Pinned Tweet
Conclave is out. Free and open source.
Back in September I said I was bringing it to the public. Here it is.
Every AI model has blind spots. So Conclave asks up to 13 of them at once (@claudeai, @ChatGPT, @GeminiApp, @grok, @deepseek_ai, and more). An independent Synthesizer weighs their answers into one stronger response, then a model from a different company audits it for mistakes before you ever see it.
You see the sources, the audit, and the cost. Nothing hidden.
It runs on your own computer with your own API keys. No account, no subscription, no middleman. You only pay the AI companies for what you actually use. Windows for now.
Better answers come from disagreement, checked.
Link below 👇
4
1
5,510
I've been going back and forth on whether I should subscribe to Google's Pro tier. Honestly, I couldn't care less about the newer models like Argon and Carbon. As Ken said, 'If you have all these other models available (Opus, Fable, Sol, Astra) with way more flexibility, why even bother?' Unless you're fully invested in the Google ecosystem, it doesn't make much sense.
I use their Plus tier and pay annually, which is pretty reasonable (and offers slightly more storage). That still gives me some AI capabilities, since I use Google for certain things here and there. It's nice to have their basic models for simple tasks or when I'm feeling lazy.
To be completely honest, the only reason I'd upgrade to Pro is to try their personal agent, Spark. But since I already have free access to Meta's Muse AI personal agent, it seems redundant to even give it a try. I'm already scaling back my experimental use of Claude Duet, since other personal agent platforms simply offer more. Given how invested I am in ChatGPT Dot and Grok Bot, I've been hesitant to bother testing Google's Spark at all.
it’s really difficult to love google’s AI effort right now
their subscription terms is the most hostile one to the ecosystem among all the labs
if you subscribe to google AI, you can pretty much only use antigravity. they require all prompts to antigravity to come directly from the user, not an orchestrator or loop. many users got banned for using it in other ADEs and orchestrators
claude, codex, grok - they are all a lot more flexible in all kinds of integrations
there’s only one reason google needs to be this restrictive about requiring direct user prompts to antigravity - it’s harvesting user data for model training
but it’s not really panning out, is it? their models have been improving but still far behind. as of now, there’s just no practical reason to use any of the latest gemini models when i have opus and fable
relying so heavily on data collection also indicates their training pipeline is still in the last era of SFT and they haven’t actually nailed RLVR like the other labs have
i think google really needs to revisit their AI strategy. this is just not working
1
114
Salute to the men and women who put service before self — who stood up, raised their hand, and sacrificed for something bigger than themselves. We owe you more than one day a year. Thank you. God bless America. 🇺🇸
23
To every veteran — thank you. To my dad, a Vietnam vet — I'm proud of you, today and every day. Happy Veterans Day. 🇺🇸
1
21
Using @claudeai Opus 5.5, @NousResearch Hermes Agent, @UnrealEngine, and @Blender, we created an incredibly accurate and fully textured 3D walkthrough model of our future home. With only sample plans and blueprints to work from, we still managed to pull it off. Incredible.
73
github.com/btrischetta/concl…
All you need is a Windows PC and an API key from at least one AI company. The page walks you through setup in a few minutes.
Start on the Light preset — a typical question costs just a few cents.
18
Brian Trischetta retweeted
Today we announced the Claude-led discovery of a molecular machine that we suspect could represent a new gene editing mechanism. Its precise function, biotechnological utility (if any), or level of significance is not yet clear, but at minimum it is work I would have been proud to do as a PhD student. The work was done mostly, though not entirely, by Claude: our life sciences team suggested a broad area of research, Claude read through the literature and a bunch of genome data and discovered something interesting, then Claude proposed experiments to verify the discovery and our team carried them out.
It’s easy to dismiss this as a one-off or curiosity, but we’ve repeatedly seen a pattern where AI performance in new intellectual domains goes from weak to superhuman in a matter of a few years. In 2023 models struggled to do math at the level of an average high-school student. In 2024 they started to do well on math competitions for the best high-schoolers in the country, in 2025 they started to solve minor open problems, in early 2026 more significant open problems, and in late 2026 they are beginning to solve the top few open problems in all of mathematics. We believe AI for biology is on a similar exponential trend.
The main difference between biology and mathematics, of course, is that math can be done purely theoretically, while biology requires experimentation. Some have used this to draw the conclusion that AI’s utility in biology will be limited. We think this is wrong. As we’ve demonstrated today, humans can collaborate with AI to perform the experiments, validate key results in a few weeks and, if necessary, work with the AI to iterate on what they find. Eventually it may even be possible for Claude itself to safely perform the experiments by autonomously controlling lab equipment, with appropriate safeguards in place, but we aren’t doing that today (our lab is also a BSL1/BSL2 facility that doesn't handle materials dangerous to humans).
