Hussam Ali

@EthanCastr @ozenhati @hannaniapas1 @JonathanRoss321 @sundeep @GroqInc Congrats!

Congratulations @ozenhati @hannaniapas1 @JonathanRoss321 @sundeep and others from @GroqInc on the new deal!

@EthanCastr @GroqInc @nvidia @Kimi_Moonshot Very impressive stuff Ethan, this is huge!

In light of the @GroqInc and @nvidia news, I am going to start posting more publicly about a personal project I am working on: Augment - augmenting.work Here's a demo of me making a website on Augment using @Kimi_Moonshot running on @GroqInc . Less than 10 seconds to generate. I made a very simple website for the sake of the example. I think current vibe coding tools are a bit too slow to iterate comfortably given the fact that it may or may not do what you want, but you have to wait ~ 2 minutes to find out (and potentially spend money on tokens that wound up making it worse). I also think deep research queries take a little too long for most folks to casually use. Shoutout to @perplexity_ai for how well they do around this. You can use open source models on @GroqInc , @cerebras , and LLMs from the major labs as well.

@AnthropicAI @EthanCastr called it. Described something very similar to me ahead of time

We’re releasing Bloom, an open-source tool for generating behavioral misalignment evals for frontier AI models. Bloom lets researchers specify a behavior and then quantify its frequency and severity across automatically generated scenarios. Learn more: anthropic.com/research/bloom

@EthanCastr Ethan, I know you well enough to say those finals stand no chance! Can’t wait to see your progress after semester’s end!

Putting projects on pause for finals. We're in a good spot. augmenting.work/experiments Working on enabling generation/iteration at the speed of ideas in one-shot.

@OpusClip Very cool

🚀 Turn podcasts into viral clips in minutes. Virality Score finds your best moments, AI B-Roll adds flair, Speaker Detection keeps faces framed, and removes filler words like “um” & “uh.” Don't sleep on this. Try OpusClip today and get 25 free clips/month.

@WorkflowWhisper Crazy seeing this progress unfold in real time

Claude and Cursor can now deploy n8n workflows directly into your instance. Not "generate code you have to fix." DEPLOY. 95% complete. Ready to run. And you don't change a single thing about your setup. Same Claude you already use. Same Cursor you already use. Same n8n instance you already run. Just connect Synta's MCP and watch what happens. I typed: "Build a competitor monitoring system that scrapes pricing, analyzes with AI, and alerts Slack when I'm being undercut" Didn't open n8n. Didn't configure a single node. Didn't debug a single webhook. Closed Cursor. Made coffee. Came back. 6 workflows sitting in my instance. Connected. Running. Time: 4 minutes Nodes configured manually: 0 Consultant quote for this: $14,000 Here's why this changes everything: Most AI tools generate broken JSON you spend 3 hours fixing. Synta's MCP: → Interviews you before building → Scrapes real-time n8n docs (not 2023 training data) → Deploys directly to YOUR instance → Auto-debugs before you even see errors Your workflow. Your instance. Your existing tools. Just 10x faster. While consultants schedule "technical scoping calls"... You already shipped. Comment "MCP" and I'll send you: → Setup guide for Claude + Cursor → 5 workflows to deploy in your first hour → Link to check if you got early access The barrier to automation just became a conversation.

@sundeep I need to utilize web search more often myself

This aligns with my usage of the closed models. With OpenAI, I primarily rely on thinking with web search.

@sundeep Very interesting, I will stay tuned 👀

👀👀👀

@diodeinc @AnthropicAI @cojennin Very interesting.

We worked with @AnthropicAI to teach Claude how to be a better electrical engineer. Claude 4.5 is the first frontier model trained with our data, and we saw a major improvement in both accuracy and speed for electrical reference design generation. Huge thanks to @cojennin and the Anthropic team for making this possible. claude.com/blog/making-cl…

@ozenhati @EthanCastr @hannaniapas1 Thank you for sharing! 🙏

@EthanCastr @Electricaliee @hannaniapas1

A good friend, @Electricaliee and prob the smartest (and hardest working) person I’ve ever met is looking for a electrical/hardware engineering-focused internship (spring) and full-time role (may graduation) I’ve worked on a few AI/ML/LLM-based projects with him and he was one of the first TSMC intern classes (along with other jobs). Ik he deserves a shot more than anyone. Tagging a company he’d be an asset to and is already familiar + built with: @GroqInc @ozenhati I think he would be the best hire (maybe) ever. He’s looking into the ASIC Formal Verification but (imo he can do anything so) he’s also sending in apps for the general opportunities roles. (I posted this because he’s too busy working/studying and I can’t bear to see him not using his skills)

@EthanCastr I can’t find the words to convey how appreciative I am for you. Thank you. I’ll make sure to keep working at it 🫡

@GoogleAI @Google @googledocs @GoogleWorkspace Can y'all add a bit. ly type link shortener and QR code generator to google slides?

I also think @Replit , @vercel v0, @Lovable and the rest should consider using @cerebras and @GroqInc for MVPs and prototypes. It's very hard to edit and augment when you have to wait 2-3 min for the agent and it may/may not do what you want. Also, consider the price of something like Kimi or GLM or Qwen, it is on average 1/3 of the price of a frontier company's LLM and you can still have Sonnet/Opus or GPT-5.1 be the orchestrator. @Replit maybe you should add a fast design mode the same way you've added the fast mode for quick edits. Of course, if you want to just retain your partnership with Anthropic (and maybe google with gemini 3), just use Haiku 4.5 or Flash 2.5:preview. Theoretically if a code editor uses cerebras or groq, they may be able to create 3 previews of a site within a few seconds, for someone to do a visual choose your own adventure. @amasad has discussed how PMs are expected to come up with a mock or demo to hand off/show engineers. It's not so great if you start off with mid, then iterate upon mid. Also, we are not yet at the point where everyone can accurately externalize their thinking via a prompt, but we are closer to folks being shown X options and them selecting which one is closest to what they were imagining. @mattyp, @amasad, @rauchg, @SarahChieng, @ozenhati, @JonathanRoss321 thank you all for having a public presence and making me aware of these tools/your tech. @chamath your mention of @GroqInc , last year is what introduced me to the world of inference, so thanks.

Working on a small project to demonstrate the value of faster inference augmenting.work Thesis: Frontier models have pretty fast inference, though not fast enough for test-time compute/reasoning and 10+ tool calls. If we are to augment with AI and save time, let's not create a new type of down time... waiting for responses. We used Cerebras as our inference provider to create websites, analysis, and textbook chapters within 2 seconds. We typically hit around 2000 tokens/s. Details: Using Cerebras and Groq as inference providers. Models - GLM 4.6, GPT-OSS-120B, Qwen... Horrible demo video below. Only the typing is sped up. I am still working on this. I just wanted to start posting updates for posterity because @GroqInc and @IBM partnered after I started this and I don't want to miss anymore news regarding the benefit of fast inference when it comes to tool-calling, Reasoning, Enterprise, and healthcare need for speed.