on workshops, the community explored what comes next for inference, reinforcement learning, and AI agents.
To everyone building, deploying, and contributing: thank you for making this possible.
Explore the announcements, engineering lessons, and moments from SGLang Summit 2026 in the link below.
> friday 13 nov
> big overseas email and AI services go down across Australia for hours
> everyone refreshing the same dead tab
> @AgentausTD stays up the whole time
> runs on its own servers in Australia
free to try: agentaus.com.au/client/login…
🤝 Paid partnership
We built Australia’s own AI model, and today it’s open to the world.
Agentaus 1 (@AgentausTD): 220B parameters. 84.4% on MMLU-Pro. Ranked 43rd in the world.
It runs on Australian servers. Nothing ever leaves Australia, and nothing you type is used to train AI. Delete a chat and it’s gone for good.
Most of the world’s AI answers to somebody else. This one answers only to you.
Free to start: agentaus.com.au
Stefan Friedman retweeted
We built Australia’s own AI model, and today it’s open to the world.
Agentaus 1 (@AgentausTD): 220B parameters. 84.4% on MMLU-Pro. Ranked 43rd in the world.
It runs on Australian servers. Nothing ever leaves Australia, and nothing you type is used to train AI. Delete a chat and it’s gone for good.
Most of the world’s AI answers to somebody else. This one answers only to you.
Free to start: agentaus.com.au
Stefan Friedman retweeted
delete a chat on @AgentausTD and it's gone from their servers for good
wild that this has to be a selling point now
free to try: agentaus.com.au/client/login…
🤝 Paid partnership
We built Australia’s own AI model, and today it’s open to the world.
Agentaus 1 (@AgentausTD): 220B parameters. 84.4% on MMLU-Pro. Ranked 43rd in the world.
It runs on Australian servers. Nothing ever leaves Australia, and nothing you type is used to train AI. Delete a chat and it’s gone for good.
Most of the world’s AI answers to somebody else. This one answers only to you.
Free to start: agentaus.com.au
openai drops gpt-6.2 astra and higgsfield has it running agents the same day
We built Higgsfield Miracle to address one of the biggest challenges in AI video: editing a specific part of a shot without changing the rest.
Powered by GPT-6.2 Astra, it splits any video into layers for pixel-level editing in real time, with world knowledge built in. Every shot keeps the image depth that cinema-grade post-production needs.
Now in private beta with select testers. Coming soon to Higgsfield MCP.
Set up Higgsfield plugin in ChatGPT to be the first to try it.
Stefan Friedman retweeted
We built Higgsfield Miracle to address one of the biggest challenges in AI video: editing a specific part of a shot without changing the rest.
Powered by GPT-6.2 Astra, it splits any video into layers for pixel-level editing in real time, with world knowledge built in. Every shot keeps the image depth that cinema-grade post-production needs.
Now in private beta with select testers. Coming soon to Higgsfield MCP.
Set up Higgsfield plugin in ChatGPT to be the first to try it.
las agencias de marketing cuando el cliente les dice que el estudio de mercado ya se lo ha hecho un prompt
We built Higgsfield Miracle to address one of the biggest challenges in AI video: editing a specific part of a shot without changing the rest.
Powered by GPT-6.2 Astra, it splits any video into layers for pixel-level editing in real time, with world knowledge built in. Every shot keeps the image depth that cinema-grade post-production needs.
Now in private beta with select testers. Coming soon to Higgsfield MCP.
Set up Higgsfield plugin in ChatGPT to be the first to try it.
Stefan Friedman retweeted
GPT-6.2 Astra is LIVE on Higgsfield.
OpenAI’s new frontier model for your most demanding projects.
With Higgsfield plugin, GPT-6.2 Astra powers proactive multi-agent workflows across design, coding, and creative production.
Join Higgsfield with up to 65% off for Black Friday.
Some of you have been asking very politely. Some of you have just been asking.
GPT-6.2 Astra and Sol are now available.
