👨🏻‍💻 Software Engineer ⚡ AI-first coding · Indie Dev 📈 Exploring AI tools & Polymarket 🌍 Traveling often

Berlin, Germany
Based in United States
Does anybody have any good Wispr Flow alternatives? I'm tired of it just failing on the most basic level sentences ever It's also kind of expensive for the quality that I get back. It seems like it's been nerfed. I don't care about those open-source alternatives that are going to make me feel "private" and deliver bad quality (i doubt a local first option can do this) I really just want high-quality responses
447
237
61,373
FluidVoice is a great alternative and free. Local dictation tools has become so good and they are private.
1
27
just hit $545k MRR... still the only full-time dev and the app is over 1m lines of code... in the last 7 days i merged 1,089 PRs here's the tech stack.. 1. over 50 oh-my-pi agents running in parallel on my home linux server 2. 8 Max Claude plans, 1 SuperGrok Heavy plan, and 5 max Codex plans 3. Slack & Telegram to communicate with my bots. I no longer use a terminal or IDE 4. Linear, the central PM tool my bots use for issue tracking. Every engineering request, bug report, alert and error gets posted here 5. Supabase staging database + Railway preview environments for testing 6. Ubicloud runners for GitHub Actions 7. 4 Mac minis as self-hosted runners for iOS builds and 15 end-to-end iPhone journey tests 8. Sentry for error monitoring 9. pstack by @poteto, my main agent uses her orchestrate playbook to manage the other 50 sessions. it never touches code. 10. a custom 5-stage planning harness before any code gets written. 11. customized pr-af and codex for independent code reviews, so that the model that wrote the code never passes it 12. greptile for final code reviews 13. a watcher that tracks every web merge in production for 24 hours, and reverts it on its own if real users start failing
133
42
1,242
114,884
For some reason this kind of posts with no real profile photos appear a lot and feels fake.
1
1
237
seems like now the best offer is $30 Premium plan so you get X, Grok, Bot, Cursor + $20 claude code for Claude models thoughts?
We've unified plans across Grok, Cursor, and X Premium. Introducing The X Subscription.
9
11
1,142
$30 for X Premium plan + Team plan from Claude Startup program 🤝
1
2
161
We might see Grok 4.8 from SpaceXSI this week! This could be a big one. Elon Musk has confirmed that Grok 4.8 has 2.5 trillion parameters, compared to 1.5 trillion in Grok 4.6. That's a massive 67% increase in model size, and I'm expecting a substantial leap in capabilities too. As with previous releases, I expect it to appear first in Cursor and Grok Build, with a wider rollout to the Grok app and website later. Really looking forward to putting this monster to the test!
Grok 4.8 is coming soon. Grok 4.8 will be the first Grok version under the new SI term. SpaceXAI should give it the name Grok 4.8 SI
52
24
506
26,624
Grok 4.8 needs to be at least Sonnet 5.5 level with affordable price. If they combine this with new Cursor/X subscription merge, we can see them back in the race.
2
218
Are people still using visual git clients? If so, what's the best client out there? What would make it even better?
106
1
96
32,917
Github Desktop, simple and does the job well
265
Got approved for Claude Startups program but the $1000 API credits and Claude Team offers disappeared from the portal. Saw it earlier but didn't claim it at the time. Anyone experiencing the same?
72
10
298
124,132
Özhan çözebildin mi aynı durumdayım
1
44
They re-reviewed my application and it is approved now. Any updates on yours?
7
BREAKING: GROK is getting ready to let you merge your CURSOR account into the X SUBSCRIPTION! 👀 A new "Merge your Cursor account" banner is coming to Grok settings. X, Grok, and Cursor under one roof! 🔥
69
30
677
38,116
I am very curious how they are gonna pull this. I am just hoping they make usage limits clear.
72
Özhan Yılmaz retweeted
Rather than using 5% of some big honking package like Microsoft Office or Adobe Creative Suite, you'll probably soon just ask your agent for the 5% you actually use. Bespoke software.
337
167
4,307
227,840
Özhan Yılmaz retweeted
Grok Bot now has its own email. Bot can use it to sign up for services, contact businesses for you, or schedule time with someone.
