Slingshots // Four is live! Another batch, another fourteen projects shipping open source artifacts that I’m excited about. See below for the full list. A few themes from the batch: 1. Harness time: This quarter harnesses shot up in visibility, with increased appreciation for the parts of an agent that aren’t the model and what they can give you. This batch includes a harness supporting persistent agency (Headlong); a harness supporting self-improvement via context management (ACE); a harness supporting self-improvement of the agentic harness itself (Exo); and a harness supporting multi-agent setups (dotagents). 2. Up and down the stack: There’s innovation to be had at every layer of the stack. We saw projects worth backing at the level of kernels (Thunderkittens); inference (M*); training (Marin); data (Atlantic-CC); evals (Decision Assistants); optimization (SkyDiscover); applications (Wagglehaus), etc. 3. Talk of the town: Slingshots continue to tackle timely problems at the frontier. Concurrent with Jev taking over X, an even faster type 1 decision model (CLM) came out of academia. With RSI on the brain of every big lab researcher, we now have a public literature retrieval benchmark grounded in authors’ firsthand accounts of their research process (ScholarCatalyst). And a new RL training method (Pedagogical RL) addresses head-on the question vexing RL practitioners of how privileged information can be used to discover generalizable behaviors, not just verify. Congrats to all the researchers in this batch and the previous three who continue to ship their research out into the world with open artifacts that can be adopted and built upon. Open science leads to better outcomes for everyone. And the good times will continue to roll – batch five is looking just as good. If you’re a researcher with a project that’s gaining momentum and ready for an adrenaline shot, shoot me a DM or apply at laude.org/slingshots. 👏 @a1zhang, @AlexKrentsel, @ankrgyl, @Azaliamirh, @bariskasikci, @bfspector, @chelseabfinn, @chipro, @Diyi_Yang, @dlwh, @drmapavone, @HazyResearch, @jackyk02, @jonasgeiping, @JonSaadFalcon, @jure, @kothasuhas, @lateinteraction, @martin_casado, @mertcemri, @michaelryan207, @MikeCafarella, @NickAJalbert, @NoahZiems, @nsagan271, @ohmyksh, @percyliang, @qizhengz_alex, @RussoMatthew, @samrmadden, @shagarw21, @ShashwatGoel7, @shulynnliu, @simran_s_arora, @souradipchakr18, @stuart_sul, @tianyu_li_, @tim_kraska, @WilliamBarrHeld, @yoonholeee, @YejinChoinka, @Stanford, @MIT, @LaudeInstitute, @CarnegieMellon, @UW, @UCBerkeley, @MPI_IS, @UWMadison

Not gonna lie, I was kind of surprised that we were able to create a review bot that’s apparently both faster and cheaper than all these venture backed solutions in just a week, given how much investment is going into coding and review agents right now. 🤷‍♂️ maybe just a different place on the cost-quality-speed curve (a fast high quality review is worth a dollar to us and maybe isn’t to someone else)? in any case, we’re happy customers of ourselves.