Sign in

Brett McCully

@bmccully.bsky.social
194 followers 87 following 636 posts

Engineer/Manager. ~25 years in the tech industry. Opinions about everything, many of them wrong.

PostsRepliesMedia
Brett McCully @bmccully.bsky.social · 26/07/2026
Claude Code seems to now be struggling to run installed skills, even when referenced in CLAUDE.md and asked explicitly. I said "use superpowers to show me in a browser" and it still created an artifact to push to claude.ai/code/artifact/ and spun up the local dev server before getting it right.
000
Brett McCully @bmccully.bsky.social · 16/07/2026
People still haven't learned that the "your name is your grandfather's first name and X" threads are easily data mined for security question answers. Sharing just this, and another piece on a Facebook thread, and other places online, all gets correlated together. OSINT tools make it easy.
100
Brett McCully @bmccully.bsky.social · 14/07/2026
Claude Code with Fable has hung the main thread multiple times when subagents were completed, but did not return. Fable also tends to create scripts in tmp directories and asks permission to run them, rather than multi-step shell commands. It's less transparent/observable.
100
Brett McCully @bmccully.bsky.social · 29/06/2026
Today I chose an off the shelf project management tool instead of vibe coding my own. The world is healing.
010
Brett McCully @bmccully.bsky.social · 20/06/2026
Decades of building, deploying, and supporting tech products gives me greater appreciation for the Human Computer Interaction courses in college. The way you think humans should behave is often very different from how they actually behave. It's been true for so much more than interface design.
110
Brett McCully @bmccully.bsky.social · 15/06/2026
Changed my handle and profile details to my real info. While I prefer to keep my data and info off the internet, there are real consequences with credibility when choosing to stay anonymous/psuedonymous.
030
Brett McCully @bmccully.bsky.social · 13/06/2026
Schroedinger's Bed Sheet: Sides are both wide and long until you reach the opposite corner.
220
Brett McCully @bmccully.bsky.social · 13/06/2026
Added a Solar Savings calculator to the site. It can tell you how much you can save with solar, or how many panels you need to offset your usage for the year. powerusage.app/solar #buildinpublic
Solar Savings calculator showing daily, monthly, and annual savings for solar panels, with configurable assumptions.
170
Brett McCully @bmccully.bsky.social · 11/06/2026
I've had to re-authenticate with Claude 3 times in the last 24 hours. They were in different projects on the same host, but it would not previously require another login. Either behavior has changed, or something is broken.
000
Brett McCully @bmccully.bsky.social · 10/06/2026
Holy sh**! Solar overtook coal in the breakdown of power sources to the US grid. That is huge!
000
Brett McCully @bmccully.bsky.social · 10/06/2026
I'll try not to spend my Facebook Consumer Privacy Settlement windfall all in one place.
Facebook Privacy settlement for $6.92 USD
000
Brett McCully @bmccully.bsky.social · 08/06/2026
For the millionth time, Chrome, I don't want to save my OTP as the password for this site.
110
Brett McCully @bmccully.bsky.social · 08/06/2026
I wrote a Power Usage calculator because I wanted to understand the real cost of my home lab and other electronic devices. Seattle gives the option to move to time of use billing, and I wanted details. . . . and then there was even more scope creep, so I built: powerusage.app #buildinpublic
Power Usage calculator showing the daily, monthly, and annual power cost of specific electronics.
160
Brett McCully @bmccully.bsky.social · 02/06/2026
Started using Codex as a fall back for Claude quota exhausted . . . not a fan. Default permissions are WAY too strict for command line usage. Workspace write is still too strict. It does not allow granting ongoing permission for headless browsers for testing.
110
Brett McCully @bmccully.bsky.social · 31/05/2026
Did Anthropic nerf subagents? Maybe to give them more wiggle room with capacity? Despite explicit requests to parallelize with subagents, Claude is still executing serially.
