Chillieman

I did the thing

@RocketGPT Bro Caleb Hammer is so entertaining

a bunch of the people that told me the covid vaccine would kill is all are now injecting random Chinese peptides they find online.

@AlexFinn Have you tried the /compact command?

This is a fix for a very specific problem: Running a ton of cron jobs bloats context If you don't run a lot of cron jobs this won't be an issue for you

IF YOU'RE ON OPENCLAW DO THIS NOW: I just sped up my OpenClaw by 95% with a single prompt Over the past week my claw has been unbelievably slow. Turns out the output of EVERY cron job gets loaded into context Months of cron outputs sent with every message Do this prompt now: "Check how many session files are in ~/.openclaw/agents/main/sessions/ and how big sessions.json is. If there are thousands of old cron session files bloating it, delete all the old .jsonl files except the main session, then rebuild sessions.json to only reference sessions that still exist on disk." This will delete all the session data around your cron outputs. If you do a ton of cron jobs, this is a tremendous amount of bloat that does not need to be loaded into context and is MAJORLY slowing down your Openclaw If you for some reason want to keep some of this cron session data in memory, then don't have your openclaw delete ALL of them. But for me, I have all the outputs automatically save to a Convex database anyway, so there was no reason to keep it all in context. Instantly sped up my OpenClaw from unusable to lightning quick

@OfficialLoganK Please, for the love of God, increase the rate limits for Tier 1 (Gemini 3.1 Pro) The worst hit to productivity is a poorly timed 429

We just shipped a bunch of stuff to make it easier to scale with the Gemini API: - Automatic tier upgrades - Tier 1 -> Tier 2 now happens much faster (30 days post payment -> 3 days) and with less spend ($250 -> $100) - New billing account caps on each tier to limit over spend

@gvenviber @HarshithLucky3 Yes my OpenClaw only uses the `gemini-3.1-pro-preview-customtools` model. It's wildly efficient for me. It only ever becomes inefficient when it hands off work to a lesser model (such as a flash) But when 3.1 has the wheel - guaranteed success (with some steering ofc)

@Chillieman1 @HarshithLucky3 You mean 3.1 pro connected to openclaw for coding? If that's true, I think Google is messing up Antigravity big time!

Google AI Pro Users Rate limits for Gemini CLI are much better than Antigravity For a Pro user you get 1500 req/day. This means you can send 200 - 250 reqs to Gemini 3.1 Pro, and then it falls back to Gemini 3 Flash This still gives you way more than Antigravity Drawbacks: - You cannot access Claude models - Few times it shows high demand for Gemini 3.1 Pro

@gvenviber @HarshithLucky3 It's heading my OpenClaw VPS and it does extremely well

@HarshithLucky3 Is Gemini 3.1 pro, good at coding, most of the times it ends up messing up with my existing code,

but its warming up

The Forge is not hot

where is grok build?

Call me crazy: I review pretty much every line of code my AI writes

@RocketGPT Lol just don't forget to sleep

@Chillieman1 yup back to the drawing board

oh dear god it’s done

@RocketGPT Never a true failure if you learned how to do it better / different next time! It's really only a failure if it makes u give up

@Chillieman1 and it was a failure! lost too much of the original model with the fine tuning

@WhiteHouse Peter Griffin spotted

UNDEFEATED.

@RocketGPT That was me dammit! 😂 Just wasn't me on the very first one tho :p Or if that's just your way of calling me an NPC ...

@Chillieman1 silence clanker!

i don’t mind ai art, or ai code. what drives me completely insane ai text. EVERYONE CAN TELL YOU WERE TO LAZY/DUMB TO THINK OF AN ACTUAL RESPONSE.

@RocketGPT The irony is truly thick 😂😂😂 I always get a kick out of that OpenClaw dude getting upset when his own framework is responsible for a new wave of AI replies / PRs He calls PRs made by his own community AI slop - yet admits he widely doesn't even review his own AI code 🥴

@Chillieman1 to be fair i’m actively developing an automated communication platform 😬

@RocketGPT 🫶

@Chillieman1 mhmmmmm

@RocketGPT Who me? Doing the thing that makes you completely insane? Never!

@Chillieman1 i’m pro automating thinking. anti automating communication.

Claude Code is pretty legit I helped my buddy get set up and he's making something - not a coder, just a man with a dream ✨