Aquileo | Stacklok (@StackLokHQ) / X

Stacklok

404 posts

Stacklok

@StackLokHQ

Makers of open source and free-to-use tools for AI-curious developers. Find our most recent project here: toolhive.dev

Remote and asynchronous

Joined April 2023

Stacklok
@StackLokHQ
Mar 28, 2025
"AI's effects on programming jobs; doom and utopia are not our only options." hubs.la/Q03dmSPW0
Stacklok
@StackLokHQ
Mar 27, 2025
Will / should this also include code?
China will enforce clear flagging of all AI generated content starting from September
From tomshardware.com
Stacklok
@StackLokHQ
Mar 26, 2025
MCP: The Ultimate API Consumer (Not the API Killer)
layered.dev
MCP: The Ultimate API Consumer (Not the API Killer) | Layered System
APIs are the connective tissue of our digital world. Now there's a new protocol reshaping the landscape: Model Context Protocol (MCP). Let's debunk the misconception that MCP will kill APIs.
Stacklok
@StackLokHQ
Mar 25, 2025
Three types of AI missteps during agentic coding and how to safeguard against them; thoughts from @birgitta410.
martinfowler.com
Exploring Generative AI
Notes from my Thoughtworks colleagues on AI-assisted software delivery
Stacklok
@StackLokHQ
Mar 24, 2025
Emergent misalignment is strongest in GPT-4o and Qwen2.5-Coder-32B-Instruct, but all fine-tuned models exhibit inconsistent behavior
arxiv.org
Emergent Misalignment: Narrow finetuning can produce broadly...
We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts...