Ferran Bonàs

@DanielLockyer KISS 😅

🚀📉

MUST READ! Articulazo!

@carlosredondo @claudeai Estamos igual! He podido terminar tirando del extra. En mi caso no veo reset y no lo he usado tanto para comerme el 100% de la sesión.

@ferranbonas @claudeai No me ha quedado colgada la tarea porque tenía extra-usage, pero vaya robada. Supuestamente habian detectado un bug esta mañana, y habian hecho reset de tokens, pues yo no lo veo

Algo no va bien @claudeai Opus, uso una skill y consume un 17%. Abro otra sesion, uso la misma skill, unico cambio en la fase de planning cambio el input (de extension similar) Cuota 99% ¿Osea gastas 17% en hacer algo, pero la siguiente vez te comes el 82%? No sé Rick...

Hello Opus 4.7 @claudeai Epic fail!!

@DanielLockyer Openrouter too!

Supabase is now big enough that it needs to collect VAT 😅

Great AI insights from @marsbased by Xavi Redó (@xavier_redo). Solid RPI usage in real world projects.

@Teknium I installed gws few days ago and updated the skill. Great to see it in the basecode

We now use the new Google Workspace CLI as our built in Google Workspace skill, much more comprehensive capabilities for all!

@claudeai @davidbaratech 200$ no donaran ni per 30’ 🤣

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale. It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days. Now in public beta on the Claude Platform.

@bcherny @davidbaratech 😅

Starting tomorrow at 12pm PT, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw. You can still use these tools with your Claude login via extra usage bundles (now available at a discount), or with a Claude API key.

@elwatto Prueba Hermes Agent de @NousResearch tanto instalacion como uso mucho mas fàcil.

lazy X, which OpenClaw version should I install: the INSANE, the LIFE CHANGING, or the SCARY?

@Teknium @plastic_lab Please keep it simple. One of the many reasons why Hermes > OpenClaw

Hermes Agent now supports @plastic_lab's Honcho, @mem0ai, @openvikingai, @Vectorizeio's Hindsight, @retaindb, and @ByteroverDev memory systems! Try them now with `hermes update` then `hermes memory setup` We have rehauled our memory system to be much more maintainable and pluggable, so anyone can make their own memory system to build on top of Hermes easily and cleanly with a special class of plugin! Which memory system is your favorite?

@NousResearch @DavidOndrej1 Hermes with Qwen 3.6 Plus @OpenRouter works like a charm!

@DavidOndrej1 Hermes Agent

openclaw is unusable today

Hermes Agent from @NousResearch or OpenClaw from @steipete? I’m testing both. The pace of releases is crazy. Great time to be in tech.

@heyandras @Jean_build How do you change provider so fast? I only see models of current provider.

Be resilient, use @Jean_build. If one provider enshittificated, you just click and you can continue yoloing on another provider. 🤘 ps: I will release a new version tomorrow with huge improvements on Codex And Opencode backends.

@heyandras I’ve found this . So I’m not alone using it

@heyandras Opencode with mimo-v2-pro-free is pretty good!! And fast!

Chat, which one?

@heyandras Same here. Since yesterday it’s completely off. In ~10 min session = 78% usage. Today still happening. Definitely something changed.

Something changed today afternoon. This is 4 prompts. In the last session, I was at 20%, started 4 prompts and in 10 mins I run out of the limits.

Soy muy fan de Cloudflare pero ya no probamos nada nuevo y de hecho estamos de salida a otros providers (que no tienen ni la mitad de funcionalidades) gracias a @LaLiga y el amigo Tebas. Que esta gente limite el acceso a servicios tech TOP es de traca. Pero queda el turismo eh!!

Software horror: litellm PyPI supply chain attack. Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords. LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm. Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks. Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages. Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.