DevRel As Service

Let's talk DevRel 🥑

[DevRel As Service @devrelasservice]

https://t.co/KCNZLjfn7m

[elvis @omarsar0]

If you use LLM-as-judge, this one is worth reading.

(bookmark it)

It's actually one of the most effective ways to use LLM-as-a-Judge for evals.

Holistic judge scores hide both their reasoning and their ceiling effects.

BINEVAL decomposes each evaluation criterion into atomic yes-or-no questions, answers each independently per output, then aggregates the verdicts into calibrated multi-dimensional scores.

Every question-level verdict is inspectable, so you can diagnose exactly why an output scored low, and the same verdicts feed straight back as targeted prompt-improvement signal.

Across SummEval, Topical-Chat, and QAGS, it matches or beats UniEval and G-Eval, training-free, with especially strong results on factual consistency.

Paper: https://t.co/oar6BZcasm

Learn to build effective AI agents in our academy: https://t.co/1e8RZKs4uX

[Pratham @Prathkum]

Everyone is chasing self-improving models.

The bigger opportunity is self-improving products. Your users generate the best learning signal every single day.

I think that's where the real competitive advantage will come from.

[Ahmad @TheAhmadOsman]

Wanna replace Anthropic/OpenAI? START WITH THIS

The bible for running LLMs locally is now available online to read for free

Covers what to use on

- Laptop / edge / odd hardware
- Mac-first workflows
- Single RTX GPUs
- 2-4+ NVIDIA / CUDA GPUs
- General production serving
- Long-context / MoE / routing
- NVIDIA max performance
- Cluster orchestration

Software

- llama.cpp
- MLX / MLX-LM
- ExLlamaV2
- ExLlamaV3
- vLLM
- SGLang
- TensorRT-LLM
- NVIDIA Dynamo

You should read this, and if you cannot now then you most definitely wanna bookmark it for later

Opensource & Local AI FTW

[Shubham Saboo @Saboo_Shubham_]

UI/UX for building org-level Agent Harness.

Bring your model, own the runtime, and wire it with your tools.

100% Opensource.

[GREG ISENBERG @gregisenberg]

A friend asked me how to actually build a company that runs on AI agents.

I drew him 4 simple diagrams and this is what I told him:

For this to work, a few things have to be true.

- The humans move up to strategy, taste, and judgment while agents handle the execution.

- The whole business becomes readable to agents. Your data, SOPs, pricing, permissions, and decisions all live in one shared context layer.

- And you point it at the right work. Repetitive enough for an agent, complex enough that the incumbents never bothered. That's the goldmine.

In the old world, the company was the people. They held the knowledge, made the calls, did the work.

In this new world, the people become the creatives, the agents become the labor, and the company itself becomes the context layer.

That shared brain is the actual company now. The humans and the agents are just plugging into it.

Which means the most valuable thing you can build in 2026 is a business so well-documented that an agent can run it.

I see it everyday with @MeetLCA. I don't talk about it much publicly, but we've built a SWAT team for building AI-native orgs and AI-native products.

The moat is how legible your company is.

I drew it all out below.

[@levelsio @levelsio]

✨ I think I've been coding almost solely on my VPS with Claude Code for almost a year now

All I can say it's just fantastic:
- no need to keep laptop open ever
- no laptop battery drain
- can switch to phone or any other device you like whenever you want to continue (like when you're outside)
- it just keeps going all night while you sleep (esp with /goal)
- you can start hacky projects from scratch and go live in seconds because you're already on the server which is great to ship things and get it used by people fast (not stuck on your local laptop webserver)
- it just feels like living in the future

I used to code on my laptop, test locally, then push to GitHub, then it auto pulled and deploy to production, that'd take me ~1 minute to get a new feature out

But then when I bought a new Mac Book Pro a few years ago I was too lazy to install a local Nginx environment, so I just started pushing to prod and everything went fine, and I sped up deploying to about 3 seconds from laptop to server, which people called me crazy for too

But now with Claude Code on my VPS in the last year, it just live edits on my production server, which sounds like it should go wrong but it just doesn't, it's very careful and only twice in 12 months messed up which meant my site didn't load for 10 seconds which is OK

If I wasn't working solo, like at a big company, I' think I'd recommend the same workflow but with a staging server, so it wouldn't touch production, for safety and regulatory reasons etc. but for me it's fine

I agree with @theo completely, it's clear to me this is where it's going, also seeing @karpathy with Claude moving to the cloud (via Slack etc), I think AI "agents" and AI coding will operate on servers / from the cloud first

P.S. I have 3-2-1 backups, multiple on-site and off-site backups which you should also even if you wouldn't code with AI, safety first!

