And we're just getting started...

New Split View option available from the View menu. Allows up to three side by side columns with all folders and other actions tucked away. Great for working across two or three different folders at once.

The labs have little impetus to make it cheaper... It's a hard sell when token sales are your underlying bread and butter.

After some real time with both, I think we prefer GLM 5.2 to 5.3 for many many tasks. Want this model pinned! It just runs so much cleaner. Less overthinking.

There will always be conflict between those making harnesses and those making models. The labs want the models to be more intelligent and more proactive and burn tokens on the way generating revenue. The harnesses want the models to respond to architecture and not brute force through everything while blowing tokens. Literally every new model release gets a bit more aggressive in how far it will go, which changes how a harness must respond to that model if it cares to keep it contained and not a money pit. The RL training leans on "add" and "solve more" so harnesses are left to fight this behavior as it impacts their interaction quality. It's weird to be involved in. This weird "what IS best?" time. This is where MCP really does win. You can let anyone use whatever model they want for the MCP call, but build your own intelligence behind the MCP that doesn't depend on flavor of the month. You may even pin an older model with RL training that does the job perfectly. Specialists, not generalists. They do one thing well, and that's the entire MCP's job. The user's model then can't really negatively impact it. MCPs should deliver outcomes, not tools.

Yep, that's us!

in 42.1k (22.7k cached) · out 2.7k · $ 0.04 Wow. Just wow sometimes. And because it was GLM 5.3 prioritizing TPS it finished so fast I couldn't read the reasoning. Things are getting close to where the speed vs cost tradeoff is such that there's no value in reading-along / eagle-eying your coding agents. The cost of a mistake is simply a rollback and doesn't eat the more expensive asset, time.

New providers added for GLM 5.3 that really let it cook! 90+ TPS across the board right now.

Wow what a compelling list of reasons to use it...

I believe you're describing GLM 5.2-5.3.

Anthropic completely misses the point Who cares about Fable 5.1 if you burn your weekly limits in a couple of hours I'm sure this model race is not to make users happy but just a signal for enterprises so most of us shouldn't care

Fable proposed "rebranding" a 500 error. Not fix it, not make the state impossible. Rebrand the error. That's all I needed to see.

Token-efficiency-maxxing

And we're just getting started...

Best design skills MCPs?

Normal people do not want to build AI Agents. If I have learned one thing running an AI startup that’s sold and delivered millions in contracts, it’s this. No one cares. No one cares to learn a new mental model. They just want to talk to a thing and get results. They don’t care about agents, skills, connectors or any of the other neologisms we in tech fetishize. They just want the thing to work so they can do something else with their lives. The mistake I see so many companies—and competitors—making is rushing into an ill thought through human computer interaction paradigm where one human manages teams of purpose built agents. I hate that future and we are actively building the opposite at AgentPress. Our ideal is the agents and the neologisms and the gizmos fade into the background and our customers experience AI as a singular ongoing conversation with a chief of staff who also happens to be a mentor, a friend, and a genius. I have always believed the true promise of generative AI is that it radically elevates the quality of our relationships with machines, lowering friction and increasing understanding. I see very few SaaS companies who seem to understand any of this. It is not enough to put a chatbot in your app. If you are not converting your entire company to selling a conversation between your superhuman AI and your customer, you don’t get it. — If this resonates with you and you’re on a sales team of 3-10 people and you’re drowning in follow ups, emails, and CRM updates, we are taking on selected design partners for our AI Chief of Staff for Account Executives.

A harness is everything between a raw AI model and useful work. The model is the jet engine, and the harness is the cockpit: everything between raw thrust and a safe landing. I fly planes. You can buy the same turbofan Airbus puts in an A320, but that won't fly 180 people to LA. The engine is a commodity, but the cockpit is how you harness thrust into a destination. The failure patterns and recovery logic we encode into harnesses for our clients won't show up in an open-source repo, because that's judgment earned from real deliveries, not documentation. The argument that smarter models make harnesses obsolete is a bad take. A more powerful engine needs better avionics, not fewer, and you'll hit orchestration problems only your harness can solve as labs ship smarter models. The harness is where your alpha compounds.

vibecoding made people realize how badass programmers are. Like, imagine doing it without Claude.

Token-efficiency obsessed architecture that treat a model as commodity and the architecture itself as the brain.

We added Underboss to regular chats. This is a simpler version that acts like /goal might on other services, but works to aggressively conserve tokens throughout the run while doing it. Give it a shot! Just tag @ underboss during a chat to let them takeover. For example, here's giving Underboss a sign in bug on a random project to go find. We just told Underboss what the bug was, and it'll run the chat until it's solved.

Despite its name, AI actually doesn't replace your brain. It replaces your hands. If i take the house analogy, AI builds the house, but you need to be the architect. If you let AI design your house too, you'll end up with a toilet in the kitchen.