Kieran Klaassen
@kieranklaassen ·
This is what I've been building since 2024
Back
AI posts
AI posts
People and companies shaping AI. Filter your watched accounts, catch up on recent posts, or find the most liked and viewed.
Compiled by the Toolstash team · Updated
209 watched accounts · 2984 matching posts · Showing up to 3,000 recent stored posts. Counts are snapshots, not live X totals. This page refreshes every minute while visible. Last collected .
kache@yacineMTB ·
One thing I like about Carney is how he pretty much refuses to define Canada relative to America. He defines Canada as Canada, and answers the questions about how to deal with USA using answers about how Canada should be, irrespective to USA. bro actually read George grant?
Santiago@svpino ·
These guys built an agent that takes a process description and turns it into a TypeScript workflow.
Here is how it works:
1. You explain the rules you want to automate to the agent 2. The agent creates the automation workflow 3. You review the workflow and ask for any changes 4. When done, you can publish the workflow
After it is public, anyone at your company can run the workflow from Slack or Microsoft Teams.
Vox@Voxyz_ai ·
Change the plan mid-task, and unless your coordinator agent runs a top model, it 𝘄𝗼𝗻'𝘁 𝗲𝘃𝗲𝗻 𝘁𝗵𝗶𝗻𝗸 𝘁𝗼 𝘁𝗲𝗹𝗹 the agents working in the background.
They grind through the old plan and hand back "done" with a straight face. You burn tokens once for nothing and again on the redo.
On a team it's worse. Plans often change in meetings, and however smart your coordinator agent is, it 𝗻𝗲𝘃𝗲𝗿 𝗴𝗲𝘁𝘀 𝗶𝗻𝘃𝗶𝘁𝗲𝗱.
@jakejooyoung launched Serro today. It's an Agentic TPM, basically an AI version of a technical program manager. When the plan changes, it checks with whoever owns it first, then updates every person and every agent.
If it's just you, send this to your coordinator agent after you change the plan 👇
"I just changed the plan: [what changed]. Act as the program manager for every agent working on this: 1. Update the plan file first (create PLAN.md if there isn't one). If any part of the change is unclear, ask me before you pass it on. 2. Tell every agent that's still running what changed. Ask what it already built on the old plan, and stop anything that no longer fits. 3. From now on, have every agent reread the plan file before it starts and before it reports back. If the plan changes mid-task, it stops and asks first. 4. Every report covers what was done, where it is, how it was verified, and what's still open. 5. No agent pushes, deploys, or touches production without my OK. Then show me what needs to be redone."
Nathan Lambert@natolambert ·
This is very needed. Talking to models like Claude about anything that has an overlap with an area like legal, healthcare, etc is mind numbing. They’re so desperate to hedge and steer away from grey area that they often are really avoiding the real question.
Aravind Srinivas@AravSrinivas ·
/teardown by @jakubkrehel now available as a skill in Perplexity Computer. Allows you to break apart any thing and look into it in 3d interactively. 5000 trial credits per user to tinker around.
jack friks@jackfriks ·
so like 2 months ago i setup a grok bot to use @postbridge_ to mirror any post i make on here (X) to all other platforms
then i go look every few weeks and see i have posts that got a bunch of traffic for essentially 0 extra effort and a 1 time setup
hard to beat that
Marcus Williams@Marcus_J_W ·
Some details on what our monitoring system currently looks like https://openai.com/index/how-we-detect-frontier-model-misalignment/
corbin@corbin_braun ·
building from 0
a lot of you won't like the amount of years of nothing.
would say after year 10
you become numb to it all
and just become an on going train toward destination.
or shall I say destiny.
- kache
@yacineMTB ·
THANK YOU MR CARNEY. FOR INVESTING IN AI AND THE FUTURE OF CANADA 🇨🇦 IT IS THE MOST IMPORTANT TECHNOLOGY EVER . I WILL NOT BE LAMENTING FOR MY COUNTRY TODAY 🇨🇦
Miles Brundage@Miles_Brundage ·
Claude Duet being a separate app is not ideal
Fireworks@FireworksAI_HQ ·
Can AI piece together how a company works from scattered records?
Epiq Corporate Bench, now in our Specialized Intelligence Index, tests how models reconstruct knowledge and track changing relationships.
Learn more in Epiq’s blog: https://ailabs.epiqglobal.com/announcements/fireworks-ai
Every 📧@every ·
Early this year we built Plus One, our personal-agent product. In May, we deleted 86,730 lines of its code because it wasn’t working.
A personal bot like OpenClaw was too much work to run: Each agent lived on its own cloud computer, which was too high-maintenance. Many of us ended up abandoning our bots.
For the bots that remained alive, we noticed that they were most useful when borrowed by other people. @tedescau connected his Plus One to our analytics tool, and people on the team asked it analytics questions.
We decided to start over, making two changes: 1. We let Anthropic’s Claude Managed Agents take care of the infrastructure. 2. We replaced our fleet of personal agents with one shared company agent.