Super efficient and built to perform where it counts—the real world.
openai.com/index/introducing…
picking a parser because it sits one spot higher on a leaderboard is a risky bet
Reducto tilted the same pages 2 to 4 degrees and first place changed on 6 of 12 benchmarks
parsejudge.com lets you test them on your own documents instead. free and open source
Last week, I said every parser is #1 on its own benchmark. So we tested the benchmarks.
We ran 8 parsers across 12 benchmarks, then tilted the pages by 2–4°. 6 benchmarks got a different winner.
We’re calling it BenchBench.
Stefan Friedman retweeted
Last week, I said every parser is #1 on its own benchmark. So we tested the benchmarks.
We ran 8 parsers across 12 benchmarks, then tilted the pages by 2–4°. 6 benchmarks got a different winner.
We’re calling it BenchBench.
Evita que tu agente acumule código en un archivo gigante que destruye tu contexto
Añade un gancho de parada que envíe a tu agente de vuelta al trabajo cuando intente terminar con un archivo de más de 1.000 líneas que ha crecido desde tu último commit
Los archivos grandes que ya has confirmado no lo bloquean a menos que añada algo a ellos
Script y configuraciones en las respuestas
2
38
785
Stefan Friedman retweeted
most agent setups send every single call to the biggest model they have
nasiko's gateway routes each one to the model it actually needs. up to 50% less token spend, they say
want to see that hold on a real workload
🤝 Paid partnership
Nasiko - Open Runtime platform for managing AI agents.
See every agent. Cut token spend by up to 50%. Route to the right model with the agent gateway. Govern tool access. Set permissions and budgets per agent, per team. One command. Same workflow.
Open Runtime for agents starts now. First, every token. Next, every action!
Start Free: buff.ly/k79CiWW
#ai #tokenops #openruntime #agents
most agent setups send every single call to the biggest model they have
nasiko's gateway routes each one to the model it actually needs. up to 50% less token spend, they say
want to see that hold on a real workload
🤝 Paid partnership
Nasiko - Open Runtime platform for managing AI agents.
See every agent. Cut token spend by up to 50%. Route to the right model with the agent gateway. Govern tool access. Set permissions and budgets per agent, per team. One command. Same workflow.
Open Runtime for agents starts now. First, every token. Next, every action!
Start Free: buff.ly/k79CiWW
#ai #tokenops #openruntime #agents
Stefan Friedman retweeted
Nasiko - Open Runtime platform for managing AI agents.
See every agent. Cut token spend by up to 50%. Route to the right model with the agent gateway. Govern tool access. Set permissions and budgets per agent, per team. One command. Same workflow.
Open Runtime for agents starts now. First, every token. Next, every action!
Start Free: buff.ly/k79CiWW
#ai #tokenops #openruntime #agents
Stefan Friedman retweeted
> give an agent access to the prod db
> it decides to "clean up" a table
> nobody approved that
nasiko lets you set which tools each agent can touch, per team. that's the part i'd turn on day one
🤝 Paid partnership
Nasiko - Open Runtime platform for managing AI agents.
See every agent. Cut token spend by up to 50%. Route to the right model with the agent gateway. Govern tool access. Set permissions and budgets per agent, per team. One command. Same workflow.
Open Runtime for agents starts now. First, every token. Next, every action!
Start Free: buff.ly/k79CiWW
#ai #tokenops #openruntime #agents
The most useful question you can ask an ad account is "what should I fix?"
Max, the ads agent from Creatify, answers it every day: what's working, what isn't, where people drop off before buying
It suggests, you approve. Try Max on Creatify
Stefan Friedman retweeted
Meet Creatify Max, the newest member of your ad team
Everyone gets their own Max. It watches your accounts 24/7, writes the briefs, makes the videos, and launches the campaigns
Max does the work. You make the call.
every small online store has that one ad that just works
and nobody knows why
max from creatify reads it, tells you why it works, writes the brief and makes new versions from it
you hit approve, it launches
search creatify, the agent is called max


















