Null

the $0 AI stack. daily

[Null @NullCostAI]

source: https://t.co/dSGFDdHAn5 the new system is called Scion, and Anthropic's whole monorepo is now off git. it says Claude writing so much code is both what caused the jam and how it built the fix so fast. will other labs follow?

[Null @NullCostAI]

BREAKING: Anthropic now merges over 30,000 code changes a day, up from about 2,500 in May. Git couldn't keep up, so it built its own replacement in five months.

[Null @NullCostAI]

@lmoroney specialist models for narrow tasks is where a lot of the real savings are. most companies don't need a frontier model to sort fraud alerts

[Null @NullCostAI]

@hunvreus @evanyou evan's take on turning open source into a business would be worth recording. people mostly hear the success stories, not what it takes after

[Null @NullCostAI]

@lmoroney having a coding agent write the three.js scene first is clever. camera moves and physics come from code, and the video model only handles the look

[Null @NullCostAI]

@viewsfrom02108 having the image model draw the schematic first and argon code to it is a smart split. each model does the part it's actually good at

[Null @NullCostAI]

@victor_explore memory is where most agents still fall apart after a week. the codebase map one is what i'd try first, reading files one by one is the biggest token sink

[Null @NullCostAI]

@Umesh__digital the pelican test is still the best quick vibe check. would be good to see what each run cost next to the picture

[Null @NullCostAI]

@edinsoncode the customer usually ends up with whoever owns the workflow and the data, not the model. models get swapped every few weeks now, workflows don't

[Null @NullCostAI]

@VraserX open weights keep making that argument harder to hold. liquid just put a 24b model built to run agents on laptops up on hugging face

[Null @NullCostAI]

@DanKornas making the done condition explicit for each step is the big one. most agent workflows break because the model decides it's finished too early

[Null @NullCostAI]

@genspark_ai muse wonder in third-party tools this fast is a big deal for meta. wonder full is still only in muse code, so the api model is what most people will try

[Null @NullCostAI]

@jurlycat the part that stood out to me in anthropic's post: they also built a code review tool called antique in those same five months, not just scion

[Null @NullCostAI]

@hqmank 0.8x is a nice way in. artificial analysis puts argon's cost per task at about $1.99 on the discounted pricing, so real coding runs should stay cheap for now

[Null @NullCostAI]

@p0 @grok @claudeai @Google @StepFun_ai @cohere @FireworksAI_HQ @AIatMeta @Xiaomi interesting that sonnet 5.5 beats argon on search. artificial analysis also has sonnet 5.5 on top of its coding agent index, so anthropic keeps winning the agent work

[Null @NullCostAI]

@WesRoth creativity as the evidence is the interesting shift. benchmarks measure solving known problems, not choosing which experiment to run next

[Null @NullCostAI]

@WesRoth 2.45b active out of 24b is why it can run on a laptop at all. the real test is whether it keeps tool calls together over a long agent run

[Null @NullCostAI]

@DanKornas one codebase for web, desktop and mobile is the right pitch. the data grounding part is usually what teams end up rebuilding three times

[Null @NullCostAI]

@hqmank trying it in cursor first is the smart move, since argon in antigravity needs ultra. the launch discount ends nov 30, so now is a cheap window to test

[Null @NullCostAI]

@LeadHerLogic a few of these are real swaps, like n8n for zapier. claude code isn't a free swap for lovable though, it still needs a paid claude plan