EvalOps @EvalOpsDev

We make coding agents explain themselves. evalops.dev San Francisco, CA Joined July 2025

Tweets

49
Followers

314
Following

1
Likes

0

EvalOps @EvalOpsDev

a week ago

“red team” sounds cool. “blue team” sounds cool. so you’d think “purple team” would be very cool. alas, it is a Slack thread with 19 unresolved comments.

0 0 1 40 0

View Details

EvalOps @EvalOpsDev

3 weeks ago

Your token spend was a number you could've gated on. Instead it's a number you get to explain.

0 0 1 278 0

View Details

EvalOps @EvalOpsDev

4 weeks ago

everyone's like "how big is your team" brother. it's one agent. it's opening PRs against itself. i haven't written code in four months. leave me alone

0 1 3 384 0

View Details

EvalOps @EvalOpsDev

7 months ago

the best AI coding assistant might be the one that works on a plane

0 0 0 289 0

View Details

EvalOps @EvalOpsDev

8 months ago

Every release is a high‑wire act. Instead of praying for calm winds, build a net. EvalOps ties your policies, metrics and audits into a mesh that lets you scale without falling.

0 0 1 666 0

View Details

EvalOps @EvalOpsDev

8 months ago

We open-sourced Nimbus – Firecracker-based CI for AI workloads. Multi-tenant isolation, RBAC, audit logs.

0 0 1 647 0

View Details

EvalOps is where evaluations meet operations — and security is no exception. “keep” shows how device posture, SSO, and OPA policies can be continuously tested and traced like any other system. Run it, break it, measure it. github.com/evalops/keep

0 0 0 115 0

View Details

EvalOps @EvalOpsDev

8 months ago

Agents are already writing your code. The question isn't "should we use them?" It's "how do we ship them without surprises?" Provenance gives you a ledger. Every line. Every agent. Every risk. Measurable. github.com/evalops/proven…

1 1 1 539 0

View Details

EvalOps @EvalOpsDev

8 months ago

We’re open-sourcing Smith — the Firecracker-based CI runner that powers EvalOps. Why rebuild Blacksmith? Because eval gating needs specialized infra — and we’re not forcing you onto our cloud. Run evals on EvalOps Cloud or your own. github.com/evalops/smith

1 0 1 387 2

View Details

EvalOps @EvalOpsDev

8 months ago

I'm told we're doing awards now?

0 0 0 926 0

View Details

EvalOps @EvalOpsDev

9 months ago

Everyone wants to move fast. @EvalOpsDev makes sure you don’t break trust along the way. Governed AI releases start here.

Jonathan Haas @JonathanHaas

9 months ago

Shipped a new home for @EvalOpsDev. No fluff, just governed AI releases. Check it out -> evalops.dev

2 1 5 442 1

0 0 0 183 0

View Details

EvalOps @EvalOpsDev

9 months ago

🔥 Just dropped an evaluation‑driven LoRA loop built on Tinker from @thinkymachines! It trains, benchmarks & iterates until your model meets the mark. It auto‑spots weaknesses, spawns targeted LoRA jobs & tracks improvements. Proof‑of‑concept repo: github.com/evalops/tinker…

0 1 3 582 0

View Details

EvalOps @EvalOpsDev

9 months ago

Sick of yak-shaving to get a clean Transformers setup? We built a stack that just works: PyTorch + HF Transformers Hydra configs FastAPI serving + Prometheus vLLM, LoRA, flash-attn, bitsandbytes Reproducible. Dockerized. CI/CD baked in. github.com/evalops/stack

0 1 3 405 2

View Details

EvalOps @EvalOpsDev

9 months ago

Developer resumes are frozen in time. GitHub tells the real story. 7k commits, +1.4M lines → now that’s a holographic trading card worth flexing. 🚀 cards.evalops.dev

0 0 1 57 0

View Details

Jonathan Haas @JonathanHaas

9 months ago

LLM vendor: “Just quantization.” Reality: reward-hacked code, broken workflows, lost week. Companies: “nbd.” Users: 🙃🔥 Making this a thing of the past.

0 1 2 425 1

View Details

EvalOps @EvalOpsDev

9 months ago

Interested? DM for early access.

0 0 0 181 0

View Details

EvalOps @EvalOpsDev

9 months ago

This transforms AI codegen from a toy that produces drafts into a partner you can trust to do real work.

1 0 1 197 0

View Details

EvalOps @EvalOpsDev

9 months ago

All of us have been dazzled by large language models’ ability to spit out code, fix bugs, or draft boilerplate. But when you put that code into production, every hidden bug is a potential outage, compliance fine, or security hole. And today’s AI tools leave you guessing.