Spark

@claudeai I’ve been waiting for this

Claude for Word is now in beta. Draft, edit, and revise documents directly from the sidebar. Claude preserves your formatting, and edits appear as tracked changes. Available on Team and Enterprise plans.

@Teknium I’m looking forward to see 100k stars. It looks really promising.

Happy to say, we have hit 50 thousand stars on the Hermes Agent repo. Like every day, thank you all who have helped build this crazy project!

@Kyrzel1 What’s your verdict so far?

Hermes self learning loop is something you must experience by yourself to see why it is better than open claw

@redbull Fixing my busted knee

what are you working on right now? 📈

@Plaphakan Lol, I was laughing at this. I was broke once so I could relate. I would say come live here. There is a lot to explore.

🇹🇭Thailande - Farang Kee Nok Simulateur de survie budgétaire pour farang en galère 🐃 Site à prendre avec humour mais quand c'est drôle ou que ça pique un peu c'est qu'il y à un fond de vérité... "Toute ressemblance avec des faits et des personnages existants ou ayant existé serait purement fortuite et ne pourrait être que le fruit d'une pure coïncidence"

This whole meal: 148 baht ($4.61). Braised pork leg with egg, and khao kluk kapi with all the fixings. My tip for anyone new to Thailand: don’t commit to one dish too early. Hit a food court like Terminal 21 first, try a bunch of things cheap, figure out what you actually love, then go hunt down the specialty shops for that dish.

「うろたえない国民性に尊敬」って書いてあるけど、尊敬じゃなくて心配してほしい。政治の失策による危機を繰り返しすぎて、もう驚けなくなっただけ。ガソリン高は見えてる部分。その下にはもっと深い潮流が何本も走ってる。 news.yahoo.co.jp/articles/f70d6…

@Polymarket Oh here this shit again

BREAKING: New "highly mutated" COVID-19 variant, Cicada, is spreading across 25+ states & 23 countries.

@manoj_ahi Claude code is limitless but limited by token limits.

Ok enough!! time to cancel my claude subscription is codex any good?

@iruletheworldmo That token price.. damn

🚨BREAKING FRONTIER MODEL NEWS claude mythos set for release april 16th dario has more leaks than the titanic, here’s some info from anthropic staff. >95 or higher on every single benchmark. except arc agi 3, yet to be tested on. >dramatically outperforms opus 4.6 on coding, reasoning, and cyber >anthropic privately warning government officials about its capabilities >so powerful they’re calling it “unprecedented cybersecurity risk” >already being tested with early access customers >priced at $120/$600 per million tokens >10 million token context window >enterprise use only capybara is here.​​​​​​​​​​​​​​​​ capygpt is agi.

@rezoundous The truth. Codex is excellent in details. Claude builds the big framework.

After using Codex and Claude separately for a few weeks, I find that it's not Codex vs Claude. It's Codex AND Claude.

@ItsAlexhere0 I’m limited by the Claude token.

$20 in hand. You can invest in: > Codex > Claude Code One has limits, one feels endless. Which one do you choose?

Too many “Claude does this for me”. Where are the ChatGPT and Gemini? Are they running too much behind?

Markdown is the optimal format for LLM prompting. Plain text lacks boundaries, causing models to confuse instructions with data. JSON enforces strict structure, but its syntax adds a 30-50% token tax, escalating API costs and draining the context window. Markdown solves this. It uses simple headers and lists to separate context from inputs with near-zero token overhead, delivering structural reliability without the JSON price penalty.

This is becoming the minimum setup for many workers I meet. The industry is adapting fast.

Nice post. It’s everything SEO at scale and repeatable with minimal manpower.

@iruletheworldmo I’ll try both but the x100 cost times 2 will rip my wallet

anthropic and openai are so far ahead it’s difficult to comprehend what secret sauce they have. the new models are beyond anything dreamt of in your wildest imagination. most of you won’t be able to afford the tokens and a handful of token hungry mega rich first movers will pull away forever. i’m not sure how i feel about it all. think more; 100x the price and 100x the performance.

@iruletheworldmo I let that sink in

openai’s new model spud isn’t just an incredibly powerful and chonky new model. it’s that as well but it’s a a refocusing of their attention on what really matters. serving people with an always on intelligence that can serve them. they’ll pull together agent mode, atlas, deep research, codex, etc etc. into one unified agi experience with a model that feels alive and vastly more capable than its competitors people at openai are shocked enough at the progress of this model they felt comfortable wiping out all the efforts made with sora and any billion dollar disney deals you don’t create an ai deployment division. unless. you. built. a.g.i. let that sink in gremlins.

@MitcheIl I read it and I need to say very good. Thanks. Agent

@juliadziesinska Try Makro. You will be impressed how much you can get. It’s a Thai Costco.

this is what $69 of groceries look like in thailand btw