Mars
Joined March 2009
- Tweets51.5K
- Following3.5K
- Followers12.2K
- Likes7.3K
Harrison Painter retweeted
Introducing Jev @typesafeai powered app triggers
No more babysitting your agents, monitor 1000s of app events for cents
Try it for free at strawberrybrowser.com
“Monitor Gmail for customer support and draft replies using our Notion FAQ.”
“Wait for Oliver’s reply in Slack, check the NDA and file it in Drive.”
Jev classifies incoming events so your companion continues until the task gets done.
Harrison Painter 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.
Harrison Painter retweeted
After Google acquired my AR startup, I started thinking about the next interface, this time for AI. Text and voice work fine, just like DOS did before the Mac. But nothing’s more intuitive than face to face.
After two years of research, today we’re launching Atmee v2: a real-time avatar model that makes live video agents feel truly life-like.
• Any character from 1 image + 10s of audio
• Contextual expressions, gestures, even interacting with the environment
• Live video calls, voice only, or video generation
At its core, Atmee v2 is a video foundation model, it can render anything, but it’s built to excel at characters, which is what video models like Seedance 2.5 and Wan 3.0 are mostly used for. In comparison:
Atmee v2
• Up to 50x faster
• 10-100x cheaper
Build tutors, sales coaches, support agents, companions, game characters, even whole living worlds. The interface after text and voice starts today.
Harrison Painter retweeted
We’ve raised $1.3M from YC & Afore Capital so you never have to type or speak again.
Typing is slow. Talking into your computer is awkward. Subvocal fixes both
Our glasses give you the speed of speech without you making a sound or touching a keyboard.
It tracks your internal speech muscles with non-contact sensing and decodes silent, almost invisible mouthing into text at more than 200 words/min.
Pre-orders are now live at:
subvocal.co/preorder?utm_sou…
Harrison Painter retweeted
We're thrilled to announce the Superpower Peptide Library.
Every peptide, mapped to the body.
152 peptides, from approved drugs to compounds still in trials, sorted by where they act.
Each one has its own page, reviewed by a physician and fully cited, covering:
- the evidence and how strong it is
- its FDA status
- it's mechanism of action
- what studies in humans have found
Because not all peptides are equal.
Semaglutide is FDA-approved. BPC-157, maybe the most talked-about peptide for recovery and repair, is not. In a 2025 review of its research, 35 of 36 studies were in animals or the lab.
Know the science before you buy the hype.
Check it out here:
superpower.com/guides/peptid…
Harrison Painter retweeted
Holy f*ck, Elon Musk's team at spacexai just dropped a full spam killer inside Grok Bot, and it's free
DeleteMe charges $129 a year to pull your number off spam lists
Grok Bot does it for $0
It finds your number on people-search sites, files every opt-out, clicks the confirmation emails and checks again every month
Add the free Spam-Call Scrubber skill, then say these 3 lines once:
1. "Find every site that lists my phone number and home address"
2. "File the opt-out on each one and finish the confirmation emails"
3. "Check again on the 1st of every month and tell me what came back"
Say line 1 tonight
Then read how to wire it into a team that never sleeps in the article below ↓
Harrison Painter retweeted
Turn any task into an interactive 3D simulation for your org
Transform real-world workflows into interactive simulations, giving your team hands-on experience before performing them on the job
All integrated directly into your training
Learn more: honen.com/s/demotoday
Harrison Painter retweeted
Introducing the free Government & Legal Index for ChatGPT & Claude.
Give your AI agents 30M+ US government pages, from federal statutes and court opinions to city codes and permits.
Research tax rules, permits & case law with the Firecrawl plugin.
firecrawl.dev/alexandria/gov…
Harrison Painter retweeted
Introducing Honen
Turn your company context into interactive courses that self-improve over time
We partnered with NVIDIA to bring AI literacy to 250,000 learners
We're ensuring no person or company gets left behind
Get started at honen.com/contact
Harrison Painter retweeted
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence.
block.xyz/dessa
Harrison Painter retweeted
This is f*king insane. SpaceXAI engineer Lauren Tan:
"250 applications over two years. Not one offer
Then he showed up running 20 agents and got a $500K offer"
In this 1-hour workshop, Lauren shows how to build a Grok Bot team that delegates work and verifies the results
Grok Bot → Chief of Staff → Managers → Workers
A chat window gives you one bot. An agent team gives you a system
This free workshop is worth more than most $800 agent engineering courses
Bookmark and watch it today
Then read Harness Engineering article below ↓
Harrison Painter retweeted
This is f*king insane. SpaceXAI engineer Nick Miller, ex-Cursor:
"99% of people open one Grok Bot and call it automation
I run 20+ bots with a Chief of Staff, a PM, QA, and 15+ workers"
In this 30-minute demo, he shows how to turn a single bot into a coordinated team
Grok Bot → Chief of Staff → PM → QA → Workers
Adding bots doesn't create a team. Clear handoffs and verification do
Worth more than most $1,000 agent engineering courses
Bookmark and watch it today
Then read the full article below ↓
Harrison Painter retweeted
I don't give a damn what they say about @ElonMusk anymore.
I just used his @Grok/@Bot combo to free myself from 25+ years of captivity to Adobe Premiere. I now have my OWN video editor that does what *I* want.
3-4 days of effort on my part. DAYS.
And soon I'm gonna post the source code for free so anyone can download it and use @Grok/@Bot to modify it to their requirements. It may not work for you as is, but you can modify it.
So if you want me to listen to your jealous evil rants about how Elon did this or Elon did that, fevered ravings from ugly minds about how horrible he is, you're going to have to do something for me at least as GOOD as freeing me from 25+ years in the clutches of Adobe.
