Willy Drucker

@OpenRouter I believe the results! Built an extension for VS Code that allows Claude and Codex to iterate back and forth and the results are mind blowing.

@iAnonPatriot This place looks like Action Park in the making.

Old footage of a 1920s amusement park ride designed to throw people off.. People were built DIFFERENT back then. Lmao

It's extremely similar, I register an MCP server as the "bridge" between Claude and Codex (or other models). Everything communicates back and forth on the bridge. Since AI treats the MCP server as a registration in memory or a tool-call essentially, you can use natural language to communicate on the bridge. There a messaging system included so the models can talk back and forth and even iterate but it needs to be a little more matured. But you can ask pretty much any question for now and expect a response. I had an issue once where Codex couldn't establish an SSH connection to one of my PCs and Claude noticed it was doing something wrong. Without my intervention, Claude reinitiated the bridge multiple times until Codex got it. Was pretty wild to see them talking to each other.

@WillyDrucker @OpenRouter I do something similar in VS Code with Claude Code Extension I ssh connect to my VPS then I call Codex Adversarial Review of all plans and code implementation and have Opus review Codex’s suggestions/improvements to come up with final answers. How would you compare to yours?

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

It actually already works with it! I use an OpenCode harness to help with tool calls and you can put your local IP or remote LLM IP into the settings and it will connect. You can even use OpenCode's free model's like Big Pickle. I didn't expect it to get this much attention, so it has limitations, but does work. Looks like I'll be expanding on this, though the Git is open source. github.com/WillyDrucker/W…

@WillyDrucker @OpenRouter Could that extension be modified to work with locally hosted models? Or even better refactor to a proxy server?

@GetRichGiveBack @OpenRouter Hey there, yes you can. It uses the VS Code extensions (or CLI technically) you've already registered in your .claude and .codex settings. It never touches your keys or tokens those stay within the tools themselves. Basically, the way you already have it set up now.

@WillyDrucker @OpenRouter Hey Willy, thanks for sharing. Question: can I use my Claude and Codex subscriptions or is it API access only? Thanks

@elonmusk I mean, did anyone really buy that COVID came from a fish market one mile from the Wuhan bio lab?

Wow

@ChaseIrons I weigh more than Chase Irons! I weigh more than Chase Irons. 😭*Puts back donut*

I've lost 70lbs in the last 3 years but not for the reason most people think

@henokcrypto Just rewrite your CLAUDE.md using the standard language. "You are a Fable 5 model and senior developer..."

I’m experiencing Fable 5 withdrawal

@mitchellvii The small wins are always fun. 10lbs more on bench, 10lbs more on military. Serves as that angel on your shoulder for days you can't see your toes. Having someone to go with helps too.

I don't enjoy working out not because it's hard but because it's boring. If I could find a way to make working out fun, I think I'd do it more.

@DaveBlundin So much to unpack here. If someone can influence AI results to steer an outcome, they will. If someone can restrict AI usage to force a result, they will. These are not, maybe's, and it's coming to a western civilization near you. TV had its run, AI's turn.

This is one of the most pivotal events in history because of the precedent it sets. Even if it doesn't stick, the cat is out of the bag: the government can now unilaterally decide who gets to use AI. Over the last few days I had fully transitioned to orchestrating with Fable. It initially felt like the cookie jar was moved out of reach. Now after spending the day with Opus, I've accepted just how monumental this is. Being denied the best AI model is effectively the same as being denied future employment.

AI Tip#18: Frontier labs charge you for cache "misses". To simplify, when you change a model from Sonnet > Opus, effort from high > max the session context has be reloaded. If the current session is using 100K tokens and you change, this cache reload or "miss" counts towards usage. All frontier labs charge differently for cache loading, but just be aware of this when switching existing or resuming sessions. You might have noticed that some sessions show you the token usage before resuming and ask to /compact, this is why.

@Amank1412 Pure Speculation. Seeing how Opus 4.8's performance improved as Fable 5's performance went down - likely Fable 5 was on it's own datacenter. They could potentially have an entire datacenter not in use, so I'd say yeah, they're going to get Fable 5 back up pretty fast.

Do we think Anthropic is going to re-release Fable 5 / Mythos?

@omarsar0 On one of their posts they were able to achieve within 1% of Fable results, at half the cost, using non-frontier models.

Even more data to support what I have been talking about. The combination of model intelligence (and this includes human expertise) has a compounding effect unlike anything I've seen. There are too many assumptions that a large general-purpose model will be a one-size-fits-all. I don't buy it. The reality, and the research supports this, is that these different models show different strengths and capabilities. Understanding how to tap into them in combination is a huge unlock. All engineering teams need to be thinking about this more carefully as a strategy going forward. Especially now, given the trends from frontier models in terms of selective access.

@OpenRouter That is just incredible, nice work OpenRouter!

Notably, the budget panel was comparable with Claude Fable 5 in performance. A panel of Gemini 3 Flash, Kimi K2.6, and DeepSeek V4 Pro, fused together, beat solo GPT-5.5 and solo Opus 4.8 outright. And it landed within 1% of Fable 5 while costing roughly half the price.

Since a lot have asked for it, here is the link. You have to have a Claude and Codex (or OpenCode/Local LLM) account of course and enable the "Epic Handshake" option. Allows you to use natural language in your Claude session to initiate a handshake conversation between other AI's like Codex and have Codex actually do the work and reply. marketplace.visualstudio.com/items?itemName…

@_tararais_ @OpenRouter I know, but the CLI is just a little too basic. Nothing wrong with a fast uncluttered CLI, but it has limits. I basically use VS Code as an advanced Claude code management tool at this point.

@WillyDrucker @OpenRouter vs code? xDDD

Hey there, look up WAT321 on Google or even directly in VS Code's extension marketplace. Direct links here. marketplace.visualstudio.com/items?itemName… open-vsx.org/extension/Will… It's more for offloading work right now, so one session is considered the primary, but works between Claude and Codex. Wish I had more time to build this out but if you do have a Claude and Codex account, while in the Claude session you can say things like "Have Codex look into this..." and it will fire up Codex to that (using Codex's tokens) and Codex responds when done.

@WillyDrucker @OpenRouter Extension link?

Great questions and I'm still expanding on it. But for now since the idea is everything flows through one main session using natural language so you don't have to have multiple windows open. So the initiating session and or your natural language determines tie. And yes they can iterate back and forth but that's more advanced, for now it's more for offloading work. From my Claude session "Hey Claude, tell Codex to scrape this website for me." and Codex fires up, does the work, all tokens on Codex and replies when done. But they can actually iterate on a problem which is kind of amazing to see. I just have to build out the messaging system a little tighter and there's only so much time in the day.

@WillyDrucker @OpenRouter When you say iterate back and forth do you mean allowing them to interact and effectively have a conversation with each other or something else? How do you get tie breakers in interactions where they disagree? Who's the authority?

@PavelPenev8 @OpenRouter Oh hey, just saw this! Do a search in VS Code, or even Google for WAT321, but also here's one of many links. MIT license, free. open-vsx.org/extension/Will… If you have any questions let me know. Needs both accounts with both Claude and Codex of course.

@WillyDrucker @OpenRouter I’ve found a similar method very useful and am looking for the best way to automate it. Could you share the extension name if it’s already published?