Tim | Optimatic Solutions LLC retweeted
i built @WisprFlow’s paid ads program
here’s how i’d rebuild it in 30 days
Tim | Optimatic Solutions LLC retweeted
Your laptop is now the voice of your whole house.
Boubou turns open-source TTS models into local runtimes with one command. Your phone, robot or smart home on the same Wi-Fi just talks to it.
100% local. Built on @LiquidAI_ + @huggingface 🤗
github.com/runboubou/boubou
Make viral content in one prompt with Fable 5.2 + AI/ML API 💥
With aimlapi.com/mcp your agent can:
→ Find what’s blowing up on any social platform
→ Decode why each video went viral
→ Create content with top video models
→ Grow your account on trends that already work
First 50 commenters get a $10 promo code!
One MCP. No subscriptions. 0% markup.
Prompt in comments 👇
Tim | Optimatic Solutions LLC retweeted
What if we could manipulate UI at the speed of thought?
Built this voice coffee ordering system with @typesafeai Jev. The drink and any updates show up while I’m still mid-sentence, ~200 ms from word to screen.
Feels pretty magical!
We’ve raised $51 million to rethink how kids learn with AI. Our bet: conversational learning.
Language isn’t just how we communicate. It’s how we think. That’s the idea behind Gakku, our AI learning coach. The learning process itself is the product—not something to automate away.
Does expression matter more in the age of AI? This time, the AI is asking.
Watch Raku, our AI learning companion, interview co-founder Annie Chen @anniechen419 , who created him.
Tim | Optimatic Solutions LLC retweeted
LinkedIn is dead
Introducing job search tools for ChatGPT & Claude.
→ Match your resume to 7M+ open roles
→ Find hiring managers to email from 250M+ people
→ See what they care about before you reach out
Run your job hunt from any harness with the Firecrawl plugin.
alexandria.firecrawl.dev/go/…
DUDE WTF?? ... Now you can turn your Claude Code into a fully loaded setup with 𝗷𝘂𝘀𝘁 𝗼𝗻𝗲 𝗶𝗺𝗮𝗴𝗲. 🤯
Simply drag the image into Claude Code in your project, send this, and you're done:
“Read this image, compare it with my current setup, list what’s missing, and add it once I say OK.”
No tutorials. No setting things up one by one. No starting over.
Perfect for running big projects, blocking rm -rf, starting new projects, setting up a new machine, and letting one AI (Codex) keep another in check :)
𝗧𝗶𝗽 for $20 Claude Code/Codex users:
Your 5-hour limit 𝘀𝘁𝗮𝗿𝘁𝘀 𝘁𝗵𝗲 𝗺𝗼𝗺𝗲𝗻𝘁 𝘆𝗼𝘂 𝘀𝗲𝗻𝗱 𝘆𝗼𝘂𝗿 𝗳𝗶𝗿𝘀𝘁 𝗺𝗲𝘀𝘀𝗮𝗴𝗲. Set a scheduled task to send a good morning 2–3 hours before you start work, and by the time you start, you're only 2 hours away from a full reset.
Claude Code:
/schedule every weekday at 7am, no repo, use Haiku and just say good morning
Codex:
Set a weekday 7am cron job: codex exec "good morning"
𝗖𝗼𝗱𝗲𝘅 𝘁𝗶𝗽: if you still have half your quota left when it resets, you’re throwing away days of Astra and Sol.
Use `/goal` to squeeze every last bit out of it and clean out what months of vibe coding piled up: dead code nothing calls, the same logic written several times over, dependencies you don’t need, old sessions and worktrees hogging your disk, or even scheduled tasks that have been running for nothing.
Here are 5 prompts and goals you can copy-paste directly. ↓
Tim | Optimatic Solutions LLC retweeted
Meet hunch! Jev-like decisions in ~20ms without even needing a GPU, learning live from a teacher model.
Built on @GoogleGemma's EmbeddingGemma 2, it can works with any teacher model like @CloudFlare's Clef.
Multimodal, w/a systemone endpoint, slots into your existing stack 🧵
Tim | Optimatic Solutions LLC retweeted
We decoupled memory from the model.
Living Brain is one persistent brain for ChatGPT, Claude, Cursor, Codex and your own agents. Write in one, retrieve in any.
92.2% on LoCoMo. 464ms median retrieval. Up to 22.6x fewer tokens per question.
LLMs have parameters. Living Brain has plasticity.
Tim | Optimatic Solutions LLC retweeted
i’ve gotten 2 billion views for startups, influencers, and myself.
here’s how to go viral (without getting lucky):
Tim | Optimatic Solutions LLC retweeted
An open-source AI agent just shipped a desktop app that's 5 MB.
Five. Megabytes.
Meanwhile your AI chat app is a 300 MB browser in a trench coat that forgets you every time you close it.
This is groundbreaking and nobody is talking about it.
Tim | Optimatic Solutions LLC retweeted
The wait is over.
Mercury Desktop is here. All of Mercury in one app for macOS, Windows and Linux.
It learns how you work. It keeps a second brain that grows with you. Optimus uses your computer and asks first. And it calls you back.
Free and open source.
Tim | Optimatic Solutions LLC retweeted
Got fable to hand-write weights of a 100k param model to recognize real versus fake legal citations.
Basically one-shotted a full NN that’s better than training it
Tim | Optimatic Solutions LLC retweeted
We just killed Clay
Introducing headless Clay for agents.
→ Search 250M+ people & 26M+ companies
→ Get emails, job & company data
→ 1000 credits/month free
→ 88% cheaper than Clay at scale
Run all of your enrichment flows in ChatGPT, Claude, Grokbot, and beyond!
firecrawl.dev/alexandria/cat…
Tim | Optimatic Solutions LLC retweeted
Your Harness. You Define It.
Meet Creator Mode in DeepSeek Harness.
Turn ideas into plugins that you can use, from a design workspace to a sandbox game or a 3D LLM visualizer.
What will you create?
Tim | Optimatic Solutions LLC retweeted
RightNow is out today. our first “System Zero” model
it streams in text, JSON, PDFs, images, voice, codebases, robot state and video, and returns a decision with a probability for every option while the input is still arriving
30 ms decisions on text. up to 1,024 questions in one call. output is free
system 1 is fast thinking. system 2 is slow reasoning. “System Zero” is the step before both -- the decision itself
this is our first checkpoint. there is a lot of work ahead, and we decided to ship early to get your feedback. more features and fixes are shipping this week, with more checkpoints after
rightnowai.co
Tim | Optimatic Solutions LLC retweeted
Replying to @cachetronaut_
Yeah, there are different evaluations that measure different things. You can probably find a benchmark for whatever specific task you're looking to evaluate. Usually they publish the API cost for different models and reasoning efforts, which you can then adjust with subsidization information that you can get from mypriors.com, or just the real API pricing repo, or other sources. But it's highly dependent on what specific thing you're doing.

























