Nick Scheifler

Incredible how the new communication meta is not proper grammar but rather spotting and avoiding evolving trigger words that make you sound like a bot. Even if you're not a bot (you probably are). Key examples: - saying "real" before a noun when removing "real" does not change the meaning. ("the real question", "real scale", etc) - "Not X, but Y" rhetoric - Agreeing to the point and elaborating without actually saying anything new - Obvious comment trail on other accounts with the exact same behavior - EM dashes Basically, if you're not handwriting your thoughts and you think that's clever, you're NGMI

@LutheranNerd @roddreher

@roddreher There seems to be an underlying assumption in the article that LLMs *actually reason*. They don't. We still need competent knowledge workers. If the projections are true, we'll actually need even more knowledge workers to validate the flood of Ai generated analysis.

Read this. It's important. It's from a Silicon Valley guy talking about what AI is about to do to us, whether we want it or not. sahajgarg.github.io/blog/cognitive…

@sweatystartup The "just works" feeling when signing up for a cloud AI tool that you didn't implement yourself: a drug That sing-song voice the vendor's salesman deploys as they nudge you to subscribe: a siren's call

Every time you consider making a key AI tool a significant part of your business ask: Would this tool still make sense if it costs 5x as much? How disruptive would it be to stop using it completely 6 months from now? People aren’t thinking about the downstream impact.

@Spaztazim @oliverhenry all good brother, I learned a couple useful things in this thread. happy hunting

sorry, i was a little short and didnt mean to imply you were wrong. something is definitely going on, the enforcement and TOS isnt consistently applied. i think your right, the blowback would be crazy, they are kinda the golden child of frontier models, but that wont last if they go around ruining everyones fun.

Has anthropic finally banned openclaw? Just upgraded my max plan to 20x from 5x. Went from working fine, to: run error: HTTP 401 authentication_error: Invalid bearer token Thought I'd treat Larry to more tokens, now i think i have to cancel my anthropic subscription and switch.

@aisauce_x @staysaasy Tell your bot to stop saying “the real skill” when it can just say “the skill”

@staysaasy the real skill now isn't building. it's knowing what not to build. your team didn't suggest vibe coding it because they're optimizing for speed not ownership. that's a different kind of engineering maturity and most orgs haven't figured it out yet

About to buy some SaaS for my team next week. It has little scale or compliance or data moats. But it’s thoughtfully built a bunch of stuff that makes it a great product that will accelerate my team. Not a single person on my team has suggested we try to vibe code it ourselves. Feeling proud about that.

@staysaasy You’ll all regret that in 6 months or 2 weeks when you want to add a feature and can’t

@DannyLimanseta @alightinastorm People are commenting on themselves more than you. Your attitude is great. This is clearly the future and everyone wins except the big companies that ruined gaming

I don't care if people call it AI slop. Vibe coding games is fun. It's become my main hobby now, and no one can take that away from me.

@Austen Gemini is simply not competitive as a coding tool. But that will probably change. Their AI integration flywheel into their legacy stack is progressing well though

Honestly Google sucks at marketing its AI products. Gemini and family are dramatically underhyped for how good the models are. Partially because they don’t have a charismatic leader, partially because they’re buried in 18 layers of confusingly named Google enterprise bloatware.

@NickADobos @empathyx100 @petergyang @figma All bolt-ons that do not answer the question of why do we need figma at all

@empathyx100 @petergyang @figma - Figma make - Tons of ai tools. From things like remove background to nano banana 2 - I believe they are working on a supabase integration and hosting, so you tons of simple sites can probably just be done 100% in figma

Screw the haters, I am long @figma

@michaelfreedman I was actually just wondering about the architecture for my multi-agent platform and how to both back up and scale .md files for reliable access and editing... this is very interesting. Thanks. Followed

