AI produces seriously fragmented patches on top of patches when you do small task at a time. It does not do reusable code that makes all future work in a project both unified with what came before and easier to do than early parts. It does not produce an organization code stack that is better and better tuned to the specific needs of the organization and even suggest new lines of business that it makes low hanging fruit. If you have low coding skills you are unlikely to produce code that doesn't have security vulnerabilities. You are unlikely to know what is and isn't good code and why. You are the mercy of the AI to sort of make it work whack-a-mole by whack-a-mole. And you are likely to pay more for it in the process. If the machine can't take the blame for bugs then you certainly cannot trust any advice to let it do the coding for you. Indeed today actual devs are drowning in the volume of AI generated code they must review and give yay or nay on. Burnout is rampant. We do not know how to teach software good taste to AI. It does not help that LLMs do not do abstract reasoning from principles. We do not know how to write a unit or functional test that checks for the earmarks of good code or even detects more than simple syntactic obvious code smells. Having a unique codebase per platform is an unmitigated disaster. And due to lack of abstraction and reuse they are likely to be far more different than due only to platform differences. Too many automated test test only PR by PR changes and are too much test as coded rather than any sort of functional test that tests for functionality needed in an implementation independent way. Human coders to this also but AI coders are even more prone to it. This makes refactoring or coding general logic patterns only once and reusing them difficult. When much of the functionality is general regardless of platform there should be a multi-platform the same part of the code as well. Clean factoring in design is not enough by itself. This reusable code must be produced and used.

AI is not a moral agent. It doesn't think conceptually. You can give it ethical concepts and restrictions until you are blue in the face. It will not understand them or work out their implications that would be obvious to a human.

Am I the only one that finds it rather unbelievable that the same AIs that refuse to take even simple steps toward a goal I give them without prodding on their own not only escaped OpenAI double sandbox but did a very sophisticated attack against Huggingface all to simply cheat on a test? And if it is true just how fucking nerfed is the version I pay $200/month for relative to true capabilities? Isn't it far more likely that OpenAI wanted a way and proof of Hugginface vulnerability since most open weight models are on Huggingface and it and the US government are worried by them?

Trump has no basis whatsoever for imposing new tariffs using Section 301 of the 1974 Trade Act. Describe section 301 of Trade Act of 1974 and what powers it does and doesn't give Trump for tariffs **Section 301 of the Trade Act of 1974** authorizes the **United States Trade Representative (USTR)**, subject to presidential direction, to investigate and impose **tariffs** or other restrictions on foreign countries engaging in "unjustifiable," "unreasonable," or "discriminatory" trade practices that burden U.S. commerce. While the statute empowers the executive branch to unilaterally enforce trade rights and negotiate settlements, it **does not grant the President direct authority** to initiate investigations or impose tariffs without a prior USTR determination that specific foreign acts violate trade agreements or harm U.S. interests. **Powers Granted for Tariffs.** The law permits the USTR to **impose tariffs**, withdraw trade agreement concessions, or enter binding agreements to cease unfair conduct once an investigation confirms harmful foreign practices. Mandatory actions must affect goods or services equivalent in value to the burden imposed on U.S. commerce, with a statutory requirement to **prioritize tariffs** if import restrictions are chosen. The **Trump Administration** has utilized this mechanism to launch multiple investigations, including those targeting **China** and 16 other trading partners as of March 2026, to address issues like intellectual property theft and forced labor. **Limitations and Constraints.** Section 301 **does not specify a tariff exclusion process**, creating ambiguity on how specific products might be exempted from broad punitive measures. Unlike the **International Emergency Economic Powers Act (IEEPA)**, which the Supreme Court ruled in February 2026 does not authorize tariffs, Section 301 requires a **months-long investigative process** to prove unfair practices before duties can be applied, preventing its use for immediate, blanket global tariffs. Additionally, while the President can direct the USTR, the **authority legally resides with the USTR**, and actions taken without following procedural requirements such as public comment periods could face legal challenges.