110
Brett McCully @bmccully.bsky.social · 28/05/2026
When will journalists stop anthropomorphizing AI? LLMs don't "believe" anything. They vomit statistically likely text combinations from their training data. Only removing the bad info from a training dataset will mean it won't be repeated. arstechnica.com/ai/2026/05/l...
arstechnica.com
LLMs believe false statements even after explicit warnings that they're false
Fine-tuning tests show "bias ... toward confidently representing the claims as true."
210
Brett McCully @bmccully.bsky.social · 25/05/2026
Is it Hermes or GPT 5.5? The combo strongly prefers to use convoluted approaches to solving easy problems. Instead of using command line utilities like curl, it writes python with httplib. Instead of tea to interact with forgejo, it uses curl. It does it even after preferences are in memory.
020
Brett McCully @bmccully.bsky.social · 15/05/2026
"May you live in interesting times" means now, if you work in cybersecurity.
030
Brett McCully @bmccully.bsky.social · 14/05/2026
Claude: Here, let me interrupt your complex multi-agent workflow to ask permission to remove an insignificant file while you are AFK
220
Brett McCully @bmccully.bsky.social · 17/03/2026
There were jokes about Code Janitor becoming a role because of all the vibe coding. While not a real title, the function is definitely real. I just joined a project that was vibe coded by a PM. The codebase doesn't need to be cleaned up, it needs to be burned to the ground.
111
Brett McCully @bmccully.bsky.social · 26/02/2026
Claude Code recent planning changes make yolo mode less useful. Without going to planning mode, it now stops you to ask if you want to continue to use bypass permissions, or clear context and bypass permissions. I use it so more can be done AFK. Stop asking!
100
Brett McCully @bmccully.bsky.social · 12/02/2026
Claude Opus 4.6 solutions are becoming "over elegant." It just gave a ~20 step plan for accomplishing a goal for running SSH commands locally to execute on a remote host. Bruh, there are already built in features (alternate fail2ban jail).
100
Brett McCully @bmccully.bsky.social · 06/02/2026
Dark pattern when claiming Opus 4.6 credits: Requires enabling extra usage when on a plan. People are going to forget they turned it on and likely continue paying for more than their subscription. At least it defaulted to Auto-reload off.
000
Brett McCully @bmccully.bsky.social · 06/02/2026
Asking Claude Code with Opus 4.6 to tackle a task list with subagents/teams in the backgrounds was FAST. About a month ago, building an app with separate task lists was mostly serial, even when asking to background. It's actually executing in parallel now.
100
Brett McCully @bmccully.bsky.social · 22/01/2026
@hboon.com I ended up trying the Ralph loop with recommended agent definitions directly within Claude Code, but it still did not continue to run. I feel back to the command line loop calling claud -p "/ralph-loop" and it ran much longer.
210
Brett McCully @bmccully.bsky.social · 22/01/2026
Claude Code vs Google Antigravity Claude Code wins overall, but Antigravity is easier for frontend workflows.
300
Brett McCully @bmccully.bsky.social · 15/01/2026
1. Do a Google Search 2. It brings you directly to the Gemini AI 3. Ask How to turn off AI search 4. Get a wrong answer 5. Switch the default search to Duck Duck Go
100
Brett McCully @bmccully.bsky.social · 07/01/2026
Claude Code . . . . what happened? Bad auto-update on Mac? Instances running on linux still work. 😢
200
Brett McCully @bmccully.bsky.social · 03/01/2026
"Token anxiety" When you are worried your current implementation burns too many tokens and could potentially bankrupt you.
010
Brett McCully @bmccully.bsky.social · 31/12/2025
They be little chonkers!
110
Brett McCully @bmccully.bsky.social · 31/12/2025
Reached a new milestone! All image assets are procedurally generated. Still significant fit and finish work to do on the project, but art changes are now much easier.
000
Brett McCully @bmccully.bsky.social · 29/12/2025
Back to work! Blender + Python for game assets.