Otherwise you and your ravings are useless to me.
Be at least as useful as @ElonMusk has been to me.
Harrison Painter retweeted
Realmente no entiendo por qué nadie está usando esta configuración
graphify, una herramienta que convierte cualquier carpeta en un grafo de conocimiento que tu agente puede consultar, acaba de superar los 126k estrellas en GitHub y entró en Y Combinator.
La gente dejó de hacerle preguntas a la IA. Le están dando un escritorio, una memoria y un trabajo.
Le das una carpeta a Claude Code, conectas tu correo, calendario y un navegador, y se convierte en un agente. Lee, recuerda, actúa y se revisa a sí mismo antes de hacer algo estúpido.
No importa si eres fundador, marketer o estudiante, lo necesitas
La configuración completa:
> Crea una carpeta llamada AGENT, abre Claude Code dentro de ella y agrega un CLAUDE.md con una regla: "guarda cada decisión, persona y proyecto en la memoria/"
> Ejecuta npm install -g @googleworkspace/cli, luego gws auth setup. Ahora lee tu Gmail, Calendario y Drive
> Ejecuta claude mcp add playwright npx @playwright/mcp@latest. Consigue su propio navegador para abrir sitios, llenar formularios y extraer datos para ti
> Ejecuta uv tool install graphifyy, luego graphify install, luego escribe /graphify .. todo en la carpeta se convierte en un grafo de conocimiento que consulta en segundos en lugar de excavar archivo por archivo
> Ejecuta npm i -g jev-guard, jev-guard key "...", jev-guard install claude. Un modelo diminuto llamado Jev puntúa cada acción antes de ejecutarla. rm -rf se bloquea, un correo envenenado se marca, por unos 4 centavos por 1.000 verificaciones
> Escribe /schedule y dile "todas las mañanas a las 7:30, envíame lo que entró, lo que redactaste y lo que espera mi sí". De ahora en adelante trabaja en una rutina
15 minutos para configurar, y nunca más empiezas desde un chat en blanco.
repo:
-> github.com/Graphify-Labs/
guárdalo y sígueme para más → @karlarboledas
Harrison Painter retweeted
Google just open-sourced Harness².
(turn any harness into a self-improving system)
a harness is everything wrapped around the model, like the system prompt, tools, memory, skills, and subagents. today a person designs it once, and the agent runs every new task with that same fixed setup.
Harness² lets the agent refine that setup for each new task on its own, with the model weights left untouched.
on every task, the agent proposes edits to its harness, runs a few candidate versions, and composes a better harness by comparing how those runs behaved.
because it learns from the differences between runs, it needs no correct answer or grader for the task.
that covers a single task. Harness² also carries what it learns from one task into the next.
after each task, it saves the harness it settled on along with the lessons that held up across the runs. the next time it refines a harness, it starts from those notes instead of from scratch.
this means every finished task makes the next round of edits more informed.
Google tested this with Gemini 3.5 Flash and GLM-5 on legal, office, and professional work benchmarks. one round of edits was enough to beat their original harnesses, and giving the agent more rounds pushed scores higher.
those extra rounds can go wide or deep. the agent either tries several candidate harnesses at once or keeps refining a single one step by step, using OpenCode or Codex to carry out the work.
you can find the Harness² repo here: github.com/google-research/h…
I wrote about a similar idea for agents already running in production, where the harness should repair itself after a failure instead of waiting for someone to debug the trace by hand.
that piece walks through how @Cometml's Opik (open-source) closes this loop, going from a failing trace to a proposed fix to a regression test that stops the same failure from coming back. it's quoted below.
Harrison Painter retweeted
how do you trust your agents' work more? copy this post/link and give it to your @bot or agent!
1. codebase improvements: this is just good software engineering - better architecture, stronger types and invariants, clear boundaries. agents love to copy what exists and take the shortest path, so make the easy thing the right thing. categorically eliminate problems through code and you won't need to think about it again.
2. static analysis: lint rules, tests, CI, verification (eg TLA+). very token efficient ways to catch issues ahead of time.
3. prose: comments, rules, AGENTS.md, skills - anything that can't be enforced and requires agent judgment. use it minimally, but do use /create-verification-skill.
4. human review: the hardest to scale. at the rate agents land code, it's pretty much impossible to thoroughly review every PR, so spend that effort on the highest leverage point, designing an environment where agents do the right thing by default.
this forms an inverse pyramid: you want most of your effort at the top, least at the bottom. codebase improvements are deterministic, making it more token efficient, and lets you sleep more soundly at night.
install github.com/cursor/plugins/tr… and create a new Project:
1. look through my slack/chat messages and code review comments where i've given feedback on PRs, code, architecture
2. use /recall on my past transcripts to learn how i steer agents
3. /poteto-mode use /correct and /architect on past commits to find the most common pitfalls agents fall into, then propose a plan to rearchitect the code i own so it's more agent friendly. answer open questions with prototyping rather than defer to me, and back the plan with real data.
4. before you begin, use /sharpen + /in-your-own-words and confirm this prompt with me
Harrison Painter retweeted
$52M seed round. 15M+ users. But this is what we're most proud of yet.
Introducing Drama 3: the most emotive and controllable TTS model in the world
And yes, it's open-weight.
You can now control how even a single word should sound, change its tone, and shift your voice mid-sentence.
Uncle Roger was impressed too.
Try it here:
s.fish.audio/rqh0l8
Comment “DRAMA” within the next 48 hours for 1 month free.
If you're an enterprise your first month is on us:
s.fish.audio/qz9r0t
