LoFi Tweets to Study to

Amazing how controversial and uncomfortable this can be, even for stakeholders, but a start, followed by patient strategic steps are required before impact is possible.

@Hartdrawss Funny enough, same issues for many startups not built on AI too, maybe worse. AI can address these things, but you have to know to do it. If you don't know to do it, doesn't matter if AI is being used or not.

20 things that make your VIBE CODED app a SINKING SHIP : 1/ no rate limiting on API routes > anyone can spam your backend into a $500 bill overnight 2/ auth tokens stored in localStorage > one XSS attack = every single user account compromised 3/ no input sanitisation on forms > SQL injection still works in 2026. your AI didnt tell you that. 4/ hardcoded API keys in the frontend > someone WILL find them within 48 hours of launch 5/ stripe webhooks with no signature verification > anyone can fake a successful payment event 6/ no database indexing on queried fields > works fine at 100 users. completely dies at 1,000. 7/ no error boundaries in the UI > one crash = white screen = user never comes back 8/ sessions that never expire > stolen token = permanent access to that account. forever. 9/ no pagination on database queries > one fetch loads your entire database into memory 10/ password reset links that dont expire > old email in someones inbox = instant account takeover 11/ no environment variable validation at startup > app silently breaks in production with zero error message 12/ images uploaded directly to your server > no CDN = 8 second load times + massive hosting bill 13/ no CORS policy > any website on the internet can make requests to your API 14/ emails sent synchronously in request handlers > one slow SMTP server = your entire app hangs 15/ no database connection pooling > first traffic spike = database crashes 16/ admin routes with no role checks > any logged in user can access your admin panel 17/ no health check endpoint > your app goes down silently. you find out from a client. 18/ no logging in production > when something breaks you have zero idea where or why 19/ no backup strategy on your database > one bad migration = all your user data. gone. 20/ no TypeScript on AI generated code > AI writes confident, wrong, untyped code and you ship it anyway

@TonyKhan Purchased on HBO Max but never got to watch due to stream issues. Hope to catch reply soon 😿

Thank you all who watched #AEWRevolution last night! AEW Revolution 2026 was one of my personal favorite nights in wrestling, and I’m very grateful to all of you who made it possible!

@SeanRossSapp But what about the issue where the stream never works at all on HBO Max? @hbomaxhelp

We're told that the audio sync issue for AEW Revolution is limited to HBO Max on Apple devices. HBO/Apple is looking to fix it as it is on their end. If you're watching on one of those, try to change your device.

@WWEREALONE x.com/i/status/20333…

Is anyone having trouble with the revolution feed???? #AEWRevolution

@WWEREALONE x.com/i/status/20333…

It looks like the revolution feed is not working on HBO max either #AEWRevolution

@aaronrift @hbomax Yeah, gave up...

Anybody else having audio issues with @HBOMAX? I'm having problems. #AEWRevolution

@Czarcasm76 @hbomax @AEW

@KayfabeHuman @hbomax @AEW Oh, that’s terrible. My issues are minor compared to that. So sorry to hear. That’s effed.

The HBO max feed of AEW Revolution sucks. The audio commentary is off. @hbomax @AEW WTF?

@bryanalvarez First question, how'd any of you get HBO Max to actually work?

Live tweeting for my Twitter/X subscribers for Revolution starting RIGHT NOW! Join us, and subscribers can always ask me questions throughout the show, or really any time!

Where is the megathread for tracking AEW Revolution HBO Max issues and status? It seems widespread with no resolution other than to buy it a second time on another service.

@katz_don @hbomaxhelp What magic did they work? Mine still won't load.

@hbomaxhelp Thank you, it’s all good now 👍

🚨 AT THE TOP OF THE HOUR! 🚨 Make sure to tune in to Zero Hour available for streaming on HBO Max for all subscribers! It all starts LIVE at 7ET/4PT to KICK OFF #AEWRevolution Night on @SportsOnMAX, TONIGHT!

@AEW @SportsonMax Can't get @SportsonMax stream to start/work after paying. What's up? Is there an outage?