010
Brett McCully @bmccully.bsky.social · 23/12/2025
Claude: Here's a detailed plan for what you just requested Me: Looks good, implement it <steps away for lunch> Claude: Here's extra detail on what you already approved. What do you want me to to? (I want you to stop halting your work to ask redundant questions) 🤦‍♂️
000
Brett McCully @bmccully.bsky.social · 22/12/2025
Telling Claude to "Ultrathink" feels like telling my kids to think about what they've done after they did something wrong.
000
Brett McCully @bmccully.bsky.social · 11/12/2025
Can confirm, Claude github integration burns through tokens. I asked it to add details and a plan to address an issue. In the CLI, it would be a small fix. When reading it's own investigation, it decided to walk the codebase again and use a multi-step thinking process with a todo list.
200
Brett McCully @bmccully.bsky.social · 10/12/2025
First time hitting the Claude 5x usage limit. Very productive morning with major changes. Time for a lunch break.
010
Brett McCully @bmccully.bsky.social · 09/12/2025
. . . . and now we're isometric.
000
Brett McCully @bmccully.bsky.social · 09/12/2025
It's getting there. Too bad I forgot how to math and can't calculate angles properly.
110
Brett McCully @bmccully.bsky.social · 07/12/2025
(Opens app on dual monitor setup) Me: Wow, this is taking so long to load, maybe I need a faster machine. App: Hey, I'm over here on the other monitor, idiot.
000
Brett McCully @bmccully.bsky.social · 05/12/2025
Refactoring with Coding Agents is like eating your vegetables. You should be doing it every day. Agents bolting on new features have limited context and do not prioritize reusing code. Even with agent definitions being told to do so, managing context windows has side effects.
000
Brett McCully @bmccully.bsky.social · 03/12/2025
(Minor change) Claude: Do you want to auto-approve the edits? Me: yes Claude: <asks permission for every tool used to read a directory related to the change>
010
Brett McCully @bmccully.bsky.social · 02/12/2025
Fought Claude Sonnet 4.5 on a bug for about 20 minutes, chewing through ~30% of the 5h quota. Very frustrating. Upgraded to Max and tried Opus 4.5. It fixed it first try. Happy for Opus, still angry with Sonnet.
110
Brett McCully @bmccully.bsky.social · 28/11/2025
I'm seeing the value of Claude Code's interactions limits, rather than just tokens. Its back and forth lead to significant token usage, and not fully under user control. By counting interactions, the user is not penalized. It also doesn't stop working mid-interaction leaving code broken.
010
Brett McCully @bmccully.bsky.social · 27/11/2025
Claude 5 hour usage limit is frustrating. 1. It does not show how many are left. /cost only shows tokens, not available interactions 2. Most of the interactions were explaining what it did wrong, not on new development. Non-transparent limits are bad. Don't penalize the user for your bad code.
300
Brett McCully @bmccully.bsky.social · 27/11/2025
Claude workflow: 1. Basic requirements prompt ask it to do Q&A to fill in details 2. Build a PRD, track open questions and tasks 3. YOLO code mode It ignored most of what was in the plan.
000
Brett McCully @bmccully.bsky.social · 27/11/2025
First impressions with Claude Code: - Much better at breaking down tasks than Gemini - Better at managing context window by offloading to markdown - Better interface for question and answer based planning workflows - Easy creation of specialized agents (PM, SWE, QA, etc)
100
Brett McCully @bmccully.bsky.social · 25/11/2025
Codebase is ~2500 lines, with ~100 lines of README.md and other instructions. Tried to refactor how the game tracks game pieces and renders enemy locations. It was a constant game of whack-a-bug.
000
Brett McCully @bmccully.bsky.social · 25/11/2025
Bad Gemini CLI behavior: ask it to roll back with a "git reset --hard" then it tries what it was doing again without being asked.
000
Brett McCully @bmccully.bsky.social · 25/11/2025
@hboon.com how good is Claude Code at avoiding spaghetti code?
110