Nope, it’s a thing called “chain of thought” where the LLM basically recursively invokes itself and outside tools to e.g. think up search terms, get results back, read them, not find it, back to the tank to think of new search terms, another tool invocation, etc.
@patio11
-
LLMs Will Entirely Replace Search Functionality
By
–
LLMs are going to entirely eat that search, FWIW. (To my great edification, as I do that constantly for written and audio artifacts.)
-
Japanese Bureaucracy Status and Talent Selection Impact
By
–
The Japanese government is extremely capable of awarding status to bureaucrats, and historically that gets a lot of Japan's best to select into joining the bureaucracy. Whether that has broadly positive results is a complex topic that I am someone constrained from discussing.
-
Civil Service Incentives and Policy Implementation Failures
By
–
And so our civil service races down an incentive gradient to avoid getting in the paper and avoid the ire of elected officials, who have their own incentive gradient isolating them from policies which they pass.
-
Government Lacks Reward Pathways for Innovation Success
By
–
But we have basically no pathway for rewarding success. Mikey mentions that if you invent Gmail you end up taking home an eight figure award. Not only can we not do that in government (our own choice, to be clear), we can't even seem to award status for success.
-
Civil Service Accountability and Project Management Failures
By
–
You won't be fired as a civil servant, and won't suffer any consequence at all really, if your project is over budget, doesn't achieve goals, and arrives years late. All of that is par for the course; we wouldn't have a civil service left if there were actually consequences.
-
Institutional Reform Paradox: Self-Inflicted Problems and Fraud Tolerance
By
–
Some of the problems are self-inflicted, including due to patches for past iterations of reform against graft, waste, and abuse. It's also very difficult to openly pursue tradeoffs, as nobody wants to be the Optimal Level of Fraud is Non-Zero politician or administrator.
-
Government RFP Process Favors Bidding Over Software Delivery
By
–
Instead we focus on structural issues in e.g. how the government sends out RFPs and gets bids by the usual suspects, who are perfectly adapted to winning bids and don't put that many points into actually shipping software, because the government buys process not outcomes.
-
Government workforce competence and economic outcomes
By
–
Mikey is largely not of POV that workforce competence levels determine outcomes, with the somewhat persuasive argument that the government workforce is so large that it ends up being a sample of general competence levels available in the economy.
-
Government Digital Transformation: Dickerson on Healthcare.gov and Digital Service
By
–
This week on Complex Systems I was honored to interview Mikey Dickerson, probably best known as one of the architects of the healthcare dot gov rescue operation. He also founded the US Digital Service. We discussed government software, procurement, and staffing.