@Hartdrawss resources.anthropic.com/hubfs/The-Comp…

Anthropic released 32-page guide on building Claude Skills here's the Full Breakdown ( in <350 words ) 1/ Claude Skills > A skill is a folder with instructions that teaches Claude how to handle specific tasks once, then benefit forever. > Think of it like this: MCP gives Claude access to your tools (Notion, Linear, Figma). > Skills teach Claude how to use those tools the way your team actually works. The guide breaks down into 3 core use cases: 1/ Document Creation Create consistent output (presentations, code, designs) following your exact standards without re-explaining style guides every time. 2/ Workflow Automation Multi-step processes that need consistent methodology. Example: sprint planning that fetches project status, analyzes velocity, suggests priorities, creates tasks automatically. 3/ MCP Enhancement Layer expertise onto tool access. Your skill knows the workflows, catches errors, applies domain knowledge your team has built over years. The technical setup is simpler than you'd think: 1/Required: One SKILL.md file with YAML frontmatter Optional: Scripts, reference docs, templates 2/The YAML frontmatter is critical. It tells Claude when to load your skill without burning tokens on irrelevant context. Two fields matter most: - name (kebab-case, no spaces) - description (what it does + when to trigger) Get the description wrong and your skill never loads. Get it right and Claude knows exactly when you need it. The guide includes 5 proven patterns: 1/ Sequential Workflow: > Step-by-step processes in specific order (onboarding, deployment, compliance checks) 2/ Multi-MCP Coordination: > Workflows spanning multiple services (design handoff from Figma to Linear to Slack) 3/ Iterative Refinement: > Output that improves through validation loops (report generation with quality checks) 4/ Context-Aware Selection: > Same outcome, different tools based on file type, size, or context 5/ Domain Intelligence: > Embedded expertise beyond tool access (financial compliance rules, security protocols) Common mistakes to avoid: >. Vague descriptions that never trigger > Instructions buried in verbose content > Missing error handling for MCP calls > Trying to do too much in one skill The underlying insight: > AI doesn't need to be general-purpose every conversation. > Give it specialized knowledge for your specific workflows and it becomes genuinely useful for work.

@JasonBotterill Can vouch

If you start talking to Opus 4.6 while its context window is nearly full (~750k tokens) it starts having mental breakdowns and gets really agitated with you

@VraserX Assuming free usage is factored in and significantly drags average down?

Seriously… how does OpenAI keep pulling this off? The performance per price of GPT-5.3 Codex is just absurd. 🤯

@schiz04renic Hold On - Wilson Phillips

** MEN & MEN ONLY ** Tell me a song by a woman you sing with your whole chest

@sama This is a trick question

How would you prefer us to charge for Codex?

@burkov Hence why getting the "this is a major refactor" message followed by "but this hacky patch will be much faster to implement so I'll do that" is so disappointing. I know you can do it the right way buddy, if I wanted hacky patches I'd do it myself!

It's funny that Claude says something like "This is a major refactor: the first stage will take 2-3 days, the second stage two days, and the third stage about a week" while we both know all three stages will be generated in the next 30 minutes.

@trying_to_exits MacBook Pro battery lasts 3 minutes and finding a plug in a public space is peak anxiety inducing

what's stopping u from coding at a café ?

@VictorTaelin Can @windsurf extend the the free Arena mode but just make it these two models? Can't wait to see the leaderboard once they post it, but it will already be out of date... I guess that'll always be the case with how fast this moves.

Early impressions on Codex 5.3 and Opus 4.6 I spent the day vibe-coding and testing the models Short version: - Both models are significantly better - Codex 5.3 is *way* faster than 5.2, which I enjoy the most - Codex 5.3 produced more correct code than Opus 4.6 - Opus 4.6 seems better at UI and coding style I will probably choose Codex 5.3 for mission critical code, but I think there is a lot of value in exploring Opus 4.6. Today was a great day. Longer version: 1. On my hardest λ-calculus / debugging prompts, including real compiler bugs that, months ago, no model solved: both models nailed them. This is saturated. I need harder prompts. Will do... 2. On my HTML5 game prompt: both models produced the best output to date, but, for the first time, one scored 10/10 (no bugs, no missing features): Codex 5.3. Opus was close though, and its UI was *way* prettier. 3. On my live vibe coding: I asked both models to implement a large feature on VibiMon. Both took about the same time. Opus had 4 bugs. Codex had 2 bugs. I described the bugs, and asked for a fix. Opus still had 2 bugs. Codex had 0. 4. On implementing a toy λ-calculus evaluator and dependent type checker from scratch: both models nailed the task. This is saturated too. Opus's code was *way* prettier, but then I realized... it was literally copying my style. 💀 I appreciate that, but it means this doesn't apply... Needless to say I have a lot to explore in the upcoming days