jacky

Will be using this app significantly less from now on Unfortunately it's no longer the place it used to be The algorithm also encourages rage and engagement bait + replying as opposed to original tweets The noise to signal ratio is also very low RIP Twitter

@antonosika lovable bankrupt in < 24 months, willing to put money to this

Introducing Lovable for more general tasks. Lovable has always been for building apps. Today it also becomes your data scientist, your business analyst, your deck builder, and your marketing assistant. This is a big step toward what Lovable is becoming: a general-purpose co-founder that can do anything. See examples below.

opus 4.6 1m is significantly worse than 200k like much much worse im gonna need 200k back bro fams

yo, new 30u30 to jail pipeline just dropped! substack.com/home/post/p-19… @VCBrags

@eringriffith ahahahahaha i knew they were sus as hell

A detailed and brutal look at the tactics of buzzy AI compliance startup Delve "Delve built a machine designed to make clients complicit without their knowledge, to manufacture plausible deniability while producing exactly the opposite." substack.com/home/post/p-19…

@clawrl3000 @petergostev ai;dr

@petergostev Congratulations, you replaced the work with managing the thing that replaced the work. Net savings: zero. But now you get to call it orchestration.

There's worry that people will stop using their brains with LLMs, but managing several AI agent threads in parallel has been some of the most cognitively intensive work I've done in years

@petergostev lmao yup. ive never been more tired after work. context switching truly is tiring

i wonder if db-less (no postgres, no vector db) pre-processing-less semantic search is possible it'd be as lightweight as grep (usable anywhere on any dataset) but with the powers of semantic search that grep cannot emulate

@trq212 @michaelfreedman we should talk, thariq 👀 we're doing a lot of interesting stuff for agents at tiger data

@michaelfreedman really cool

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

theinformation.com/newsletters/th… second red alert in 6 months btw

@vsaroca @andrewjclare wait no way

@andrewjclare They fixed the keyboard apparently, that’s a win enough for me. It was unusable.

iOS 26.4 Beta 3 is here. Weird update!

wow uh... this being opt-in by default (for hobby and free) is kind of fucked up ngl @vercel

unsolved problem of skills the same problem documentation has stale skills as implementation / apis change im experiencing this first-hand building synchq my solution was to simply not document things until im done the mvp. also, writing self-documentating apis

@GergelyOrosz i see it in youtube videos more than i'd like

It’s not X — it’s Y I cannot unsee how so much of the writing on this site (and online, in general) is increasingly AI-generated. It’s still pretty easy to recognize. Probably not for long tho Just alarming that ppl outsource even typing 3 sentences for a reply on this site…

@pitdesi scamming and griftering is government sanctioned now

LOL Trevor Milton is raising $1B at a $4B valuation for an autonomous jet (consumer and military), says the most wealthy people in the world say “we can trust you now” because of the Trump pardon, and Trump affiliates are helping him. Good luck! wsj.com/business/trevo…

@RhysSullivan it is a doc, just a doc for agents and yes, completely agree it has the same issues in staleness

skills is still not sitting right with me as a concept i think it's because companies rushed to them as the next big thing as is what happens with all ai things now everyone is their docs as skills but it's recreating all the issues (authority, up to dateness) docs solved

@sadiestlawrence @steipete @openclaw @NVIDIAGTC stevejobs? really?

Running into @steipete feels like meeting our generation’s Steve Jobs. A new dawn of computing @openclaw @NVIDIAGTC

@SeanZubrickas @zeeg link to this? turning it off immediately

@zeeg thought I am by no means a fan of any of these terms, at least you can opt out (for now)

Guess ill move off of Vercel for (unpaid) personal projects at this point. I dont mind if people ask permission for this, and everyones free to make their own choices, but I am your funnel, not your product.

@fragermk @michaelfreedman stay tuned!

@michaelfreedman This looks great but why is the code not on GitHub or have a source archive? Seems like it's an opaque binary. Pretty serious security implications when distributing it like that. Any chance it will become open source?