incredibly excited to announce that droid is now v1.0 - we've modernized just about every part of our cli, including a full rewrite to the agentic engine that powers it. reflecting on the last few months leading this project, it has been awesome to see how heavily the team has embodied factory's operating principle of "build together," which is timely considering the doomer phase our industry is going through. "software factory" is a term everyone is throwing around these days but it often gives the vibe that humans are no longer in the loop. for factory, this couldn't be further from the truth. our agent factory is human-first: @ain3sh, @wenemilyy, @agent_crunchwrap and i went through every PR droid proposed, threw out the changes that overfit to a single model, and pushed droid to keep going. we collaborated on sessions together, experimented with hundreds of approaches, and fought the slop we left behind via huge refactors that we only had confidence in due to the extensive e2e tests we invested in half a year ago. getting to this point wasn't easy. it involved challenging our priors on how agents should work, deviating from old patterns, and setting innovative goals for our harness to hillclimb itself towards. attached is the video of the process that got us here - the result is the world's best agent. droid is back in first place, and we're here to stay.

Introducing Droid 1.0: the new engine behind Factory’s agent. Built for complex projects and everyday development: >more accurate >more efficient >faster than ever before

@FactoryAI builds Factory on @droid, and Finance is still one of the biggest internal users. Here are a few examples of how a lean team is building finance from the ground up on Factory, automating financial operations end to end:

Your scanners find security vulnerabilities faster than your team can fix them. Learn how Factory finds affected repos, upgrades dependencies, fixes what breaks, and opens PRs for your team to review. Register here:

Autoresearch with coding agents can now run for days on a single problem, but we've seen an increasing number of cases where they stop improving early. We address this issue with a simple idea: forgetting. Introducing our new paper: "Scaling Discovery Requires Forgetting"

interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works

As the world’s largest alternative asset manager, @Blackstone requires the highest standards of deployment flexibility and governance. Factory made it possible to operate agentic software development within Blackstone’s own data centers without compromising model choice or workflows.