Sean Ford 🌟🌟

@NVIDIAGeForce @007GameIOI #007FirstLightRTX I could really use this.

Classified intel: prize 003 has entered the field... Up for grabs is this custom @007GameIOI GeForce RTX 5080 Founders Edition + PC copy of the game. Want it? Comment #007FirstLightRTX below

@jumperz Was this tested on the same harness? I've seen that have a huge impact when comparing models as well.

we all saw deepseek cut prices 75% on may 23 and everyone said ai is getting cheap.. then deepswe tested these models on real engineering work and turns out cheap doesn't mean capable. deepseek v4 pro costs $0.87 per million tokens it solves only 8% of the tasks.. when gpt-5.5 costs $30 per million tokens and it solves 70% of most tasks.. Basically, DeepSeek is 34x cheaper but also 9x worse at the actual work. why tho? because making tokens cheaper is an engineering problem better chips, smarter caching, leaner architecture... they solved that.. but being smart across a long task by reading a codebase, planning changes, keeping track of what you're doing across thousands of steps that's a different problem. nobody solved it by making things cheaper. so prices keep falling butcapability keeps pulling ahead and the gap between cheap model and smart model gets wider, not smaller. so the smart play isn't picking one but it's using both.. let the expensive model think and let the cheap model execute.. gpt-5.5 plans the work, breaks it down, makes the hard calls when deepseek runs the repeated parts.. that's where the 34x cheaper actually pays off not as a replacement, but as a multiplier on what the smart model already solved..

@madebygoogle both my wife and my Pixel Watch 2 don't last for more than an hour, rendering them useless. Is there a program to replace the battery? I stopped upgrading because I keep buying stands & chargers and then I have to replace not only the watch, but everything else.

@leojrr Yes please

we want more followers on IG i'm dropping Anything credits to everyone who follows us could be 5k could be 100k reply if you want some

@anything I'm ready!

🚨 JUST IN: we're giving away 20k credits! > vibe code your app > publish to App Store or Play Store > on us reply to get yours

@lydiahallie Definitely useful ... But expensive.

💯 this is why I really like Learning mode in Claude Code I personally use this for all my side projects and it keeps me so much sharper, great if you want to use Claude Code but still stay hands-on! /config → Output style → Learning

@redaxed_ @LLMJunky It's Dual-4k, he's correct.

@LLMJunky 4k is actually only 1/4 an 8k display not half

Best Buy has these Samsung Neo G9 57" Ultrawides Open Box for $878! This is a $2000 monitor. It's great for agents and multitasking. I can fit AT LEAST 8 individual "panels" in a grid at once, but with how I stagger mine, I can comfortably fit 12-16. It's a DUHD (dual 4k) 4K240HZ display, but you will be limited to 120hz most likely on Mac. It is half an 8K display after all. It *might* work at 240hz on any of the Pro, Max, or Ultra lineups. Definitely can hit 240hz on DP2.1 GPUs from NVIDIA or AMD. This is an amazing productivity display. Very happy with mine, and this price. YMMV, depends on local stock. If you see one nearby, it's worth considering. Best Buy has a very liberal no questions asked, no restocking fee return policy (14 days). Link in comments.

@KirkeMannik01 OS

I just built a fully mapped AI Agent OS covering every layer a GTM engineer needs to run a connected agent stack from one project folder. Feed it your ICP, your GTM workflows, and your current tool stack → it maps every skill, agent, memory system, and protocol to the right layer → so you know exactly what to install, what each thing does, and how the layers connect. All inside one free reference document. Perfect for GTM engineers and RevOps leaders who are still installing tools without a system underneath, running agents with no memory between sessions, and rebuilding context from scratch every time they open a new session. If you're running GTM on AI agents in 2026, you already know the math - the engineers shipping the most aren't running more tools, they're running a connected OS where every layer feeds the next. Most engineers have skills without memory, memory without safety hooks, and agents without observability. Nothing compounds. This map solves it: → Five root config files built in 30 minutes - CLAUDE.md, BRAND.md, SOUL.md, MEMORY.md, and settings.json turn any terminal agent into a dedicated GTM operator → 235+ skills across 11 domains including 18 GTM skills, 21 Clay workflows, 8 n8n automations, 44 marketing skills, 34 C-suite advisory skills, and 2,000+ B2B sales prompts - every one with install command and source repo → 500+ sub-agents across 6 collections with three personas - Startup CTO, Growth Marketer, and Solo Founder - each pre-loaded with the right skill stack → Four memory systems mapped with a decision guide - Obsidian vault for long-running projects, claude-mem for zero-config capture, cipher for lightweight setups, supermemory for autonomous agents → Safety hooks wired before any agent touches real data - block-dangerous-commands, protect-secrets, auto-stage, and notify-permission registered in settings.json → Full ecosystem coverage - 6 terminal agents, 9 multi-agent frameworks, 5 GUI clients, 5 infrastructure tools, observability stack, and 3 open protocols that make all of it interoperable No installing skills with no system to route them. No running agents with no memory between sessions. No rebuilding context from scratch when CLAUDE.md and MEMORY.md should load it automatically. What you get: - 30-minute setup guide for all five root config files with exact build order - 235+ skills across 11 domains with tiered loadout - always-on, project-specific, and situational - 500+ sub-agent templates across 6 collections with orchestration patterns - Four memory systems with a decision guide for which to use when - Full ecosystem map across terminal agents, frameworks, GUI clients, and open protocols Built from 6 months of mapping every open-source GTM agent repo, skill library, and protocol that ships in 2026. Want it for free? > Like this post > Comment "OS" And I'll send it over (must be following so I can DM)

