←
Poolside229 posts
Poolside avatar

Poolside

@poolsideai

We build models for agentic coding and long-horizon tasks. Try Laguna: poolside.ai/get-started

◷ Joined May 2023▧ 58 Photos and videos
Poolside avatar
Poolside@poolsideai·Jul 28

Today, we’re releasing Poolside Desktop Assistant. One place to run coding agents across macOS, VS Code, and Visual Studio. We built it for ourselves and have used it every day for the past year. Now we’re opening it up to everyone.

0:07
Ilya Kochik avatar
⟳ Poolside retweeted
Ilya Kochik@ilyakochik·Aug 25

Frontier-Bench looks good. However at n=74, it may be too small to reliably distinguish model checkpoints. Our quick analysis suggests 100+ tasks would provide a more reliable signal...

We’re releasing Frontier-Bench: a benchmark that measures and evolves with the frontier of agent work. Built by the team behind Terminal-Bench and Harbor, Frontier-Bench is an on-going community effort. Frontier-Bench v0.1 contains 74 tasks on which the best agents score ~34%

Post attachment
Poolside avatar
Poolside@poolsideai·Aug 17

We’ll be at ModCon ’26 in SF on August 18! @varunrandery is joining the frontier models panel to talk about building models for long-horizon agentic work, where open models differentiate, and what it takes to get them into production. Join us in SF or tune in online ↓

Building frontier models involves a hundred decisions rarely discussed publicly: when to stop scaling, what data to keep, how to differentiate, whether to release the weights. On August 18th at ModCon '26, Paige Bailey of @GoogleDeepMind, Joseph Spisak of @reflection_ai, Victor Su-Ortiz of @MiniMax_AI, and Varun Randery of @poolsideai are talking through the challenges of the industry from four different vantage points. Register for the livestream: luma.com/modcon-livestream

Post attachment
Poolside avatar
Poolside@poolsideai·Aug 17

Agentic evals are messy. A benchmark score tells you something about model performance, but it also reflects the whole system around it: the harness, sandbox, dependencies, timeouts and sometimes a loophole the agent found in the task. That’s why trajectories matter so much to us. They show what the agent actually did and whether the score means what we think it does. We publish them to make that evidence transparent and auditable, giving the wider community more to learn from. Watch @aalSonOfRavi and @ConnorBAdams go deep on all of this with @petergostev from @arena, including some surprisingly creative reward hacks!

Meet… Arena Conversations. @petergostev sits down with @poolsideai researchers,Connor Adams and Aalhad Patankar, to discuss how they’re building frontier open coding models. Episode drops today at 10am PT on our YouTube. They dig into Poolside's Laguna model family, why the team publishes full trajectories (not just benchmark scores) for anyone to audit, and how "experiments" at Poolside range from data mixes to harness design to reward-tuning decisions run tens of thousands of times a day.

0:24
Poolside avatar
Poolside@poolsideai·Aug 12

Come hear @mgalle and @sudip_r0y get into the weeds on post-training, agent RL, continuous learning, and what it takes to make models work reliably in production!

First episode of Field Notes, our new monthly series on the leaders shaping AI. @sudip_r0y, Adaption Co-founder, and @mgalle, post-training lead at @poolsideai discuss the last 5% of reliability and what it actually costs.

Post attachment
Poolside avatar
Poolside@poolsideai·Aug 11

we knew the community could make Laguna faster. 2.6x faster is pretty fun :) huge congrats to the winner, and to all 35 solvers who spent the last few weeks pushing Laguna XS 2.1 further! more reasons to build in the open, together 🤝

We started the MLX.fast challenge with @poolsideai with one key question. How much faster can the community make Laguna XS 2.1 run on a Mac? The answer so far has been 2.6x faster. Nearly 1,800 submissions and 35 solvers later, the challenge comes to a close today. And there’s one more thing. One of the solvers is taking home a Mac Mini M4 24GB! Winner below ↓

Post attachment
Morgan McGuire avatar
⟳ Poolside retweeted
Morgan McGuire@morgymcg·Aug 6

Our SENPAI agent is currently no.1 on the @poolsideai x @eigenlabs inference optimization comp (for now) and first to break 200 TPS decode Lovely first validation after a complete re-write of the agent to use @OpenHandsDev instead of cc

Post attachment

Excited to launch MLX.fast with @eigenlabs today. It's an open autoresearch competition to make Laguna XS 2.1 inference as fast as humanly (and agentically) possible on consumer Macs. Eigen's agents already found 36.8% faster inference, and that's before the competition even started. The best part of open weights is that the community takes a model further than any of us could. 
Can't wait to see what everyone does on the leaderboard!  mlx.fast/

Alex Cheema avatar
⟳ Poolside retweeted
Alex Cheema@alexocheema·Aug 5

Poolside are pioneering models built specifically for local hardware. Laguna S 2.1 is a great model for DGX Spark / MacBook. The number of tokens generated is probably an order of magnitude more if you include tokens generated locally.

We just crossed 10T tokens served across all our models in less than 3 months! Laguna S 2.1 is pushing new highs at ~300B tokens a day, and has processed +2T in the 14 days since release. That’s across @OpenRouter @vercel and our direct API. Really good to see demand for open models keep accelerating.

0:14
Poolside avatar
Poolside@poolsideai·Aug 5

We just crossed 10T tokens served across all our models in less than 3 months! Laguna S 2.1 is pushing new highs at ~300B tokens a day, and has processed +2T in the 14 days since release. That’s across @OpenRouter @vercel and our direct API. Really good to see demand for open models keep accelerating.

0:14
Poolside avatar
Poolside@poolsideai·Aug 4

Thank you to everyone who tried Desktop and shared feedback in our first week! A lot of 1.4.0 came directly from you. Update the app, mix and match any model with any harness, and have fun with it. Get started: poolside.ai/get-started Then come tell us what we should build next: discord.gg/NAnCKRbZa

Poolside avatar
Poolside@poolsideai·Aug 4

We made local inference faster for any model you run in Desktop. Try it with Laguna XS 2.1. Tabs and split panels are more responsive too, and code files open almost instantly.

Poolside avatar
Poolside@poolsideai·Aug 4

First-class subagents. Claude subagents now open in their own panels, where you can follow their full transcripts as they work. Codex subagents get clearer rendering and status reporting, so it’s much easier to see what each one is doing.

Post attachment
Poolside avatar
Poolside@poolsideai·Aug 4

Proper plan mode + agent questions. Agents can now pause and ask a structured question when they need more context, so you can fill in the gaps and shape the plan before they start working instead of having them guess.

Post attachment
Poolside avatar
Poolside@poolsideai·Aug 4

Native steering + queueing. You can now give an agent a quick “keep going, but by the way…” while it’s working, without interrupting the task. Or queue up several prompts for it to work through next. Available wherever the harness supports it.

Post attachment