utx0_

@zuess05 Messy isn't the issues its all the bugs and wrong decision it takes without asking

Senior developers are currently having a massive existential crisis because Claude writes "messy code" A junior just used Claude to ship an entire feature in 2 hours. Meanwhile, the Senior is still spending 3 days reviewing code. When will y'all realize that literally nobody cares if the code is "messy"?

@jpthor SDD frameworks help with this. Ive been building this to help; github.com/mettadata/metta (Still very beta)

@atmoio So true.

AI is giving every CEO the same advice

@bensig Very cool, im building a meta SDD framework right now that could use this very nicely.

My friend Milla Jovovich and I spent months creating an AI memory system with Claude. It just posted a perfect score on the standard benchmark - beating every product in the space, free or paid. It's called MemPalace, and it works nothing like anything else out there. Instead of sending your data to a background agent in the cloud, it mines your conversations locally and organizes them into a palace - a structured architecture with wings, halls, and rooms that mirrors how human memory actually works. Here is what that gets you: → Your AI knows who you are before you type a single word - family, projects, preferences, loaded in ~120 tokens → Palace architecture organizes memories by domain and type - not a flat list of facts, a navigable structure → Semantic search across months of conversations finds the answer in position 1 or 2 → AAAK compression fits your entire life context into 120 tokens - 30x lossless compression any LLM reads natively → Contradiction detection catches wrong names, wrong pronouns, wrong ages before you ever see them The benchmarks: 100% recall on LongMemEval — first perfect score ever recorded. 500/500 questions. Every question type at 100%. 92.9% on ConvoMem — more than 2x Mem0's score. 100% on LoCoMo — every multi-hop reasoning category, including temporal inference which stumps most systems. No API key. No cloud. No subscription. One dependency. Runs on your machine. Your memories never leave. MIT License. 100% Open Source. github.com/milla-jovovich…

@thestanduppod If you dont know how to instruct a AI or a human you get slop.

The Market for Bad Programmers

@eurofounder Maybe he thought you were a dick and now you proved him right?

I offered a young engineer €350,000 salary to join my German startup He declined This is the most ungrateful generation I have ever seen How can you reject such a package? €41,000 - cash salary + €52,000 - multicultural city adjustment +€48,000 - public transport adjustment +€45,000 - universal healthcare adjustment +€41,000 - GDPR privacy adjustment +€38,000 - walkable city adjustment +€35,000 - no tip culture adjustment This is more than he would make at OpenAI or Google in the US His loss, I already offered the role to a more grateful candidate at €290,000

@3266miles @AnthropicAI context management bruh

I've been extremely hesitant to call out @AnthropicAI for anecdotal degradation in Claude's performance, but whatever they've shipped to the harness in the last few releases has absolutely lobotomised it. This is an *identical* workflow to what I was running last week.

@JosephJacks_ @OSSCapital Ha, I don't trust closed source anymore. Oh, now a word from our sponsor? lol

Welcome to the @OSSCapital portfolio. 🤲🏼

@digitalshane_ Are you using any SDD frameworks? That helps I find.

I'm not joking, I had Claude write a big batch of code last night. I am troubleshooting rn. I asked it to review, It said this is trash code and it needs completely reworked. We are spending credits to run in circles.

I just quit using #SpecKit for #GSD. So much nicer and way better results so far.

@rishikagupta__ @sev4_inchident Ive already got an agent that checks a running system for memory leaks issues and then will run tests and fix them. No human in the loop

@sev4_inchident i wish that can be automated :’)

If everything can be automated with AI, what will humans do?

@xoaanya Indexes

Interviewer: If Google searches hundreds of billions of pages, how does it return results in under 0.5 seconds?

@zebassembly Something it goes off and does the work in a git worktree without telling you.

I just watched Opus 4.6 pretend to modify the codebase for 5 minutes to implement a new thing, literally said it was done with 0 edits What the hell did Anthropic do to opus

@bcherny Would be great if it was reliable

🤯 You can now launch Claude Code sessions on your laptop *from your phone* This blew my mind the first time I tried it

@ilex_ulmus @AnthropicAI Pretty sure it was from the GPS jamming and a Iranian missile dropped on them due to this

It’s time to quit, @AnthropicAI employees. You are in over your head.

@trq212 this stops the thread for me....

We just added /btw to Claude Code! Use it to have side chain conversations while Claude is working.

@jpthor good work claude

@freak4pc @AnthropicAI @claudeai I do something similar to this, but it creates new git worktrees and a new claude-code within a tmux session on a VPC. Very handy.

Thanks to the amazing support for Ghostty scripting with ApplScript, I made a tiny skill for myself that can delegate work to new @AnthropicAI @claudeai sessions in individual Ghostty splits 😍🤩 just what I wanted for so long. 🚀 Thanks Mitchell and team! 🔥

@heeney_luke where was this?

Australians in AI are absolutely STACKED

@RoundtableSpace ??

@RoundtableSpace link?

SOMEONE VIBE CODED A FULL CLI, MCP, AND SKILLS LAYER ON TOP OF DEXSCREENER - PULL LIVE CHAIN DATA, SET ALERTS, SCAN HOT RUNNERS, ALL FROM YOUR TERMINAL. YOUR AGENTS CAN NOW READ CRYPTO ALPHA DIRECTLY. FREE AND OPEN SOURCE.