Osama Romoh

4.5K posts

Osama Romoh banner
Osama Romoh

Osama Romoh

@romoh

Follow me for practical AI tips, reviews, and more.

Dubai, United Arab Emirates Katılım Ağustos 2008
247 Takip Edilen5.7K Takipçiler
Osama Romoh
Osama Romoh@romoh·
Claude with API access to your Google Ads account is a new media buyer who: - Works 24/7 and never asks for coffee - Will pause a $200/day campaign at 2am because the CPC "looked weird" - Doesn't know your client's quarter ends Friday - Has zero fear of restructuring an ad group you spent two weeks building lol - Will email you a confident weekly report even when half the conversion data is from a tracking outage What else?
Osama Romoh tweet media
English
0
0
4
7.7K
Elon Musk
Elon Musk@elonmusk·
Try Composer 2.5
BridgeMind@bridgemindai

New CursorBench results just dropped. Two big takeaways. Composer 2.5 is way better than most people think. 63.2% score at $0.55 per task. Nearly matching Opus 4.7 Max and GPT 5.5 Extra High at 20x less cost. This is insane value. Gemini 3.5 Flash is #10 at 49.8%. Below GPT 5.5 Low. Below Opus 4.7 Low. Google's newest model can't even beat budget tier competition. Composer 2.5 is the sleeper. Gemini 3.5 Flash is the disappointment.

English
2K
3.3K
21.2K
8M
Osama Romoh
Osama Romoh@romoh·
Whoever says that GPT 5.5 is better than Opus 4.7 these days.. I gotta say, that's 100% accurate.
English
1
0
0
35
Osama Romoh
Osama Romoh@romoh·
Is SuperGrok Heavy worth the $300/month? I’m keen on testing out Grok Build tbh.
English
0
0
0
65
Osama Romoh
Osama Romoh@romoh·
Building an AI agent used to feel hard. Here's what I actually do now: – Find a YouTuber who's an expert in the thing. – Drop a few of their videos into Claude. – Ask Claude to write a prompt that mimics how they think. Done. 3 minutes. Free. Better than 90% of "prompt templates" people sell.
English
0
0
0
47
Theo - t3.gg
Theo - t3.gg@theo·
I have cancelled my subscription.
Theo - t3.gg tweet media
English
46
29
2.3K
158.6K
Theo - t3.gg
Theo - t3.gg@theo·
I can't help but feel personally burned by the Claude Code changes announced today. We put so much work into wrapping the (atrocious) Claude Agent SDK in T3 Code. It was the ONLY path they supported, so we made it work. It was hell. Now our users are getting their rate limits cut by 40x, despite us doing everything right. I listened to the Claude Code team. I had my issues with their direction, but I trusted them and took them at their word. I will never make that mistake again. Until we see significant change, it is safe to assume any statement from an Anthropic employee is a lie on a timer. The rug will be pulled, no matter how many promises are made beforehand.
English
421
312
8.7K
1.6M
Osama Romoh
Osama Romoh@romoh·
@M2Fauzaan I like how simple your app is, but yeah do ship that navigation view.
English
0
0
1
52
Osama Romoh retweetledi
Theo - t3.gg
Theo - t3.gg@theo·
OpenAI and Microsoft broke up. The impact of this is massive and I don't think enough people understand why. Put a lot of time into tracking the history of the deal to help you all understand 🫡
English
36
7
431
50.7K
Osama Romoh
Osama Romoh@romoh·
Most people using Claude Code touch about three features. I use twenty. Every day. Daily means daily. I ranked them by how often they actually save me hours, and the top of the list isn't close. ✅ Subagents are number one. Parallel work in clean context windows. Nothing else comes near. ✅ Skills are number two. Packaged expertise loaded on demand, so I'm not retyping the same instructions every session. ✅ Then slash commands at three. Repeat workflows collapsed behind one keystroke. ✅ Plan mode at four. I see what's about to happen before any action is taken. ✅ CLAUDE.md at five. The only way I've found to make project rules actually stick. The rest of the list is the muscle behind a real workflow. Honestly, if any of these dropped off the list, I'd notice within an hour. 😁 Full ranking in the graphic. 👇 Feel free to save this post or repost it to your network.
Osama Romoh tweet media
English
0
1
0
50
Osama Romoh
Osama Romoh@romoh·
Three frontier models dropped in the last few weeks: GPT-5.5, Opus 4.7, and Gemini 3.1 Pro rolling out wider, and LinkedIn turned into a benchmark trading floor overnight lol. Nobody actually building with these things seems to care which one "won," because there's no best model. There's only what you're trying to do this week. My stack right now: * GPT-5.5 runs the agentic stuff, computer use, multi-step jobs, anything I want chaining tools without me babysitting it. * Opus 4.7 handles the code; it's the first one I trust on production work without rereading every line. * And Gemini 3.1 Pro picks up whatever's cost-sensitive like bulk image work, long video transcripts, anything where the bill gets ugly fast. Different jobs, different tools. The "Claude is dead" / "GPT won" crowd mostly isn't building anything that has to work on Monday. What's doing what in your stack this week?
English
0
0
0
46
Osama Romoh
Osama Romoh@romoh·
Nice work.. any plans for dark mode?
Luca Rossi ꩜@lucaronin

