Vadim Comanescu

you can outsource your thinking but you cannot outsource your understanding

@Pinperepette 😂😂😂 cpu e gpu at 100% 💯

@vadimcomanescu Turns out it wasn’t Claude Code doing the work… it was you running in the background the whole time 😄 CPU at 100%, documentation at 0%. 😂

two weeks into rebuilding my internal ops with claude code and the real lesson isn't about the model. it's that 80% of my workflow pain was undocumented tribal knowledge i was carrying in my head. the agent forced me to write it down. turns out i was the bottleneck.

@InsiderPresider Indeed tribal yes 😂

@vadimcomanescu tribal knowledge 😂

@vadimcomanescu @atmoio LLMs can make you faster on things you are already good at. If you use it as an expert on something you have no clue about, it *will* fail you at some point. Go deep on a well known topic to see its limitations, then extrapolate that to other areas. x.com/CursiveCrow/st…

TigerFS started as a simple idea: a filesystem backed by Postgres. Over past several weeks, I’ve been pushing that idea further with history logs and arbitrary undo. Not only to named snapshots, but rolling back to any point in time. Across the full workspace, a single file, or even selectively undoing the changes made by a specific agent. It effectively creates a safe "undo" layer for agents. You don’t have to trust them to clean up after themselves, or pollute your git history with lots of unnecessary commits. One fun part was building a stress tester that runs pseudo-random filesystem operations in a loop. Simple, but very good at surfacing edge cases.

@vadimcomanescu You're not alone

@TimJanik @atmoio Will do. Anything that can help me … it’s more than welcome.🙏🏾

@vadimcomanescu You need to start watching @atmoio It might feel weird at first, but it's the only true way to get your SF de-programming journey started.

I feel dumb. I don’t understand how everyone is having this crazy breakthrough with the latest models and I’m struggling like a dog. Every single workflow feels like pain … why?

@jxnlco Just tmux?

When you gotta bike home from work but your codex needs to finish a task.

So?

Paperclip has faced some skepticism for being org-chart based Won't the infinite, all-knowing agents create their own organizational structures? Isn't the org chart anachronistic? Let me give you "7 Reasons why human org Charts Help Agents Run Things (CHART)" Starting with..

@headinthebox No, I must say the copy and paste analogy is so true. Imagine that i’m using 4.6 downgraded … I’m still shocked that the entire world is not shouting like crazy about this ..

"... The disciplined way to find it is the ... I never finished ... It's a half-day of work but it ends with bit-close parity rather than guesses ..." If Claude Code keeps just fucking around trying random shit instead of doing what it promised, and continues to be as slow as a snail ("Cooked for 1h 22m 54s"), that estimate of a half-day might actually be accurate. On a more serious note, I feel I was more productive in January 2023 copying and pasting code between IntelliJ and ChatGPT 3.5 than with the current Claude Code. Sad, very sad.

Is it just me or using Hermes or a new generation agent has literally obliterated n8n or crewai … what am i missing here

@rauchg is json-renderer an important project in your roadmap? Can we bet seriously on this?

Ghostty is leaving GitHub. I'm GitHub user 1299, joined Feb 2008. I've visited GitHub almost every single day for over 18 years. It's never been a question for me where I'd put my projects: always GitHub. I'm super sad to say this, but its time to go. mitchellh.com/writing/ghostt…

@Shivam25mishra @dkundel Unpopular for ?

Unpopular Opinion : CODEX is far better than Claude Code

@Teknium Hermes is close to being great for customer-facing chat agents. The gap isn’t capability, it’s communication: Slack/Telegram gateway messages still leak operator internals—tools, iterations, job IDs, approval mechanics. A customer communication mode would be huge. My 2 cents. Would make it easier for consultants to deploy it in companies… for production. Its ready. But needs a better customer facing messaging. My 2 cents ofc.

i'm sort of addicted to working my butt off, always have been. in oss, that can consume you. constant feeling of urgency, as issues stream into the repo. been there many, many times with my other oss. but that urgency is not real. if something is truely broken, a large number of people will scream at you on all channels. which has happened exactly zero times so far, or was caught minutes after a botched release and immediately fixed. it's kind of crazy that some people expect better support from an oss project than from commercial software. i think that's largely due to most commercial software corps not giving a fuck. try filing an issue with corporate and getting it fixed within 24h or less plus a personal response. and as oss builders don't have a corporate facade shielding them from direct contact with users, some sort of bidirectional parasocial relationship establishes itself. at a certain scale, that becomes entirely unhealthy. for every 10 kind and thoughtful people, there is 1 asshole. and whatever the asshole says or feels entitled to, sticks with you much more than positive feedback. obv. also happens in corpo environments, especially if you do comms or dev rel, where you put your face and name out there. but a corp that can afford dev rel usually also has a large team in the back, which can soften the negative aspects. in oss, you are largely on your own. and unpaid. that too is a choice of course, and nobody is forcing anyone to do oss. but if you want oss to work, consider that there are other people at the end of that issue tracker/social media account, with lives and squishy human parts. also consider that you are paying nothing for their service, and you are owed exactly nothing, neither code nor attention to your every wish.