I've had some success with using a more expensive model to plan a decent work breakdown structure in a document and then a low-cost model to implement the plan and keep following-up, but wonder about subsequent need for code review and code quality.
Can a lower-cost model verify completion? Iff tests and test coverage and e2e tests?
The same oracle / model routing and partitioning problem
> Chat responses can now render interactive Mermaid diagrams with the renderMermaidDiagram tool. This lets models use flowcharts, sequence diagrams, and other visualizations to visually break down complex concepts. The diagrams are interactive, so you can pan and zoom to explore them in detail, or open them in a full-sized editor for easier viewing.
> If you are disabled, and you want to share your experience in FLOSS communities or have accessibility issues in GNOME or other FLOSS software, report the issues and/or post about them on social media under #AccessibilityInFreeSoftware
> If you are a contributor, see if you can tackle one of the roughly 450 open issues that are labeled with “Accessibility” this month.
> Groundtruth — a Claude Code plugin that audits whether an agent actually did what it was asked; catches the false 'Done' on Stop (missed subtasks, stubs, false 'tests pass', overridden rules).
Which other agent IDEs does or could this work with?
I also find myself exercising verbal skills possibly unnecessarily (with a language learning app that's certainly not immersion) but probably predictably.
I've heard that they say to exercise mental arithmetic skills if stranded on a desert island with no reading material; and that it's normal to develop self dialogue in solitary
- Is there a suggested bibtex citation for this analysis?
- BibTeX in git for the data and the estimates can be referenced with citation identifiers with various static site build tools. Schema.org/Dataset and ScholarlyArticle JSON-LD is probably easier with React. It should be possible to generate BibTeX from JSON-LD (e.g. with citeproc-js and n3.js or rdflib.js or solidjs/react-solid-state or a different RDFJS solution that can template BibTeX).
- DVC is one way to check data into git, and to evaluate sensitivity to data quality and specificity
Additional features probably worth tracking:
- Zero Water facility?
- Types of thermal fluid in use: Water,
- Heat recovered : Heat and water forfeited to evaporative cooling
> to newer servers as expanded memory alongside servers’
local memory (e.g., DDR5 DIMMs). This approach offers a
compelling combination of benefits: near zero-cost memory
expansion through recycling, performance gains from higher
memory capacity, and a reduced carbon footprint.
Circularly recyclable chips would increase the liquidation value of existing AI datacenters.
AI datacenters are angering people; cooling tower wash in the paltry remaining water pressure, loud hum, emissions from generators, steam for dumb cooling that's not zero water for example.
When the malarky hits the fan for some of these oversold AI companies, will there be constraints defining what is an acceptable AI datacenter?
IIUC, hot plasma sterilizes water with hydroxyl free radicals and cold plasma sterilizes water with hydroxyl free radicals.
Air is about 78% Nitrogen. We use plasma, Haber-Bosch, and Biological Fixation to convert Nitrogen in air and water into Nitrates that plants can use.
Is there research on which method of production of fertilizing nitrates is most energy efficient?
I have a Chitosan-Alginate geotextile water bag concept where the geotextile is treated with Magnesium so that it will form Struvite. This one is from a chat called, "Multifunctional biochemical matrix"; https://github.com/westurner/sustainablefactory/blob/main/do...
I tried to add headings to the chats to make them something. But I just found what look like better tools for backing up chats, and also OpenInference and SIOC specs for archiving and indexing LLM chats.
Remote debugging and post-mortem debugging support might be useful.
There are many AI auditability proxies;
awesome-auditable-ai: "A curated list of papers, tools, datasets, benchmarks, and standards for building, evaluating, and auditing reliable AI agents" https://github.com/yzhao062/awesome-auditable-ai
https://westurner.org/
These comments are publicly archivable and logged: https://westurner.github.io/hnlog/
[ my public key: https://keybase.io/westurner; my proof: https://keybase.io/westurner/sigs/3t_WnYf465hEbUSdwjMXGIeLieAd_81SDYQUdDUMsI4 ]