Chaz

Founder,

[Chaz @chaz]

watching f1 race & checking out twttr

[Chaz @chaz]

@jessethanley @PlanetScale @0x15f `pscale` CLI is excellent, too. I set up a weekly Codex automation to look for slow queries and evaluate @PlanetScale schema recommendations

[Chaz @chaz]

@lorenzolasagn Truly all expenses paid? A, for the hotels + Michelin stars

[Chaz @chaz]

@hnshah Happy little Claudes

[Chaz @chaz]

Claude: the dreamer
Codex: the realist

They work so well together

[Ian Landsman @IanLandsman]

If you’re a bootstrapped startup Cloudflare will give you $10k in credits https://t.co/MkXdNnd7sa

[Chaz @chaz]

@gdb Lots of tabs

[Chaz @chaz]

I set up @OpenAI Symphony last week, and have used it to close dozens of issues.

It's not perfect. The one, perfect workflow for everything doesn't exist. Symphony is worth setting up as-is for high-confidence, low-blast radius issues.

Tip: have it attach screenshots.

[Chaz @chaz]

Turns out, @steipete will solve his own problems https://t.co/wSlp8rJi6L

[Peter Steinberger 🦞 @steipete]

This is the most useful tooling I built for OpenClaw to date. It's open source, runs on codex and you can fork and use it for any repo.

For all the hard working oss folks that drown in issues and PRs, this is for you.

[Chaz @chaz]

OpenClaw has problems today that other projects and companies don't have, but will tomorrow when agents go 100x. Startups in this space should take notice.

[Peter Steinberger 🦞 @steipete]

PRs on OpenClaw are growing at an *impossible* rate.
Worked all day yesterday and got like 600 commits in.
It was 2700; now it's over 3100.

I need AI that scans every PR and Issue and de-dupes.
It should also detect which PR is the based based on various signals (so really also a deep review is needed)

Ideally it should also have a vision document to mark/reject PRs that stray too far. This can't be fully automated, but even assisting would help.

The closes I found is an obscure oss project.
How's no startup working on this?

[Chaz @chaz]

Wirecutter for local models

[0xSero @0xSero]

Best models to run on your hardware:

—— 64 GB ——

- Qwen3-coder-next-80B-4bit (coding, Claude code, general agent)
- Qwen3.5-122B-reap: (browser use, multimodal, tool calling, general agent)

—— 96 GB ——

- GLM-4.6V (multimodal and tool calls)
- Hermes-70B (Jailbroken)
- Nemotron-120B-Super: (openclaw)
- Mistral-4-Small (general agent)

—— 192 GB ——

All these are excellent top tier LLMs and approach sonnet in capabilities

- Step-3.5-Flash
- Qwen3.5-397B-REAP
- MiniMax-M2.5 (soon M2.7)
- GLM-4.7-Reap

[Chaz @chaz]

@IanLandsman It's for the content right

[Chaz @chaz]

@arvidkahl Have you seen OpenAI ExecPlans? It's great for anything that is medium size or larger: prevents memory rot across compaction, but also tracks observations, surprises, and decisions. I commit it with the PR so that future agents can read the "why."

https://t.co/ZX01IEqLyN

[Chaz @chaz]

@IanLandsman Right. Leaves it to one of the agents to have to find potential risks during PR merge. Tests may catch but depends.

[Chaz @chaz]

@arvidkahl What would you say the median response time is? A couple of hours?

[Chaz @chaz]

@wesbos Japan made it illegal https://t.co/cS0mSIyPOx

[⛩ Ryo Saeba | Japon XYZ ⛩ @Ryo_Saeba_3]

Au Japon, les images utilisées sur les emballages alimentaires sont strictement encadrées par la loi : elles ne doivent en aucun cas induire le consommateur en erreur.
C'est pour ça que souvent les produits ont la même taille que sur l'emballage #Japon

[Chaz @chaz]

@i_am_brennan @ryancarson I've been using OpenAI's ExecPlans for months and they've been great, esp large, multi-release staged projects. Also valuable to commit them with the project so future agents can read about it.

[Chaz @chaz]

@ashleymayer I was thinking the same. ChatGPT gets the headline, but he's clearly willing to run through walls. ChatGPT only helped him find which walls. Lucky dog!

[Chaz @chaz]

I’ve been using OpenAI’s ExecPlans for 6 months, and it still works better than any planning mode.

https://t.co/nL89PEwJFy

[Chaz @chaz]

@Shpigford @openclaw @clairevo and @jessegenet know the way https://t.co/h0JOAKvfk0