Matthew Johnson

@bil0090 Clearing disk space is basic computer maintenance. Use a disk utility to understand what is taking up space. I wouldn't trust Claude to know what’s important. Also, don’t buy a new monitor when yours gets dirty. You can clean it with screen cleaner.

Claude just saved me ~$5K in 1h 🤯 So, I have a 1TB MacBook, I had 100% used, only 2GB left Was about to buy a new MacBook, but... I went ahead & just told Claude to audit my MacBook & free up some storage, without deleting anything important I had to accept everything too, just to be safe After about 1h, it literally freed up 508GB, which is nuts Nearly half my storage is free It saved me from spending ~$5K on a new 2TB MacBook It also solved a memory issue I was having & made my MacBook faster, like new Next: I will be trying the security audit idea that @levelsio shared 🔥 Thanks @AnthropicAI, will reinvest this money in Claude again :)

Agentic Discipline #5 is up at cleancoders.com. cleancoders.com/episode/agenti…

Just finished our Week 3 project for @gauntletai. We built a multi-agent adversarial attack platform designed to test our Week 2 chatbot by mutating known attacks and generating novel ones to uncover unintended behavior. It was a great project because it forced us to think about AI systems from the attacker’s perspective: not just how to build useful agents, but how to stress-test them. youtu.be/9ioqNeOeEW4

An early beta of Grok Build, an agentic CLI for coding, building apps, and automating workflows is now available for SuperGrok Heavy subscribers. Through this early beta, we will improve the model and product based on your feedback. Try it at x.ai/cli

@unclebobmartin @smikhalevski I never took clean code to be a list of nonnegotiable extremes. I read it as a list of the things you should be thinking about and how to optimize for each one of them. Engineers must understand how to balance each principle for a specific project.

@smikhalevski Rude. Plonk.

When Clean Code came out it was treated like a bible. Just a while ago everyone felt obligated to trash Clean Code for being bloated idiocy (which it is). Now everyone is praising his takes on LLMs and code going away. Looking forward to seeing this delusional take age poorly 🤣

@brilliantlabsAR When do they start shipping?

Look up. Look around. Play. Halo turns the world into a place worth exploring again. A new way to see, make, and play. brilliant.xyz.

Introducing a 100% free coding agent with DeepSeek v4 Pro Choose any model, all free: - DeepSeek v4 Pro/Flash - Kimi K2.6 - MiniMax M2.7 npm i -g freebuff

Hey guy! I just completed my second weeks project for @gauntletai . This week we extended our agentic systems into multi-agent graphs and added pdf extraction of patient data! youtu.be/dN9IsVU_I6g

@htmleverything Can’t you be both?

I’d rather work with a developer who is skeptical of AI but still uses it, than someone who is an AI maximalist. Skeptical devs verify. They read the code. They question the architecture. They test the output. They understand AI is a tool, not a replacement for judgment. Blind excitement is where the dangerous stuff slips through

@ice_carev @BitRiftTech There are several good examples in github.com/unclebob/swarm…

@unclebobmartin I’d love to see what rules you use for your agents. I have two I put in by default in every project. One is based off clean code and the other off clean architecture. It’s been a game changer for my rules files.

Make that three blocks. Blocking the blockheads.

Hey guys! Just completed my first week's project at @gauntletai ! For the first week the assignment was to develop a "Clinical Co-Pilot" on an open source medical records platform. We were able to choose what the agent did. I chose giving physicians a briefing of medical records w/ follow up question capability. The demo video is here. youtu.be/NsrfjG9Hjro

@cjzafir One of the bigger models, drained my MacBook about one percent battery per query. That’s without anything loaded in the context.

I doubt this. ⚠️ Yes, you can run quantized models (qwen, llama, gemma) on macbooks. But they drain your battery super fast. Running 70B local model on macbook for 11 hours straight, without charging is unrealistic.

@astnkennedy You’ve likely been producing crap for 6 months. You need to be enforcing high level designs and choices, reviewing code, and reading very technical documentation produced by your ai. Typing code is only about 10-15% of what a software engineer does

I'm 22 years old and Claude Code is deteriorating my brain. Every single day for the last 6 months I've had 6 to 8 Claude Code terminals open, waiting for a response just so I can hit 'enter' 75% of the time. And it's doing something to me. In convos with a couple of friends, it's been a point that's been brought up pretty frequently. None of us feel as sharp as we used to. I don't know if it's just us, or others in their 20s are feeling the same thing, but it's something I've been thinking about a lot. P.S. I know this is a problem with my reliability/usage of it, not Claude Code itself, but the effects are real nonetheless

@nolapools Omg. This is troubling to hear this from an adult. From a child it would be cute. I hope your special reasoning improves

🫠😆

@unclebobmartin @samhogan Me either. I have rule files based on the clean code and clean architecture for guard rails. And I review every change manually. As well as specifying a structure so that multiple agents changes do not overlap when you’re running more than one

@samhogan Not me.

All the best programmers I know are starting to write code by hand again

Wait, you can just 3D print a circuit layout and then copper leaf it, and it works?!! We could have done this the whole time? @i2cjak @fishPointer @yacineMTB

sorry but this is seriously fucking impressive china just shipped a claude code-level ai model small enough to run on your laptop. it codes better than opus 4.5 and its tiny. 27B beating models 15X LARGER than it. best part? shit is fully open source. no cloud, no rate limits, no api keys this model plus kimi k2.6 tells me open source has caught up to the frontier models how the fuck did china pull this off?

@gauntletai hey guys. I’m having some trouble with my account. I applied for this upcoming cohort a few weeks ago and it looks like my account has been reset. I sent an email to support, but wanted to drop a note here as I know everything closes tomorrow. The email address is matthew@bitrift.tech

I sequenced my genome at home, on my kitchen table. I wrote up exactly how I did it - the equipment, protocol, theory, and cost: iwantosequencemygenomeathome.com