6,857
1,474
17,156
5,974,758
An update: I managed to claim it from the link directly. Team offer : claude.ai/offers/75dd5acf-01… API offer: platform.claude.com/offers/c… Hope this helps
47
22
298
46,980
also getting invalid page :( anyone else made it work with different link?
1
920
we're releasing an experimental @spacexai typescript sdk! npm install @xai-official/sdk get text, voice, image and video in one sdk, with the latest grok models and tools that run on our servers, like real-time X search, web search, code execution and remote mcp
76
79
1,269
124,669
That’s big. I wanted to test xAI APIs for awhile. This is the sign I was waiting for.
1
20
GameToMac now supports external storage. You can move games between your Mac and an external SSD in one click. Also added one click deletion for games + their environments
22
9
200
8,589
Not all heroes wear capes 🫡 Amazing work Marc!
1
3
131
Reactions to GPT-6 Sol are very mixed so far. On the one hand, the pricing is great. No doubt about that. But there’s also quite a bit of negativity around its performance. In benchmarks and real-world coding, it seems nowhere close to Astra or Opus 5.5, despite OpenAI’s claims. Is it just a souped-up Terra model after all?
I finally tested GPT-6 Sol on a real work. 2 repos. 105 hidden bugs. Find and fixed what you can. It looks like a huge degradation. The results: - GPT-6 Astra (max): 45 - GPT-5.6 Sol (max): 43.5 - Opus 5.5 (max): 41.7 - Muse Spark 1.3 (max): 32.2 - GPT-6 Sol (max): 29.3 Until you measure the cost (API-equivalent): - GPT-6 Astra (max): $33.04 - GPT-5.6 Sol (max): $95.25 - Opus 5.5 (max): $58.53 - Muse Spark 1.3 (max): $18.11 - GPT-6 Sol (max): $9.93 More effort levels (xhigh, high, medium, low) dropping in this thread today 🧵
44
8
224
23,950
It feels quite similar to 5.6 Sol medium when I use 6 Sol in high mode with much more usage. Opus 5.5 definitely superior.
1
31
I’m back home in Cyprus 🇨🇾 after 10 days in Turkey 🇹🇷 We got lost in non touristic areas, and we discovered raw Turkey away from busy Istanbul. Turkish people are so kind and welcoming! People randomly talk to us, ask where we’re from, and offered us Turkish tea. Someone even gave us the figs he picked up from the tree 🤤 We didn’t do anything special. Just walking around local neighborhood. That’s my favorite way to travel, because you get to see how people are living for real. I normally don’t mess my diet, but baklavas are so good I had a few of them ever day 🙈 Teşekkürler Türkiye!
100
15
2,151
153,464
What a kind post. Teşekkürler Marc!
2
434
Been living in Opus 5.5 for a bit now. Weirdly familiar. The way it talks reminds me of Opus 4.6, which I always liked. But it’s clearly smarter. Feels close to that Fable-level “just get the hard thing done” vibe. Enjoyable daily coding partner so far.
Claude Opus 5.5 is available today.
1
98
Using Grok 4.7 in Cursor. It feels significantly slower. It also burns more tokens, so my usage limits drain faster. Price didn't change. The cost of using it did.
Grok 4.7 is here. It's a notable improvement over Grok 4.6 at the same price and speed.
1
84
Grok 4.7 is out! Smarter and more capable, at the same speed and cost.
Grok 4.7 is here. It's a notable improvement over Grok 4.6 at the same price and speed.
139
88
2,159
96,871
Let's see what they cooked :)
7
ai agent/harness tiers
452
207
5,142
755,103
Codex and Cursor are easily A tier.
1
471
Convince me to uninstall Codex. You have one line.
237
3
123
24,249
Reduced usage limit
1
106
BIG WEEK for AI incoming, starting with Grok 4.7, and including something from Anthropic (Opus 5.5) and OpenAI (GPT-6 Sol). 🚀 Which release are you most excited about?
135
19
396
20,366
Gbt usage limits have been reduced significantly. I am more excited about grok 4.7 and opus 5.5
94