Ali Abassi

@mattpocockuk pi + openrouter

Folks who are running GLM 5.2, how are you doing it? What harness/provider are you using? Getting FOMO about an open weights model for the first time

@reformedot Yes please

Browser fingerprinting is one of the most fascinating rabbit holes out there. Some Chromium fingerprinting techniques go absurdly deep. The complexity is insane, and I keep discovering new things. Should I write a blog?

Shutting down Fable 5 was the best marketing move i've ever seen.

@LexnLin real talk, its great prompting

THANK YOU 🫶 40k⭐ growth has been insane, can't even keep up with the new skills 😭

@kunchenguid yep exact same thing - its getting a bit over confident with approvals

ok be careful with your fable 5. i just ran into a new problem that never happened before - it's now doing things i didn't ask i just told it there is a bug in a repo. without checking with me, it did the fix AND raised a PR using my gh cli, claiming it's following CONTRIBUTING.md the PR was not bad, but it's a big surprise as it - assumed the credentials in my gh cli is the one i wanted to use - assumed i would be happy with the change as is - assumed i was ready to publish the work that's a lot of assumptions from just me telling it to fix a bug. i now feel the need to explicitly tell it NOT to do extra things which increased cognitive load for me and it's not a good feeling

@LexnLin Looks identical to the @ouraring website

Guess which is Opus 4.7 and GPT 5.5 👀

@kobyjconrad Ughh what in the 2025 are you talking about I haven’t given permission for ages 😅

I really don't get the appeal of codex 👀 How is having to press "yes continue" 100 times to complete a project better than Cursor just completing the project?

@paraschopra Clever!

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

@Lindyydrope great use case!

my fav use case w/ Lindy is never touching slack after a call

@masonwarner Oooo I wanna see 👀

I've worked on 2 videos the past week that have genuinely blown my mind > fully generated with AI (MJ 8.1 + NBP + Seedance 2) > finished in <24 hours > ~$1400 spent on credits The output is something that honestly feels real and atp I'm having to really start nit picking

@ChrisVanDerKlau @Ex0byt Mistral likely

@Ex0byt who the hell is this loser ?

There’s no ‘gap’, and no one’s 8 months behind. We’ve been trolled on every closed U.S drop and flexed on with open weights.

@replicate @PrunaAI Pricing is absurd - thank you

P-video-avatar by @PrunaAI is live - Built-in TTS, 20+ languages + voice selection - Dynamic backgrounds + body/camera control - Up to 3-minute generations - 1080p support, $0.025/sec - Cinematic-quality avatars Free all weekend ↓

@gregpr07 🐐thank u

How it works The LLM never watches the video. It reads it — through two layers that together give it everything it needs to cut with word-boundary precision. Layer 1 — Audio transcript (always loaded). One ElevenLabs Scribe call per source gives word-level timestamps, speaker diarization, and audio events ((laughter), (applause), (sigh)). All takes pack into a single ~12KB takes_packed.md — the LLM's primary reading view. Layer 2 — Visual composite (on demand). timeline_view produces a filmstrip + waveform + word labels PNG for any time range. Called only at decision points — ambiguous pauses, retake comparisons, cut-point sanity checks. Same idea as browser-use giving an LLM a structured DOM instead of a screenshot — but for video.

Introducing: Video Use. Edit videos with Claude Code. 🫡 I got tired of paying for video editors, so I made a Claude Code skill that does it for me. > Talk to camera, get final.mp4 > Auto cuts fillers, color grades, adds subtitles > Adds Manim and Remotion animations > Self evals the render before you see it 100% open source, 100% free.

@with_sherpa whatttt! thats amazing

We graded Notion's landing page and… it wasn't great. Get your own annotated site review in 30 seconds. Link in 🧵

@andrewfarah Thank you! Needed this

sharing my first open source project a CLI for downloading and syncing your X bookmarks locally so your agent can access them. it's free › npm install -g fieldtheory › login to your X account in a chrome tab › ft sync (done!) bonus: › ft viz › ft classify

Claude Code: Context limit reached · /compact or /clear to continue Me: hmmm okay /compact Claude Code: 👀 error Me: ughhh /clear Claude Code: 👀 error

@usebland Lfggggggg

npmjs.com/package/bland-… - Build entire calls from our CLI - Let your model of choice (Claude, Chat, Grok, etc) self simulate and iterate - Publish live - Profit (??)

@Lindyydrope Bookmarked! Too much sauce @Lindyydrope

most sales leaders are overwhelmed right now with when and how to use ai. too much noise :) this is what's actually working for me.

i use AI in every part of my sales workflow. here's exactly how →

@gdb It’s been vibes all along

Benchmarks? Where we’re going, we don’t need benchmarks.

@JustinLin610 R u going to xai after that Elon tweet?

me stepping down. bye my beloved qwen.