Runar Jordahl

[Runar Jordahl @runarj]

@mattpocockuk You are one day late; WWDC was yesterday!

[Runar Jordahl @runarj]

@leodev @theo Is this the most important news from the release of Fable 5? The end of subsidized AI.

[Runar Jordahl @runarj]

@cognition Now, Claude lovers have an eval too. Just like OpenAI fanboys got DeepSWE last week.

[Runar Jordahl @runarj]

@cognition Just like DeepSWE, FrontierCode does not evaluate Anysphere's Composer. I understand evaluation is hard without an API, but it would be very interesting to see the results.

[Runar Jordahl @runarj]

@FlotFyr86 @avec Claude Code desktop has computer use enabled in the EU. So it is possible.

[Runar Jordahl @runarj]

@QuestforYield @OpenAIDevs @OpenAI @EU_Commission @Europarl_EN I can agree... At the same time, @AnthropicAI managed to release computer use in Europe.

[Runar Jordahl @runarj]

@OskarYil @thsottiaux @sama This is probably fixable. @claudeai Cowork has computer use in Europe.

[Runar Jordahl @runarj]

@clauconstantin @zeddotdev @OpenAIDevs No. You only get the Codex harness through ACP.

[Runar Jordahl @runarj]

@zeddotdev Congratulations! I will not update again until you are on 2.0!

[Runar Jordahl @runarj]

Anyone else feeling that @raycast , @zeddotdev and @warpdotdev should merge as one, unified product? #superapp

[Runar Jordahl @runarj]

@andreaskweber @mattpocockuk @thomasdijkstra @MirzaHerdic I am unsure whether checking dependencies as edits happen makes sense. Does it burn too many tokens?

Also, do AI agents really need projects to be structured with dependencies, or will they easily cope with spaghetti architecture? I hope they need structure, as I deeply want it!

[Runar Jordahl @runarj]

@andreaskweber @mattpocockuk @thomasdijkstra @MirzaHerdic I have hooks in Claude Code to verify my Dependency Cruiser configuration. In addition to having architectural layers—UI, domain—I have functional layers in the application. The Contact module should not refer to the Accounting module. You get a matrix of controlled dependencies.

[Runar Jordahl @runarj]

@luongnv89 Thanks for a great app! Would be nice with an option to disable coloring of the text, as with some backgrounds it gets harder to read.

[Runar Jordahl @runarj]

@luongnv89 @warpdotdev I agree. It is really good. I only use the free version, as I have a Claude subscription. They should make a tiny subscription at $5 for the autocomplete to raise some money.

@warpdotdev

[Runar Jordahl @runarj]

@ToivoMattila @dxouix I had the same question. So far Opus has handled conflicts ok. But I intend to also look into Caleiderscope later for manual merge.

[Luong NGUYEN @luongnv89]

https://t.co/hoddQPOerA

[Runar Jordahl @runarj]

@jakehiggins89 @nlw I notice that Gemini 3.1 Pro nearly maxed out the Convex LLM leaderboard https://t.co/ztKJ32ce25

But when evals are maxed out, it usually means they are useless.

Do you think – just like previous Gemini models – this model will be forgotten for coding in a couple of weeks?

[Runar Jordahl @runarj]

@ScatteraAI @alexalbert__ We get a drop in coding skills when upgrading to Opus 4.6. At least if you belive this. My guess is that 4.6 will be an improvement.

[Runar Jordahl @runarj]

@synthwavedd @sama https://t.co/XoLYMul5rA

[Runar Jordahl @runarj]

4.6