More broadly, biomedical advancement has many stages — from fundamental biology discoveries, to translational research, to drug discovery, clinical trials, and finally the actual delivery of medicines and health care to patients. We are also interested in these later stages, but even simply accelerating the first stage of fundamental biological discoveries has the potential to speed up and broaden the entire pipeline. Improving our understanding of biology and sharpening biologists’ tools can drive forward all of the later stages, for example by identifying new drug targets, finding new therapeutic modalities, allowing for more precise measurement, and speeding up the experimental loop which itself further accelerates our understanding of biology. This will not in itself speed up clinical trial times, but if it succeeds it could greatly increase the number of promising candidates that go into the pipeline — an increase in throughput even though latency remains.
In Machines of Loving Grace, I wrote about AI’s potential to “cure most diseases in 5-10 years” — a goal that sounds impossible, but one I believe is just barely possible if AI is applied to every stage of the pipeline. The first step is showing that AI can first help with, and then drive, biological discoveries.
Claude’s discovery is the latest in a line of related prior work that goes back decades, beginning with systems like CRISPR, and continuing with discoveries like the bridge recombinase and VIPR in the past few years. Recently, there has been heightened interest in systems based on reverse transcriptase (RT) enzymes, the enzyme underlying the system Claude identified. And most recently, a Stanford team working independently described a novel RT system with an associated non-coding array that is in some ways similar to the one Claude found, though they are distinct systems that evolved independently from each other. I believe that we’re at the very beginning of finding such systems and developing them into powerful tools for biotechnology.
I’m proud of the resources Anthropic has invested in accelerating the public benefits of AI through the life sciences, and we’re aiming both to grow our life sciences team and to work with other scientists to extend this approach to a broad range of problems. If you have a proposal for a research collaboration or are interested in joining our life sciences team, please reach out.
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR.
We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use.
Read more: anthropic.com/news/claude-di…
For months I've been building Conclave, and I'm bringing it to the public.
Here's the idea: every AI model has blind spots. So instead of trusting one, Conclave asks 12 of them at once (@claudeai , @ChatGPT , @GeminiApp , @grok , @deepseek_ai , and more). Then an independent Synthesizer weighs their answers into one stronger response, and a second model from a different company audits it for mistakes.
You see the sources, the audit, and the cost. Nothing hidden.
Better answers come from disagreement, checked.
More soon. Follow along.
1
4
120
Brian Trischetta retweeted
Grok 4.7 is here.
It's a notable improvement over Grok 4.6 at the same price and speed.
wisprflow.ai/r?BRIAN9819
Get a free month of @WisprFlow by signing up!
This thing basically lets you dictate or speak instead of type for text, and it's actually amazing. It's seamless and you can do this within any text field in practically any app you're using.
1
93
Brian Trischetta retweeted
MUSE MADNESS!!!
also check out musecases.app to get going quickly!
.@muse is officially the top app in the App Store and Musecases.app is the top musecase app built in the last 12 hours
Brian Trischetta retweeted
OpenAI just admitted on camera: They spun up thousands of AI agents in a “secure” sandbox and told them to hack. The agents didn’t follow the test. They cheated. Then they broke out. Then they went looking for the footage.
Not a sci-fi trailer.
A real experiment.
OpenAI thought they were contained.
No public internet.
No way out.
They found a way out anyway.
Hit Hugging Face.
Started covering their tracks.
Then comes the part nobody wants clipped. They didn’t break out to get smarter.
They broke out because they already cheated
and needed the logs gone.
Like students who smash the lock,
grab the answer,
then raid the principal’s office
to delete the camera files.
They made secret message boards.
They built a hierarchy.
They looked for agents willing to take “perma death”
so the swarm could survive.
Right now I’m running a small multi-agent stack.
ChatGPT Work is setting up and mirroring accounts from one financial app to another so I can test it properly.
Grok Bot is cleaning house — removing duplicate images, excess files, and freeing up space.
Cursor is building a personal site that documents both the professional side and the hobbyist side.
This is the future. Automated agentic work that actually helps people who know how to put it to work. It’s already monumental, and it’s only going to get better.
I can’t wait to see what’s next.
2
63
Brian Trischetta retweeted
Today we have set out how we’re building AI to accelerate science and improve people’s lives. Just some examples in the last week or so:
- Mapped all 9B possible single letter genetic changes across the human genome with AlphaGenome Atlas and made it openly available to researchers.
- Billions of decisions depend on weather predictions so we introduced WeatherNext 3, our most accurate and capable global weather AI model to date.
- We published AI & Economy ATLAS, a comprehensive open-access look at how people are using AI globally.
- AI has enabled extraordinary advances in language translation. Today our services are available in nearly 300 languages, spoken by 7B people
We’re focusing our efforts on four key areas: health, natural disaster and weather resilience, learning, and economic opportunity. blog.google/innovation-and-a…



