Just released the new stable version of Tolaria. It fixes basically all bugs that have been reported! For today and the weekend the focus will be on dark mode and windows support, plus merging some of the PRs (they are good!) Also got up today to Tolaria on the front page of HN, double the Github stars, and just a ton of messages from everyone 🙏 Release page here for those interested: refactoringhq.github.io/tolaria/

English
0
0
0
18
Osama Romoh
Osama Romoh@romoh·
Anthropic just pulled Claude Code from the Pro plan.. is this true? 😱
Osama Romoh tweet media
English
0
0
0
39
Osama Romoh
Osama Romoh@romoh·
Grok 4.3 dropped on Friday with basically no press. One low-key post from Musk, no release notes, no blog, no livestream. It just showed up in the model selector for people paying $300 a month. $300 a month, by the way. That's SuperGrok Heavy, the top tier. Regular SuperGrok at $30 can see the model in the dropdown but can't actually click it. What xAI shipped is a half-model. It's 0.5T parameters, not the full 1T version that's still training. Musk confirmed that part himself. So Grok 4.3 right now is half of what Grok 4.3 is supposed to be, priced 10x higher than consumer Grok, with zero marketing telling you any of that. Companies don't quietly ship products they're proud of. A launch goes stealth when the benchmarks came back mid and you'd rather have the sub money than the comparison charts. Compare it to OpenAI this week. GPT-Rosalind for life sciences, partnered with Moderna and the Allen Institute, full press push, the whole accelerate-drug-discovery framing. Whether you buy that or not, it's what a company that wants eyes on its launch does. xAI is shipping like a company that doesn't. Anyway, time to test Grok 4.3 beta. 😄
Osama Romoh tweet media
English
0
0
0
56
Boris Cherny
Boris Cherny@bcherny·
4/ Focus mode I've been loving the new focus mode in the CLI, which hides all the intermediate work to just focus on the final result. The model has reached a point where I generally trust it to run the right commands and make the right edits. I just look at the final result. /focus to toggle on/off.
Boris Cherny tweet media
English
27
19
819
192.6K
Boris Cherny
Boris Cherny@bcherny·
Dogfooding Opus 4.7 the last few weeks, I've been feeling incredibly productive. Sharing a few tips to get more out of 4.7 🧵
English
335
1.1K
11.8K
1.6M
Osama Romoh
Osama Romoh@romoh·
Claude Opus 4.7 is reportedly dropping this week. Here's what we actually know. The Information published an exclusive yesterday saying Anthropic is prepping Opus 4.7 alongside a new AI design tool that builds websites, landing pages and presentations from a prompt. Aimed at both devs and non-technical users, which basically puts it in direct competition with Figma, Adobe, and tools like Canva. The npm code leak from March already had version strings for Opus 4.7 and Sonnet 4.8 buried in there, plus codenames like Capybara and Capiara. So this has clearly been cooking for a while. And the timing is wild. OpenAI just dropped GPT-5.4-Cyber yesterday too, a fine-tuned model specifically for defensive cybersecurity work with binary reverse engineering capabilities. Only available to vetted security pros through their Trusted Access program. Anthropic already had Mythos out to ~40 orgs under Project Glasswing doing similar stuff. Both companies are basically racing to own the AI cybersecurity space now. This week might genuinely be one of the busiest in AI history. Meta's got LlamaCon, OpenAI is moving, Anthropic about to ship. It's a lot.
Osama Romoh tweet media
English
0
0
0
91

Keşfet

@elonmusk @theo @M2Fauzaan @BarackObama @taylorswift13 @cristiano @BillGates @NASA