@bigwilliestyle breaks down the process behind the creation of the Every Agent: https://every.to/source-code/why-we-replaced-personal-agents-with-one-for-the-whole-company?utm_source=x&utm_campaign=every-agent-launch&utm_content=every-shared-agent-starting-over
Install the Every Agent: https://every.to/agent?utm_source=x&utm_campaign=every-agent-launch&utm_content=every-shared-agent-starting-over-install
Dan Shipper@danshipper ·
great to chat with the legend @nathanbarry !
- corbin
@corbin_braun ·
once you find the concept that you fully align with internally
you work toward it with a level of focus
that can not be acheived anywhere else.
concept of
I don't have enough energy is not even part of the equation
it is quite the opposite.
you have to do it,
it is by nature.
OpenRouter@OpenRouter ·
ElevenLabs x OpenRouter: Live-casting an LLM Battle Royale https://x.com/i/broadcasts/1qKVmydgwBZxB
Artificial Analysis@ArtificialAnlys ·
Phonic's Phonic 1 (High) is the new leading Speech to Speech model, debuting at #1 on the Artificial Analysis Speech to Speech Index at 87.1, while also leading on agentic performance and being competitive on latency
Phonic 1 is @phonic_co 's Speech to Speech model, available through the Phonic API at $0.07 per minute. We evaluated Phonic 1 at its high intelligence level through the Phonic API.
Key takeaways:
➤ Speech to Speech Index: #1 of 22 at 87.1, ahead of Grok Voice 3.0 (86.9) by a very small margin. The Index averages Speech Reasoning (Big Bench Audio), Agentic Performance (Tau Voice), Arena Preference and Task Success Rate
➤ Speech Agent Arena: #8 of 30 on preference (Elo 1012) and #4 on Task Success Rate (92.3%)
➤ Tau Voice: #1 at 79.9%, a clear lead of 5.4 points over the next model
➤ Big Bench Audio: #3 at 98.9%, behind StepAudio 3 Realtime (99.7%) and Qwen Audio 3.0 Realtime Plus (99.2%)
➤ Speed: #4 on Time to First Audio at 0.61s, and the fastest of the top 5 models in the Index
➤ Cost: $4.20 per hour of input audio
Congrats to the @phonic_co team 🚀
See below for more detail ⬇️
elvis@omarsar0 ·
We need to rethink agent infrastructure.
Companies are quickly moving from chatbots to autonomous agents that do real work across their systems. The infrastructure under those agents hasn't caught up.
@mintive is building that layer, focusing on governance, efficiency, and security. Agents get their own identities and permissions, traces are logged properly, and teams get token budgets to set clear limits.
- jack friks
@jackfriks ·
thank goodness i have post bridge MCP to schedule all these posts out using opus 5.5
- Every 📧
@every ·
Mike as a service. Coming soon.
dax@thdxr ·
is now a good time to get into cybersecurity insurance
Gabriel Chua@gabrielchua ·
i like when my dot manages my codex cloud threads throughout the night
Ben Tossell@bentossell ·
i expanded on this in my newsletter today and getting lots of responses
i rarely promote my newsletter but here’s the link if this tweet struck a chord
https://open.substack.com/pub/bensbites/p/ai-is-overwhelming-and-im-doing-it
Ben Burtenshaw@ben_burtenshaw ·
It was super fun to learn how @MistralAI built le chonk from the ground up in Europe in their own datasets. Why it excels at cyber. And why we should start building with it.
Allie K. Miller@alliekmiller ·
I’ve been texting with my OpenAI Dot for awhile and prefer it over the app.
Favorite use case is just screenshotting something, texting it to Dottie, and give instructions.
“Add to cal” “Handle this” “Ask Austin if he wants to go with me” “Add to my bucket list” “Explain this” “When can I do this?” “What will this conflict with?” “Remember I have to do this”
Also recommend asking it to make a contact photo. See below for Dottie the Dalmatian.
Alex Imas@alexolegimas ·
This is such an incredibly creative project.
- Every 📧
@every ·
Very little is free in NYC. But if you're a paid Every subscriber, our afterparty for Thesis: 2027 costs exactly $0.
Your agent can work late. You have a party to go to. DJ. Passed bites. Open bar. And more.
🥳 Join us at Pioneer Works in Red Hook, Brooklyn.
🪩 November 5, 2026. 6–9 p.m. ET. 21+.
Peter Gostev@petergostev ·
Gemini 4 Carbon, Genie 4, AA index 5, Anthropic IPO, 6.1 Terra & more AI https://x.com/i/broadcasts/1NGarobEZPRJj
Dean W. Ball@deanwball ·
I occasionally run into fortune 100 firms that have not adopting coding agents *at all.* adoption is still very very early.
- Dean W. Ball
@deanwball ·
"Yeah, people talk a lot about RSI as AI that does AI research. There's very little talk about self-replicating data centers, this idea that you can use AI to control robots and run fabs and build turbines or solar panels and build data centers. But I think we have that within grasp."