@kgonia7 @_guillecasaus The world of AI Slop posts

@_guillecasaus In what universe "just released" is 3 weeks ago?

🚨 Google acaba de liberar sus skills oficiales para agentes de IA. Ha publicado 13 skills compatibles con Claude Code, Cursor, Copilot y otros agentes. Permiten que los agentes puedan ejecutar tareas avanzadas y automatizar flujos de trabajo complejos. Es gratis y open-source 👇

@steipete @RazaJamil89 @obviyus Well, now you could have it record a step by step guide on its own. 😎

@RazaJamil89 @obviyus It's all open source!

We now have video proof generation for issues on OpenClaw as part of working on QA automation. Codex [or a GH workflow] generates before/afters (crabbox does the screen recording). Kudos to @obviyus for automating real Telegram login! #issuecomment-4415012577" target="_blank" rel="nofollow noopener">github.com/openclaw/openc…

@stephenasmith All of the above.

If the 2026 midterms were to take place tomorrow, what issue is top-of-mind for you heading to the polls?

@trq212 Any chance you've doubled your customer support staff? Got suspended over a week ago and lost access to my Max20 account over something CoWork did. Then got charged again but still stuck on Free plan. Not sure what to do.

We're winding back our peak hours limit reduction and doubling 5 hour limits. Excited to partner with SpaceX to bring you more compute and we'll keep pushing to bring you the best coding agent in the world.

@ChefTrillie Lol ... Elon would spontaneously combust if he had to ... err, um...let's just say I don't think this is likely given his proclivities and recent history of tweets.

Would yall approve of Elon buying the Heat from Micky?

@MiamiHurricanes @Da12thMan @CityofMiramar @CanesFootball Incredible stuff for him, but also for the program to recognize this man for his dedication to the U and his community!

Huge congrats to Shelton Douthett (@Da12thMan) on being sworn in as a @CityofMiramar Police Officer! 🙌 Every home game, he honors his brother Wayne by wearing the @canesfootball uniform. Now, he brings that same heart to the force. We’ll see you on gamedays, Shelton!

@elonmusk Insurance doesn't cover fertility, the actual cost of living is through the roof with no end in sight, and our government is no longer representative. It's just two sides clinging to power so they can cash in at our expense. So yeah, this tracks. (You're not helping, btw.)

Troubling

@Renegade_Rocks @steipete That has always been a GPT issue...Not sure if it's entirely related to OC. One of my biggest frustrations over time with OpenAI models is how they often will tell you they are going to do something they clearly cannot. 7 prompts later... "I should not have said that, I can't..."

@steipete Ohk ! I was on 26.4 btw. Just checked. I guess so gotta take a deep breath and update 😇 and add gpt models back !

If you tried OpenClaw in group chats and got mixed results, you GOTTA try again. I changed how agents talk there, it IS SO GOOD NOW. #visible-replies" target="_blank" rel="nofollow noopener">docs.openclaw.ai/channels/group… And if you used GPT and got subpar performance, switch to codex harness. docs.openclaw.ai/plugins/codex-… Enable both and boom.

@steipete Does codex harness use Codex quota or chat? Wondering bc I have a ChatGPT business account, and don't want to burn through my Codex quota for non-coding tasks, whereas the chat quota is unlimited (within reason).

@aryanlabde Might have to if they don't fix their customer service and billing issues.

Vibe coders, have you really switched from claude to codex?

@NikiNikiHall @trq212 Ironically, Fin AI, the help agent they have on their site feels like it is running on Claude 2. Maybe, I'll apply for a job with them just to fix that experience.

@seanford @trq212 Did you try to get a refund? One of the users affected by Anthropic’s scam policy in my comments managed to get their money back. But statistically, it’s rare and difficult.

we're doing a lot more of this, hunting down some of the most annoying bugs in Claude Code let me know if you have any white whales

@NikiNikiHall @trq212 Yes, but no response. I'm sure my bank will reverse the charge, but really, I just want my account back. It's not like I have a history of offending behavior. It seems that @AnthropicAI needs to use their own agents to triage requests better, bc the response time is abysmal.