🇪🇺 in the 🇺🇸 (background picture by Nicolas Raymond: https://xitter.cf/t.co/ULMIqvRPI8)

Washington, DC, USA
Joined June 2007
Guillaume Loret retweeted
Biggest misconceptions bout OpenWork is that we're a desktop app. OpenWork is a way to deploy AI capabilities safely to your team. Whether it's MCPs, AI Models, or skills - admins can configure them all in OpenWork and distribute them across a wide way of surfaces. Different harnesses, slack, simple chat interfaces, or the desktop app are all supported.
2
2
10
766
Guillaume Loret retweeted
HEY! OpenWork is now officially SOC 2 Type II compliant
1
2
2
9
1,340
Guillaume Loret retweeted
In a world where you can do 100 parallel tasks remember that same world allows *anyone* to do the same. It is not ambitious to take on more work if your work is easy. But if anyone can have 100 parallel tasks going on, why aren't there more people getting ahead? The reason is that is in a world where you can move faster, moving faster in the correct direction matters even more. You can compound faster, create more distance between you and everyone else. The important things haven't changed: deciding what to work on, sticking to it, and focusing. Your software factory isn't creating the gap you think it does. The gap you should care about is the gap in market value you captured, not the code you were able to produce. You are not working in isolation, you're competing against the entire world. Someone doing a "software factory" is not a scarce resource. What is scarce is attention and discernment. Intelligence being "on tap" doesn't change that. The truly ambitious don't only take on more work. They take on a particular kind of work in a particular way.
2
1
1
8
2,506
Guillaume Loret retweeted
we made our terrible onboarding, a bit less terrible (jk we think it's great now, but do let us know)
1
1
1
1
426
Guillaume Loret retweeted
We have ZDR at home The ZDR at home:
The only thing that would make me believe openAI did NOT train on their data is if they released the full agent trace. Let people independently verify that there was no contamination / leak.
3
3
398
Guillaume Loret retweeted
Android Bench evaluates LLM coding performance by focusing on the nuances and platform expertise that are unique to Android. See how your favorite model stacks up → goo.gle/4swdpRe Are the results what you expected? 👀 Let us know in the replies!
7
22
4
191
16,986
Open source is facing a double crisis: we’re relying on "zombie" packages with no human maintainers while using flawed metrics that ignore our most critical infrastructure. * nesbitt.io/2026/05/08/weeken… * nesbitt.io/2026/05/09/the-mi…
1
323
Using a hybrid architecture for AI agents: files as the human-readable "interface layer" for context, while leveraging databases as the scalable "storage layer" for long-term recall. thenewstack.io/ai-agent-memo…
123
Contrary to the promise of reduced workloads, new research shows that AI often intensifies work. Because the tech makes "doing more" feel accessible, employees are expanding their job scopes, multitasking more, and blurring the lines between work and downtime.
1
104
Query knowledge graphs without the hassle: GRASP lets you run complex SPARQL queries with simple natural language questions grasp.cs.uni-freiburg.de/
1
83
Tech debt isn't always bad! Like financial debt, it depends on the interest rate. High-interest tech debt can cripple your team, but low-interest tech debt can help you move faster. Check out this great read by Erik Schluntz on managing tech debt effectively.
1
92
LangChain is moving away from Retrieval Augmented Generation (RAG) and towards agentic search. [blog.langchain.com/rebuildin…
256