Jeremy Eder 🤘
@jeremyeder
Followers
2K
Following
733
Media
664
Statuses
4K
Distinguished Engineer at Red Hat. Past: SaaS/SRE, Performance/Scale, Hardware Accelerators, R&D.
North Carolina
Joined May 2009
Hey, I love social media haha! Here's the next blog: https://t.co/LgQVDQ181Y I have one coming later this week that covers AgentReady in more detail. Teaser -- I added an "align" subcommand that does the things.
ambient-code.ai
AI.engineer was exceptional. We should crowd-source somehow keeping it the way it is. Larger conferences typically operate at a higher altitude and there is a useful niche for smaller technical...
"Your codebase isn't broken — it just wasn't built for AI." Your Codebase Is Probably Fighting Claude https://t.co/1C3cuf3wDb
0
2
5
Totally agree. Will there be a rebound though? You still have to maintain focus on your core competencies in business and engineering. "Your scientists were so preoccupied with whether or not they could, they didn't stop to think if they should"
This is happening mad fast! I started to realize this when moving all my workflows to Claude Code Skills. Painful at first, but then suddenly moving at speeds never imaginable. I hear more companies embracing skills, which accelerate things more. Good read!
0
0
0
GenAI #wrapped: the most valuable feature shipped in 2025 was a pep talk. Happy Holidays, everybody. 🪩
Testing a new course-correction feature in @AmpCode Loving it so far. Catches a bunch of annoying cases where Opus 4.5 should've seen/done something. Way to go @nicolaygerold 👏
0
0
0
i dont want an AI generated comparison of CLI coding tools. just tell me which hill you'll die on
1
0
0
I mean reinforcing loops are the crux of many professions and systems. The secret is over here:
systemdynamics.org
Business Dynamics: Systems Thinking and Modeling for a Complex World explains what System dynamics is, and how it can be successfully applied to solve business and organizational problems. System...
we published a definitive overview of compound engineering in @every today. co-written by @kieranklaassen and me. if you want to know how we build software at Every this is the essay for you: https://t.co/W8iXElrGij
0
0
0
I've been waiting to see what Will thinks. Thank you so much for writing it. A commiseration of sorts: https://t.co/E19lvj6tVg
ambient-code.ai
Will Larson published a post last week on facilitating AI adoption at Imprint. It’s one of the most practical things I’ve read on the topic. It’s that way because it speaks from hands-on experience....
0
0
0
this is how you get black holes
Has anyone tried Claude Agent SDK in a container pretending to be a server and replying to requests with html
0
0
0
Who is the most creatively unhinged @cursor_ai user you know of? I will pay them for a masterclass in their chaos. 🧙
0
0
0
Getting ready to learn about the latest release of @ceph 20.2, "Tentacle". Actually though, I find hyperbole to be a sharp tool in the free-thinkers toolbelt. What's most important for 2026? It could be your org's resilience and psychological safety. 🧠 https://t.co/d6hPI5YTsi
0
0
0
The whole thing is Apache-2.0. The whole thing. With complete data lineage. It's free. Why would anyone do this, @neurobongo ? 💪
research.ibm.com
The Stanford University Foundation Model Transparency Index has ranked IBM Granite number one this year — with the highest score in the history of the index.
Red Hat CEO @MattHicksJ says open sourcing model weights is just the start: "Openness should begin with model weights, but be further supported by an open ecosystem of tools and platforms that prevent vendor lock-in." Read his argument for genuine open source AI via @Forbes:
1
0
1
OpenAI is co-founding the Agentic AI Foundation (AAIF) under the Linux Foundation alongside Anthropic and Block to support open, interoperable standards for agentic AI. We’re also donating AGENTS .md to help establish open standards that enable safe, reliable agents across
openai.com
AAIF aims to advance open-source agentic AI with the donation of standards including OpenAI’s AGENTS.md
218
560
4K
https://t.co/qcMNwIBX9Y was exceptional. We should crowd-source somehow keeping it the way it is. Larger conferences typically operate at a higher altitude and there is a useful niche for smaller technical events. Reflections on hallway buzz topics: https://t.co/LgQVDQ1FRw
ambient-code.ai
AI.engineer was exceptional. We should crowd-source somehow keeping it the way it is. Larger conferences typically operate at a higher altitude and there is a useful niche for smaller technical...
0
0
0
. @dexhorthy something like this right https://t.co/Bmy7Tb5YkX ?
ambient-code.ai
// breakthrough software engineering concepts Agentic Software Engineering Platform
0
0
0
What is your opinion on this path?
ambient-code.ai
Hey folks, I’ve been spending a lot of time thinking about how we write software. Actually, this was spurred on by a recent project: I thought, how can I drive inference workloads to llm-d? How can I...
@leantoolboxorg The latter. We should be able to expect *much* better software now.
0
0
0
The system is constantly regenerating itself. That's what ambient means. 🚀
0
0
0
Envision future software and hardware systems as a beehive of activity. Agents replacing autoscalers, replacing algorithms in order to constantly regenerate in every direction…north, south, east, west…coordinating things with each other, being as proactive as safely possible.
1
0
0
In companies trending towards AI-first development, existing staff will transition from meticulously crafting code to becoming “shepherds” of codebases, focusing on establishing guidelines and policies that optimize project goals and wielding entire development teams themselves.
1
0
0
The Path to Vibe Coding for the Enterprise: TDD + Application Specs + CodeGen LLMs + Code Shepherds + Caching = Enterprise-Ready Ambient Code https://t.co/TFkFzdovPF
https://t.co/Bmy7Tb5YkX
https://t.co/C734gs4hMT
github.com
Breakthrough Software Engineering Concepts. ambient-code has 6 repositories available. Follow their code on GitHub.
1
0
0
.@_llm_d_ is a Kubernetes-native distributed LLM inference framework designed for fast, scalable serving across hardware accelerators with strong performance per dollar. Learn how it works (and see a live demo) at this week’s @vllm_project office hours. Join details below 👇
2
5
33