Itay Adler

@bonesy why is the stat card showing Deni with an Iranian flag?

Deni Avdija is literally one of the best young players in the nba and no one cares This statline is insane

@LukeW Exactly! Using tools like frontman make it effortless for any stack holder to produce changes visually on the product right from the browser github.com/frontman-ai/fr…

finally. the designer/developer handoff is dead.

@SeHozaifa It’s all about accountability, not credit.

If AI Writes 90% of your Code... Do you Deserve 100% of the Credit?

@zachkrall trying to fit all the trends into one box to fit as many personas as possible to pump that valuation baby

ok i still dont understand why chat, cowork, code are even separate tabs to begin with

@Amank1412 I can rewrite 1000% of your code with AGI

Backend Developer interview: We can write 80% of our code with AI why should we still hire you. What will be your response?

@rotempe4 if you try Gemma download the unrestricted ones from huggingface otherwise it’s super annoying. The gpt-oss one is also nice

היום אנסה לשים מודל מקומי מאחורי הסוכן שאני בונה, יש עוד משהו חוץ מג׳מה 4 ששווה לי לנסות?

@konnydev 1337

Screw favorite colors, whats your favorite localhost port?

@kapilansh_twt I moved to frontman github.com/frontman-ai/fr…

genuine question are people still using VS Code or has everyone quietly switched to Claude Code or Codex or Cursor or am i the only one ?

@JakeKing frontman github.com/frontman-ai/fr…

Who's building devtools in 🇨🇦right now? want my algo to be filled with cool people building cool shit up here.

@ionleu github.com/frontman-ai/fr…

drop ur startup link

@theo what the hell happened?

Robinhood refused a buy order, didn't notify me, withdrew my money anyways, and cost me over $10k in lost gains in the last 24 hours. What the hell should I be using instead?

@floriandarroman I stopped using both, Frontman won. github.com/frontman-ai/fr…

I stopped using OpenClaw. Claude won.

1) use agent harnesses that use 1/10 of the tokens 2) the open source chinese models where a lot of companies including NVIDIA run a service for you to use them are competing quite well with Opus (kimi/minimax/glm/qwen...) 3) use frontman which has all this for FE work github.com/frontman-ai/fr…

Uber's CTO told @LauraBratton5 that AI coding tools—particularly Anthropic’s Claude Code—has already maxed out its 2026 AI budget 📈 “I'm back to the drawing board, because the budget I thought I would need is blown away already,” Neppalli Naga said. theinformation.com/newsletters/ap…

turns out NVIDIA is giving us free model usage for kimi/minimax/glm you name it, its on "Trial" so who knows for how long we get free clanker time

@MatthewBerman true, we are still suffering from him dissing frontman github.com/frontman-ai/fr…

Never get on Theo's bad side. He's now added to my list of people never to cross, along with Elon (re: OpenAI), Palmer (re: Jcal), and Peter Thiel (re: Gawker). Congrats Theo, you're in good company.

@svpino plugging into frontman any of the chinese models brings an experience thats on par with the top models, tbh for a lot of tasks I don't see a major difference anymore. plug github.com/frontman-ai/fr…

Obviously, models are a big deal, but coding harnesses play a huge role in making these models look good. I suspect that you can get the best frontier model out there, put it in a shitty harness, and the experience will be very disappointing. The reverse is also true: put a mediocre model in a strong harness, and it might match the experience that you get from the best agentic coding tools out there. So, yes, Opus 4.6 and GPT-5.3-Codex are amazing models, but the Claude Code and Codex harnesses do a lot of the lifting to make them work the way they are. Of course, these models might also have some specific training on their harnesses. This is also an advantage.

@Y_bareket חי את החלום

זה בסדר אם אני לא מבין בקלוד קוד? שאין לי תיק השקעות? שכשאני שומע אודיובוקס אני מקשיב לפנטזיה, לא למדריכי שיפור עצמי? שאני משתדל להיות פעיל ובריא, אבל כנראה לא אגיע למאה גרם חלבון ביום? שאני אוהב ומחבק את הילדים שלי, אבל לא נלחם מספיק שיעזבו מסכים? שאין לי תכנית לחמש שנים קדימה?

@rotempe4 opencode… ואז פשוט תחליף לאיזה מודל שאתה רוצה, המודלים הסיניים כמו Kimi ממש טובים גם למשימות פיתוח

כל נסיון עבר שלי עם קודקס (קודבייסים קטנים) לא עבד טוב. עדיין הרבה אנשים טוענים שהוא ממש טוב וזה מייצר לי פומו 😆 לקודקס או לא לקודקס, זו השאלה?!

@zeeg In frontman we just spent quite the effort to optimize the agent token usage, I wouldn’t be surprised if it’s more efficient than most harnesses, Claude code in particular

Do yourself a favor and ignore these kinds of takes. "The more tokens I spend the more advanced I am" The people who spend the most on tokens, actually, are generally wasting compute with garbage multi-agent coordinator "experiments". They produce absolutely nothing yet feign they're on the cutting edge. They're not. There is certainly a degree minimum viable usage, but if you do not live in these projects, in these companies, you cannot fathom what the real world looks like. You do not need to consume a thousand dollars a day to achieve the best results. The numbers quoted here, just like the original post, are completely fabricated. Certain tasks will lend themselves to more token consumption (50m+ in a day), while many others will be an order of magnitude less and be just as if not more productive and valuable. Measuring net tokens is no different than measuring net lines of code. Its a garbage metric and does nothing more than show output.