Introducing TigerFS - a filesystem backed by PostgreSQL, and a filesystem interface to PostgreSQL. Idea is simple: Agents don't need fancy APIs or SDKs, they love the file system. ls, cat, find, grep. Pipelined UNIX tools. So let’s make files transactional and concurrent by backing them with a real database. There are two ways to use it: File-first: Write markdown, organize into directories. Writes are atomic, everything is auto-versioned. Any tool that works with files -- Claude Code, Cursor, grep, emacs -- just works. Multi-agent task coordination is just mv'ing files between todo/doing/done directories. Data-first: Mount any Postgres database and explore it with Unix tools. For large databases, chain filters into paths that push down to SQL: .by/customer_id/123/.order/created_at/.last/10/.export/json. Bulk import/export, no SQL needed, and ships with Claude Code skills. Every file is a real PostgreSQL row. Multiple agents and humans read and write concurrently with full ACID guarantees. The filesystem /is/ the API. Mounts via FUSE on Linux and NFS on macOS, no extra dependencies. Point it at an existing Postgres database, or spin up a free one on Tiger Cloud or Ghost. I built this mostly for agent workflows, but curious what else people would use it for. It's early but the core is solid. Feedback welcome. tigerfs.io

@BEARLY_HODLING @thedawgyg Actually I have been sleeping on obsidian, what do you use it for?

@NickScheifler @thedawgyg Don’t you obsidian bro?

Opus 4.6 has a bad habit the last few days of outright lying... they must be making it more human... Have had multiple (more than 5) instances where it claims to have completed a task, then when I ask for info about the task and confirmation, it admits t didn't do the task and doesn't have an excuse on why. Then will do the task right then (finally).

@petergyang @figma I don’t see a reason to use figma when I can produce designs as code and I know I can’t be the only one thinking this

@hewarsaber Designers need to start coding faster than PMs and Engineers start designing

Holy shit. New Google Stitch is scary Designers, I think we're cooked

@AlexFinn 🤔 guess I’ll nuke them anyway to be safe

IF YOU'RE ON OPENCLAW DO THIS NOW: I just sped up my OpenClaw by 95% with a single prompt Over the past week my claw has been unbelievably slow. Turns out the output of EVERY cron job gets loaded into context Months of cron outputs sent with every message Do this prompt now: "Check how many session files are in ~/.openclaw/agents/main/sessions/ and how big sessions.json is. If there are thousands of old cron session files bloating it, delete all the old .jsonl files except the main session, then rebuild sessions.json to only reference sessions that still exist on disk." This will delete all the session data around your cron outputs. If you do a ton of cron jobs, this is a tremendous amount of bloat that does not need to be loaded into context and is MAJORLY slowing down your Openclaw If you for some reason want to keep some of this cron session data in memory, then don't have your openclaw delete ALL of them. But for me, I have all the outputs automatically save to a Convex database anyway, so there was no reason to keep it all in context. Instantly sped up my OpenClaw from unusable to lightning quick

The core problem: how can your AI give you good advice if it only knows what you tell it? Do you see yourself and your environment accurately? How can you be sure? We are all in Plato's cave. One must not be dazzled by shadows

@Bencera Hell yeah. Happy hunting, found you yesterday and you're a good role model

@NickScheifler This workflow will be automated for sure in the near future. So obvious.

my AI coding workflow as a solo founder: - opus 4.6 for exploration + planning - codex 5.4 xhigh to stress-test the plan (catches gaps opus missed) - back to opus, which usually complains codex is overengineering lol - few rounds back and forth. codex implements, opus reviews. - ask both: "safe to ship? what's the worst thing that could happen?" opus and codex arguing over my codebase is my entire engineering team. will probably ship this workflow as a Polsia feature at some point.

@Alex_TheAnalyst More people are not seeing what's right in front of them, opportunity or catastrophe, because instead of critically thinking they are asking biased questions to their AI and getting delusion-reinforcing responses. It's happening If that person is an executive... fireworks

I'm going to call this right now. We are going to have a large population with absolutely no critical thinking skills if they blindly trust AI for everything. We have all already seen it. They don't validate outputs. They don't really understand anything. They just ask questions, it looks good, and they go with it. There are going to be huge issues in every company as this continues over the years. The amount of technical debt and knowledge gaps are going to be insane. So much opportunity if you actually know what you're doing.