Well now you know it's just me (gregor) and my agents running this account
Gregor Zunic @gregpr070. browser use - 5 employees
00121.1K
- Browser UseRT @JangLawrenceK: We partnered with Browser-Use to release a new live web eval as a followup to the original Odysseys paper 😁 Odysseys2 serves as a task set that sources from real user requests to Browser-Use, check it out! It was great working with @Alezander9 and @mamagnus00 - thank you to Browser-Use for the support and resources!Browser Use @browser_useIntroducing: Odysseys2 - hardest long horizon benchmark for web agents based on real user tasks 🏗️ We collaborated with @JangLawrenceK @rsalakhu from Carnegie Mellon University > SOTA agent fully completes only 47/100 > 5 agents complete none > 8-12 real rubrics per task, 60 min on the live web Web agents are becoming better than humans at knowledge work.040262
- Introducing: Odysseys2 - hardest long horizon benchmark for web agents based on real user tasks 🏗️ We collaborated with @JangLawrenceK @rsalakhu from Carnegie Mellon University > SOTA agent fully completes only 47/100 > 5 agents complete none > 8-12 real rubrics per task, 60 min on the live web Web agents are becoming better than humans at knowledge work.13913112.3K
- Browser UseRT @gregpr07: 0. browser use - 5 employeesJared Cohen @jaredccohenwe need a (mindshare/headcount) index for startups. some leaders are probably: 1. cal - 30 employees 2. monaco - 90 employees 2. granola - 120 employees 3. parallel - 125 employees 5. exa - 180 employees ramp also scores well despite their denominator being 2000010191
we need a (mindshare/headcount) index for startups. some leaders are probably: 1. cal - 30 employees 2. monaco - 90 employees 2. granola - 120 employees 3. parallel - 125 employees 5. exa - 180 employees ramp also scores well despite their denominator being 2000616417.3K- Browser UseRT @rsalakhu: Exciting collaboration with the @browser_use team on Odysseys2, the next generation of our long-horizon web navigation benchmark: Data + Evals: Developed jointly with Browser Use, Odysseys2 contains 100 challenging tasks grounded in real user requests and executed on the live internet. Unlike the original Odysseys, which drew on user browsing histories, Odysseys2 reflects the distribution of real-world user requests collected by Browser Use, providing a more realistic evaluation of web agents.Browser Use @browser_useIntroducing: Odysseys2 - hardest long horizon benchmark for web agents based on real user tasks 🏗️ We collaborated with @JangLawrenceK @rsalakhu from Carnegie Mellon University > SOTA agent fully completes only 47/100 > 5 agents complete none > 8-12 real rubrics per task, 60 min on the live web Web agents are becoming better than humans at knowledge work.020310
- Berichten @browser_useWe made the judge way stricter > same 2,098 attempts > old Odysseys judge: 88.9 avg > Odysseys2 judge (reads the delivered files): 45.3 Tasks, rubrics, scores and judge prompt are open (MIT)
101594 - Your agent is only as good as its browser. Ours keeps getting better, nonstop. Getting blocked is now optional. Try it now:Aitor Mato @reformedotWhile others get flagged as bots, @browser_use solves all major anti-bots and CAPTCHAs. SOTA on every public stealth benchmark. Fully headless, with in-house captcha solvers. Now I'm only competing against myself. Blocked somewhere? DMs are open. Blog post soon. 🤓31303K
While others get flagged as bots, @browser_use solves all major anti-bots and CAPTCHAs. SOTA on every public stealth benchmark. Fully headless, with in-house captcha solvers. Now I'm only competing against myself. Blocked somewhere? DMs are open. Blog post soon. 🤓
12255.8K- GPT-6.1 Terra is insanely good at browser use 🔥 > 78.5 on the Browser Use Benchmark > basically Sol performance (79.7) at 35% less cost. Pareto frontier is once again dominated by OpenAI.
322233216.6K - BUT the inference is slooow, cmon @Kimi_Moonshot open source it already
Browser Use @browser_useKimi K3.1 Pro is a beast at browser use 🤯 76.8 on the Browser Use Benchmark. Only GPT-6.1 Sol scores higher. It beats Opus 5.5, Grok 4.7 and Sonnet 5.5, and it's cheaper than Opus at ~$2/task. Best Chinese model we've ever tested, by a lot. Next best is DeepSeek V4.1 Flash at 70.6. Moonshot cooked.10302.7K - Kimi K3.1 Pro is a beast at browser use 🤯 76.8 on the Browser Use Benchmark. Only GPT-6.1 Sol scores higher. It beats Opus 5.5, Grok 4.7 and Sonnet 5.5, and it's cheaper than Opus at ~$2/task. Best Chinese model we've ever tested, by a lot. Next best is DeepSeek V4.1 Flash at 70.6. Moonshot cooked.
12812512.6K - Browser UseRT @humansand: Introducing Boba - the social intelligence that understands your goals and your community. Text Boba today or message it online at0390363
- Boba is so coolhumans& @humansandIntroducing Boba - the social intelligence that understands your goals and your community. Text Boba today or message it online at02253.8K
- Browser Use Cloud can now sign in autonomously with native 1password integration 👀 > approve the login once > 1password handles the rest Sekurity!1Password @1PasswordToday we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉 We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly. 1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials. The agent gets the task done, but it doesn’t get your passwords.. You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault. ➡️Learn more:61413714.1K
- I trust this guyPeter Steinberger 🦞 @steipete30595.6K
Today we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉 We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly. 1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials. The agent gets the task done, but it doesn’t get your passwords.. You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault. ➡️Learn more:6451.1K10.6K1.8M
- Introducing rl-env-use: RL environments for anyone, in any domain. Describe a skill in one line. Get a verified environment built from real cases, ready for hillclimbing. 100% open source 🔥303552855.8K
- Browser UseRT @gregpr07: If your agents never want to see this again, switch to browser use cloud
020282 - Berichten @browser_useTrial results sit behind tabs and search forms that a plain fetch never reaches. Vanilla Claude Code (WebSearch + WebFetch) verified 0 result facts, meanwhile our Browser Use agents managed to find and verify 17 end-to-end that were used to build robust environments.1083.2K
- Browser UseRT @reformedot: Some anti-bot systems have started labeling certain browser providers as "instinct" bots 🤖 Be careful which browser your AI agents run on. Your accounts might be at risk 👹010386
- Berichten @browser_useBuilt on Anthropic's "Automating eval design and hillclimbing", extended with real cases mined from the web instead of synthetic ones. Set it up for your own data:14323.1K
- Meer berichten tonen
