Translation

TaxCalcBench: An open source eval for testing if AI can file taxes

TaxCalcBench is an open-source evaluation benchmark designed to test whether AI systems can accurately prepare and file tax returns, providing a standardized way to assess AI tax filing capabilities.

Background

TaxCalcBench is an open-source benchmark (evaluation framework) from Column Tax, a US tax-preparation startup. It tests whether AI models can correctly prepare basic federal tax returns by providing W-2s, 1099s, and other common forms, then checking the resulting 1040 against ground-truth answers. The project is a direct response to claims that large language models (LLMs) are ready to replace human tax preparers — early results show most models fail even simple cases. This matters because tax filing is a high-stakes, regulation-heavy domain where errors carry real consequences, and the benchmark reveals how far AI is from being reliable for this task.

RT Max Weinbach: I had early access to this model and I'll post more Thursday, but I think the most impressive part is this model NEVER GIVES UP If yo...
9.0
Max Weinbach says he had early access to OpenAI's new model GPT-5.6 Sol, calling it his favorite model by far. He highlights that it never gives up and will keep reasoning until it's done. OpenAI announced that GPT-5.6 Sol, along with Terra and Luna, will launch publicly on Thursday, with preview access expanding globally now.
Statement on the US government directive to suspend access to Fable 5 and Mythos 5
9.0
The US government ordered Anthropic to suspend access to its Fable 5 and Mythos 5 models for all customers, citing a potential jailbreak technique that involved asking the model to review a codebase for vulnerabilities—a capability Anthropic says is available in other public models. Access was abruptly cut off on June 12.
This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's ...
9.0
Andrej Karpathy announces the release of Claude Fable 5, the same underlying model as Mythos but with added safeguards. He calls it a major step forward, particularly for long problem-solving sessions on difficult tasks, and describes it as state-of-the-art on nearly all benchmarks with exceptional performance in software engineering, research, and vision.
RT Roman Storm 🇺🇸 🌪️: The gov't theory in my case isn't about me. It's a template. Under US v. Storm, "money transmitting" no longer require...
8.5
Roman Storm warns that the legal theory in his case could set a precedent making open-source developers liable for how others use their code, potentially criminalizing the mere publication of privacy, messaging, or crypto tools. He notes that developer Michael Lewellen cannot publish lawful code due to prosecution fears, and argues this chilling effect extends beyond any single case.
‘Why Is Meta Destroying Its Engineering Organization?’
8.5
Meta's engineering culture is deteriorating under Mark Zuckerberg and Scale AI CEO Alexandr Wang, who have introduced keyboard tracking, reassignments to data labeling, and AI-centric performance metrics. Critics argue this incentivizes performative AI use, drives away experienced engineers, and contributed to a major Instagram hijacking incident caused by AI-written and AI-reviewed code.

TaxCalcBench: An open source eval for testing if AI can file taxes

Background

Related stories

RT Max Weinbach: I had early access to this model and I'll post more Thursday, but I think the most impressive part is this model NEVER GIVES UP If yo...

Statement on the US government directive to suspend access to Fable 5 and Mythos 5

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's ...

RT Roman Storm 🇺🇸 🌪️: The gov't theory in my case isn't about me. It's a template. Under US v. Storm, "money transmitting" no longer require...

‘Why Is Meta Destroying Its Engineering Organization?’