Abdul Munim

@mac_dev9 @trikcode Never used CC but using Sonnet/Opus on Hermes and Opencode a lot. Context window can be tight but I haven't hit a dead wall yet with seriously complex and long running task yet when I use "plan-with-files"

@trikcode Claude is insanely good for long context, architecture, and frontend polish. But Codex is catching up fast on execution speed, debugging, and agent workflows. Using both is probably the real answer now.

Claude code is still better than Codex Prove me wrong

@gitlawb Thanks. it works now. You guys are amazing !!!!

@munim its good now please try again

OpenGateway climbed up to top 16 in OpenRouter global ranking in just a few hours!

@gitlawb I have provided the API key generated to "Authorization: Bearer"

@munim we already required an API key get your api key here gitlawb.com/opengateway

@gitlawb Getting this error with authorization: Bearer ogw_live_xxx {"error":{"message":"API key required","type":"authentication_error","code":"api_key_required"}}

IMPORTANT UPDATE: to give OpenGateway users the best experience we are now requiring API key to be passed in the endpoint. IT WILL REMAIN FREE. just grab API key here gitlawb.com/opengateway

@MaksimXBT @kilocode /plan-with-files do help a lot with low context size

@kilocode 256k context doesn't guarantee good design in 40 seconds

A professional-level landing page. 40 seconds. Less than ten cents. That's what a developer built with Grok Build 0.1, xAI's new coding model, now live in Kilo. 256K context. No output limits. $1 in, $2 out per million tokens. The architect to Grok Code Fast's autocomplete. Hand it the Jira ticket, step back, let it work. Already climbing the leaderboard. kilo.codes/fNLePpH

@iyoushetwt Linux is really good and usable by most people now. This wasn't the case 20-30 years ago when Windows was starting to get on everyone's PC. People started to learn using Windows and companies adapted it and of course Microsoft had money to make sure people adapts to it.

be honest, if Linux is so good why do most people still use Windows?

@bridgemindai Era of open source model will rise.

ANTHROPIC JUST QUIETLY NERFED EVERY CLAUDE SUBSCRIPTION Starting June 15, Agent SDK and claude -p usage no longer counts toward your subscription limits. Sounds like a free upgrade right? It's not. Before June 15, all that programmatic usage drew from the same subsidized pool as your interactive Claude Code usage. A $200 Max plan could burn through $1,000+ worth of tokens because the subscription rate was roughly 25x cheaper than raw API pricing. Now Anthropic is splitting it into two separate pools. Your interactive usage stays the same. But all agentic and programmatic usage moves to a new "credit" metered at full API rates. The credits: Pro — $20 Max 5x — $100 Max 20x — $200 At full API rates, $200 lasts maybe a few days of heavy agentic usage. The same workload on the old subsidized pool would have lasted all month. Anthropic is framing this as "we're giving you free credits." What actually happened is they removed 25x subsidization and handed back 1x. This is the third billing policy change in six weeks. In April they banned third-party agents from subscriptions entirely. Now they reversed that but killed the economics that made it useful. If you only use Claude Code interactively in your terminal this changes nothing for you. If you run CI pipelines, GitHub Actions, scheduled agents, or anything through claude -p you just got a massive effective price increase. The compute arbitrage era is over.

Just tried this with Hermes and works brilliantly. Amazing! Submitting forms, repetitive tasks on web pages are now a breeze.

@0xPrajwal_ How many parallel projects have been continuously running?

We pay $200/month for Claude just to hit the limit in under an hour what are we even paying for??💀

@AriaWestcott Curious about the 8 hours autonomous run. Can you share how you pulled it?

It's really impressive that BytePlus is running full GLM-5.1 at about a fifth of Z.ai's direct pricing. It's the actual model, same weights, sitting on their Coding Plan and working inside Cursor, Claude Code, TRAE and OpenClaw. Holds 8 hour autonomous runs without falling apart, which is usually where these setups start drifting. MiniMax M2.7 is on the same plan for agent workflows that tend to break after a few tool calls. Auto routing covers GLM-5.1, DeepSeek V3.2, Kimi K2.5, GPT-OSS and a couple others, so you're not stuck picking the wrong model for the job. Anyone still paying Z.ai direct should take a look. byteplus.com/en/activity/co… #GLM51 #BytePlus #MiniMaxM27

@sunxliao thanks a lot. Can you share which TradingView indicator are you using? 🙏

Thank you for all your feedback. From now on, I'll be VERY clear about EXACTLY where my trade invalidation is. For $SLNH, it's on a candle close below the 1H gold zone... of course NFA. Same goes for targets... think a reasonable goal is 1D silver resistance labelled in my previous posts. Can see how it's been holding perfectly. More charts incoming!

@SuhailKakar 28 files - large codebase?

ANTHROPIC HAS RELEASED OPUS 4.7!! i asked claude opus 4.7 to refactor a large codebase. 68 minutes, millions of tokens burned - it finished nothing worked. app completely broken but god it was beautiful

@tom_doerr Thanks. I have been looking for a similar screenshot tool like ShareX from Windows. This is exactly what serves my purpose

Native macOS screenshot and screen recording tool github.com/sw33tLie/macsh…

@Ejaz_bashir1 Ckaw

$45,918 profit in 24 hours💰💰 Using only: • A Mac Mini • OpenClaw • One AI prompt. → No trading experience. → No coding skills. → Just automation. This bot runs 24/7 on Polymarket. The results: • ~$50k/day potential • Trades ETH, SOL, XRP markets • 5–15 min market cycles • Fully automated Manual trading is dying. AI trading bots are the new meta. Want the exact set-up? 1️⃣ Like & Repost 2️⃣Comment “Claw” Follow @Ejaz_bashir1 so, I’ll DM you the guide.

@mikeysee @OpenRouter MiniMax is free on KiloCode. KiloCode uses OpenRouter as their inference backend. This could be one driving reason.

hmmm I wonder why MiniMax is being used the most on @OpenRouter right now? Who is using this so heavily?

@m13t_dev @samuel_yostt @karankendre It's kind of a feeling between butter block and butter spread. Opus is still a lot better but MinMax worked on par on my use cases as Opus.

@munim @samuel_yostt @karankendre What do you mean by saying “Minimax is like butter”? Do you mean it feels smoother, more coherent, or more consistent in long coding sessions?

I am using Minimax M2.5 heavily without worrying about the usage limit The Plus plan is all you need It gives 300 prompts per 5 hours which is more than enough for me.

@TamjidulH24v2 Change Bangladesh flag to India beside your name.

Good choice

@samuel_yostt @karankendre I've been trying for past few days and consumed around 15M tokens so far writing code. My feeling is Opus is butter spread and MinMax is butter block. I feel its better than GPT 5.2 and Sonnet 4.5. Give few millions tokens a try in your workflow and see how it fits in.

@karankendre How has the coding quality been? Is it as consistent as opus? I'm on the 100$ plan of claude and have been researching saving costs