[Rohan Paul @rohanpaul_ai]

A Japanese dev spotted the trick: ask Claude Code to automatically Find Skills.
Can match your goal to the right tool, using Vercel’s skills CLI across Claude, Codex, Cursor, and Gemini.
so install skill like dev tools rather than rewritten by hand

[Iseunife The First @Shawnife]

Put together a list of things you can automate using Claude Code.

With this, you can create the ultimate system. ↓

[Akshay 🚀 @akshay_pachaar]

Andrej Karpathy:

"Remove yourself as the bottleneck. Maximize your leverage. Put in very few tokens, and a huge amount of stuff happens on your behalf."

loop engineering is the exact thing that gets you there.

in a hand-run session you do two things. you decide what the agent runs next, and you check its output before the next step. both are manual, and both are the ceiling on how far the agent gets without you.

loop engineering moves both steps into the system. the diagram below shows the operating structure that surrounds the loop:

→ a trigger decides what to run, whether that's a message, an event, or a schedule, so the agent starts without you there to kick it off.

→ the loop is the maker that produces the work, thinking, acting, and observing until it's done or the brakes stop it.

→ a separate checker grades the output, because a model grading its own work justifies what it already did instead of catching where it failed. the checker's findings return to the maker as the next instruction, and the cycle repeats until nothing is left to fix.

→ state lives on disk, not in context, since the model forgets everything between runs. an MD file or a knowledge graph holds what's done and what's still open, so a loop can pick up again days later.

for that state layer, Zep's Graphiti is a clean open-source option, a temporal knowledge graph that invalidates stale facts and returns context through vector, full-text, and graph search in one call.

repo: https://t.co/8CboBlWffX

two things decide whether an unattended loop holds up.

the exit has to be set before the loop runs, not while it's running. a loop with no stop condition burns tokens, and the cost climbs fast once sub-agents and long runs stack up. a clean exit reads like "all tests pass and lint is clean, stop after two passes."

and the checker only catches failures inside a run. the harness around the loop, the prompts, tools, and checks wrapped around the model, still drifts and breaks in production as models change. catching that needs observability on every run, not a green checkmark.

Comet's Opik is built for that layer, an open-source tool that traces every call and turns a failing production trace into a regression test so the same break can't recur.

repo: https://t.co/Qxk9BHZBlx

your job stops being the hands inside the loop. it becomes designing the machine that runs without you, then watching the traces closely enough to trust it.

the model is becoming a commodity. the loop around it is where the real engineering lives now.

I wrote the full breakdown. the article is quoted below.

stay tuned for more on this!

[Matt Pocock @mattpocockuk]

New in-progress skill: /loop-me

Interviews you about your work and finds opportunities for delegating your day-to-day work to AI

[DevRel As Service @devrelasservice]

@hasantoxr Why not just use the best open-source.
https://t.co/N1ZeAmYLEM

[DevRel As Service @devrelasservice]

As an AI Engineer. Please learn:

> Maths
> NLP
> ML
> DL
> Computer Vision
> Harness
> Agents

https://t.co/ND3cFtfn5N

[DevRel As Service @devrelasservice]

@TheAhmadOsman https://t.co/ND3cFtfn5N covers everything from this + it's open source.

[DevRel As Service @devrelasservice]

One-line takeaway:
The biggest startups are built not by exploiting people, but by deeply understanding users, solving problems they truly care about, and growing through products people genuinely love.

[Paul Graham @paulg]

How to Earn a Billion Dollars: https://t.co/WeWBUkKym6

[DevRel As Service @devrelasservice]

@shannholmberg Replace gbrain with agentmemory and you get context and brain across every agents.
https://t.co/N1ZeAmYLEM

[DevRel As Service @devrelasservice]

@davidNbreslauer @garrytan https://t.co/N1ZeAmYLEM works with all agents and was around before gbrain existed.

[DevRel As Service @devrelasservice]

@sairahul1 This is more detailed: https://t.co/ND3cFtfn5N

[DevRel As Service @devrelasservice]

@steipete Yeah! Creating workflows, scripts, loops on the fly.

[DevRel As Service @devrelasservice]

How do you use Claude Code, Codex, Hermes, Openclaw, or any similar agents? What do you use to perform it better? What are the patterns?

What is the execution layer?

[DevRel As Service @devrelasservice]

@divaagurlxw https://t.co/ND3cFtfn5N