Mark Statkus

@CyberMikeOG Rebuild title if you can over look that.

Pretty awesome deal-2016 Tesla Model X 90D in Black for $17,900 * Free Supercharging * White Interior * Autopilot 1 * Falcon Wing Doors * Dual Motor AWD 124,000 miles.

@CyberMikeOG Can't go wrong with it. Rented a older one in SF, and it wasn't even a 90D. Even with the slower charging rate its still solid around town.

@cybercussion Can’t help it. I want this. 😂

@Jones1 Endless summer nights w/o a CT.

4-6 weeks for PCS Charging. I’m told.

@antigravity Are features still features if they are just a prompt someone else did?

We’ve built a new way to ship software: Agent Teams in Antigravity. Just run /teamwork-preview to spin up a dynamic team of specialized subagents. They coordinate in the background to plan, build, and verify complex engineering tasks in parallel.

@DanielGlejzner Everyone was just prompting us along 🤣

@cybercussion Are you coming from the future :D ?

Software hiring has become absurd. At work, you’re expected to use AI to offload manual coding and move faster. Then, to get your next contract, you’re asked to code from memory with no assistance. Pass the interview - and you’re expected to use AI again. It has never been this broken.

@farzyness Good implementor/reviewer, but not quite there yet.

Grok is the Flow LLM. Grok 4.5’s biggest advantage is its speed. It’s smart enough to be comparable to the other models on most things. But that speed allows you to make little tweaks to your system so that the output is PERFECT. With the other models, it takes FOREVER to do this, and you constantly end up outside of a flow state, which makes it way way way harder to do this. It’s now my preferred model.

@trikcode I actually interview the new model, wirk the intent. Then let Fable code review. Grok was flagged as a implementor not allowed to release. We had a deep dive on what % the model, prompt, skill and plug-ins have on outcomes.

Got rate limited mid-task yesterday and had to switch from Fable to GPT-5.6 Terra. 6 hours of back-and-forth context entirely gone.Lost 90 minutes just getting a different model up to speed on the project goals. Hitting a usage cap at the worst possible moment sucks. We desperately need a universal way to share context across different models.

@AndyZeGerman I saw the inches adjustment and figured I'd win the "you need a new side mirror" lottery. Or a new garage door 🤣

@cybercussion I can't get it to work at all for my garage.

Since you received Actual Smart Summon for Cybertruck, how often have you used it?

@kchau The compression is wild. Then building out more to go even faster. Feel like our chat history is "interventions" for training thr next model 🤣

I don’t know what changed in the last few days but I feel like something in my brain unlocked with AI usage. I’ve accomplished more in one weekend with AI than I have ever before with or without AI.

@Pickenheim @wholemars Correct. We can out-class all this with a prompt at this point. I don't think the ecosystem keeps the same shape.

@wholemars Siri still doesn’t work unless it started working and I didn’t care because it was never working all these f’ing years and my kids would just tell Siri it was stupid, and Alexa, to their “face”

OpenAI is trying to steal Siri trade secrets from Apple

@RoundtableSpace ... right.

Gemini 3.5 Pro benchmark leak just dropped and the numbers are turning heads. > Reportedly outperforming Claude Fable 5 and GPT-5.6 in internal evals > Significant zero-shot performance improvements over 3.1 Pro > Currently in private validation and testing - Public rollout preparations appear to be underway - July 17 is the targeted launch date If the leaked numbers hold, this isn't Google catching up ,it's taking the lead. Fable 5 just became the model to beat. Gemini 3.5 Pro might already have beaten it.

@CyberMikeOG These things are a weapon -- ask my toe.

Had this for a week. Just getting around to opening it. Who uses a physical card anymore? I’m Apple Pay 99% of the time.

@mikepat711 Right, opus isn't horrible, but what's stopping us from creating better orchestration? I've watched Fable blow tine on trivial stuff. Then looped back to squash reliving reasoning. Then cycles of "lets not relive this" and assemble playbooks.

I've seen enough. If Anthropic really does remove Fable on the 12th, I have no real reason to pay for a max sub anymore. Grok 4.5 is a better value than Opus 4.8. I've run it through all of my routine work and it handles it all fine. and faster.

@Jones1 I feel like we need multilayer ppf that lets you take a layer off when its not worth trying to wash the bugs off 😅

Anyone tried this for their off road light bar? PPF Shield for Tesla Cybertruck OEM off-road light bar, Cyberbeast – TWRAPS twraps.com/products/ppf-s…

@scottbuscemi Trained for this.

I want to do this cleaning myself but I’m afraid of breaking a clip and not having backups.

@nowteslafy What is up woth the random nature of this. Yours is a late 2024?

So my Cybertruck isn’t charging at the full rate of 32 amps I have at home- it’s at 24 and I can’t increase it. Thoughts?

@kchau Guess in a cab with 2 people thats that going to go the way it does when I have 4 people in the car talking at the same time 🤣

@cybercussion That’s just the navigation tool though. It’s just stuff we can do normally through the screen, but through grok They’re talking about telling FSD exactly where and how to park. Stuff we can’t do currently.

They really are doing some sort of Self Driving MCP for Grok.