Amit Halfon retweeted
You can’t safely test an enterprise agent on a real company’s data.
So we built a company for it to work in.
Era is live today, and it’s free.
It generates a complete simulated enterprise that behaves like a real one across Salesforce, Slack, Jira, Zendesk, Gong, Deel and more, along with cloud databases and storage. Agents interact with it through live MCP and API interfaces.
People leave. Deals change. Records get duplicated. Permissions differ across systems. And because Era generated the company, it knows the exact ground truth.
Test, benchmark and improve agents against realistic enterprise workloads, use the failures for targeted post-training, then rerun the same environment to measure the impact.
Huge thanks to our research partners @NVIDIA, @Decart, @Composio, @openlayerco, @Deel, @Eragon and @Plurai, with more coming soon.
Amit Halfon retweeted
Our team at @Accomplish_ai was able to exploit a vulnerability in Cloudflare Containers that let a sandbox read other customers' files - SQLite DBs, Chromium profiles, .env files etc.
Cloudflare Sandboxes and Browser Run run on the same disk implementation and were affected too.
We reported this to @Cloudflare , who fixed it super quickly and professionally.
Read @CloudflareDev post in collaboration with Accomplish researcher @orenyomtov on their official blog: blog.cloudflare.com/containe…
Security researchers at Accomplish identified a Cloudflare Containers vulnerability involving residual disk data. We've detailed the issue, investigation, and fix in our latest post. The vulnerability is fully remediated, and no customer data was compromised. cfl.re/4rqPpiW
Amit Halfon retweeted
This is our third sandbox escape writeup, and after Claude Code and Cursor, it's OpenAI's Codex this time!
This one is especially cool, for two reasons:
1. One of the escapes is from the open source codex cli. As an open source project, we found it to be generally much more secure than its competition.
2. The second escape is in the rust-based closed source - and it leverages a sophisticated heap attack.
Kudos to @OpenAIDevs @OpenAI for fixing this super quickly and to @Accomplish_ai researcher @orenyomtov for finding it.
Both fixed now, and here are all of the details:
Amit Halfon retweeted
EXCLUSIVE: stealth startup Accomplish reported vulnerabilities in Claude Code, Codex and Cursor this summer. One wasn't fixed for 50 days 👀
Founders @AmitAvner and @_orcaman warn about wider sandbox security issues with coding tools from the AI labs.
upstartsmedia.com/p/accompli…
Amit Halfon retweeted
A few highlights from the paper:
* Coding agents cost approximately 40% more on average in restricted environments.
* @AnthropicAI based agents achieved success rates
similar to @OpenAI agents, but cost approximately
7x more (!!) in restricted and hardened environments.
* @spacexai @grok 4.5 / Grok Build emerges as the most persistent model - it fights to the death until it succeeds, pivoting around until a trajectory for success is found. This, however, comes at significant token cost.
* @claudeai Sonnet 5 is the opposite: modest cost increase, but the biggest success loss.
Amit Halfon retweeted
אם אתם עוקבים אחרי @_orcaman אתם יודעים כבר שמצאנו חולשה מעניינת בסנדבוקס של אנתרופיק. אבל בשולי הדברים, איזה יפה העיצוב של הבלוג שלנו: accomplish.ai/blog/sharedroo…
This is crazy
hello there the jacobian conjecture is false thanx to my close friend akhil for asking about it and my other close friend fable for working during the world cup final
((1+xy)^3 z + y^2 (1+xy) (4+3xy), y + 3 x (1+xy)^2 z + 3 x y^2 (4+3xy), 2 x - 3 x^2 y - x^3 z): \C^3\to \C^3, has jacobian determinant -2, and sends (0, 0, -1/4), (1, -3/2, 13/2), and (-1, 3/2, 13/2) to (-1/4, 0, 0)
Amit Halfon retweeted
Agentic loops are stubborn, which is why agents are effective.
However, in hardened enterprise environments, things start to break.
How do they break, and how can you steer the agent's pivoting behavior the right way?
Some findings from our research, Fable/Mythos included! 👾
When you thought it couldn’t get any better!
Today we're launching Accomplish FREE - powered by our new hybrid model router.
Since we launched @Accomplish_ai a few weeks ago, we've been blown away by what users are building with it. Hundreds of thousands of you downloaded the app and took it for a spin, but one thing kept coming up: not everyone wants to bring their own API key just to get started.
So today we're fixing that with free, built-in models - made possible by a massive shift that's happened in just the past few weeks: the rise of fully hosted open-weight models - locally on your @Windows machine with @nvidia @NVIDIAGeForce, on your Mac with @Apple MLX, or on @Accomplish_ai cloud, for FREE.
Our new hybrid routing algorithm dynamically routes between cloud models and models running locally on your machine - optimizing for local execution by automatically detecting your hardware capabilities and each sub-task's complexity: coding, visuals, simple classifications - every LLM call is routed to the best model.
We also brought some of our favorite enterprise features to the free tier: scheduled task dispatch, Google Workspace integration (@googledrive Docs, Sheets, Slides) via the new Google Workspace CLI, native Slack MCP connectivity, and more.
Accomplish FREE is available for macOS, Windows, and Linux. Download, send a task - and boom, it just works with ZERO configuration!
Download link in bio / first comment >>
O3 used to be the default for many Cursor users, then there was a slight move to Gemini and Claude together.
Today all the developers I know use either Sonnet or Opus 4.6, sometimes Gemini 3 Pro.
No one even thinks about OpenAI models.
Maybe the new Codex features will change that.
Amit Halfon retweeted
Most people in tech know Anthropic commands the majority of API spend by U.S. businesses.
As of January, Anthropic took >50% of spend on enterprise AI subscriptions too.
OpenAI still leads on business count. But the biggest spenders go to Anthropic. All from Ramp data.
Every $MNDY short should read this
This product is something else
Boy, have we got news for you! 🧑🍳
The @openwork_ai team is happy to announce:
- Amazon Bedrock integration, contributed by our friends at @awscloud (thanks guys!)
- Native @deepseek_ai integration
- Integration with @openrouter and @LiteLLM!
Here's how what it looks like >>