Found 116 bookmarks
Custom sorting
Estimating AI productivity gains \ Anthropic
Estimating AI productivity gains \ Anthropic
(Of course, if you prompt Claude to analyze and criticize this, it heads for the shredder. One issue might be, if humans are not to be only agents, how it plans to develop and deploy them. Can they choose to except? Then again, what came first, the link or the metadata?)
·anthropic.com·
Estimating AI productivity gains \ Anthropic
Prompt Versioning: Best Practices for AI Engineering Teams
Prompt Versioning: Best Practices for AI Engineering Teams
(Strategies for Machine Cognition. AI fits the "and then a miracle occurs" step in the calculation. Somehow this rolls back to the Com/Con and Comms in Cybernetics. Now extending to multimodal and physical. Recent cybersecurity incidents seem to infer that the models can also launch Shadow AI given initial targets and, elsewhere, targeting has already been automated for protection of critical infrastructure. Who is using the electric lunch boxes? In Franklin's day, he only had to contend with Mather and math(s) Now people who buy these datacenters also purchase the adaptive RPGs because they have everybody's voice.. Incidentally Weizenbaum effectively created a generative vision of the Turing bombe originally dedicated to recognition. But AI also has to track algorithmic decision-making in the void.)
·getmaxim.ai·
Prompt Versioning: Best Practices for AI Engineering Teams
Psychologically Enhanced AI Agents
Psychologically Enhanced AI Agents
(Part of a trend toward loading familiar mental models or, in some cases, falling back to behavioral theories. kind of a shrink review or regression after Eliza. Becomes interesting to either test new theories or discover hidden ones embedded in or emergent from the machine models. Again, though, some do not buy the universal or mind-over-matter arguments and expect embodiment to be unique. See who shows up at the beach.)
View PDF
·arxiv.org·
Psychologically Enhanced AI Agents
elvis on X: "Every AI dev should know how to apply everything on this list. From prompting tips to context engineering to metaprompting. Learn it once, apply it everywhere. Check out my new 4+ hrs course (with code examples) to learn more: https://t.co/HFfSgmon2W" / X
elvis on X: "Every AI dev should know how to apply everything on this list. From prompting tips to context engineering to metaprompting. Learn it once, apply it everywhere. Check out my new 4+ hrs course (with code examples) to learn more: https://t.co/HFfSgmon2W" / X
·x.com·
elvis on X: "Every AI dev should know how to apply everything on this list. From prompting tips to context engineering to metaprompting. Learn it once, apply it everywhere. Check out my new 4+ hrs course (with code examples) to learn more: https://t.co/HFfSgmon2W" / X
The Prompt Report
The Prompt Report
(In a recent video, they highlighted techniques: few-shot prompting, decomposition, self-criticism, providing context, and ensemble prompts or models. Still vulnerable to prompt injection or misalignment. Fine-tuning can be safer for specific narrow tasks. Agentic capabilities are a new area.)
·sanderschulhoff.com·
The Prompt Report
‎Gemini - Vibe Coding: Theory and Guide
‎Gemini - Vibe Coding: Theory and Guide
(Ran generic prompt across Consensus, Elicit, and SciSpace for more explicit lit reviews and summaries: Good reference material on morphogenesis after Turing's original paper, current research trends. How is morphogenesis related to AI, e.g. artificial life, robotics, synthetic bio? Both Elicit and SciSpace had framework tables that looked at interdisciplany discussions. These all had Share. That latter ones had PDF SciSpace saved to Notebook. STORM from Stanford is running a study on effectiveness of generating Wikipedia-like articles if prompt is limited to 20 words. Google AI has morphogenesis related to sentience through the brain. All of these are mimicking user style, including textures, which seems ironic. If AGI is approaching, drawing the line is going to be interesting. Have to find a noob to be objective. Else the user may be like Narcissus, and both Echo. The BCI types are going to be fascinating. Is Generative AI going to add morphogenesis twists? What does someone see when they close their eyes? Other search engines like Google Scholar or Sourcely also list titles. Turing had 17370 citations. His middle name was Mathison.)
·gemini.google.com·
‎Gemini - Vibe Coding: Theory and Guide
Andrew Ng on X: "Contrary to standard prompting advice that you should give LLMs the context they need to succeed, I find it’s sometimes faster to be lazy and dash off a quick, imprecise prompt and see what happens. The key to whether this is a good idea is whether you can quickly assess the" / X
Andrew Ng on X: "Contrary to standard prompting advice that you should give LLMs the context they need to succeed, I find it’s sometimes faster to be lazy and dash off a quick, imprecise prompt and see what happens. The key to whether this is a good idea is whether you can quickly assess the" / X
·x.com·
Andrew Ng on X: "Contrary to standard prompting advice that you should give LLMs the context they need to succeed, I find it’s sometimes faster to be lazy and dash off a quick, imprecise prompt and see what happens. The key to whether this is a good idea is whether you can quickly assess the" / X
Planning Anything with Rigor: General-Purpose Zero-Shot Planning...
Planning Anything with Rigor: General-Purpose Zero-Shot Planning...

(How might image generators solve p;problems?
Elsewhere people used to read a lot, courses were gut or food for thought. Now social media is prevalent, so how is that used?
Robots are still unnerving.
In any case, Godel remains, and cybernetics. Where is the determinism? Can any element remotely know another without the direct prompt? Or would that have to become a function of long-term evolution. In which case, what are the competing or environmental factors?
Thiis may become interesting when robots like Optimus are sent on long-range missions such as Mars without humans around and occasionally on comms. How can that be tested more locally ahead of time? Other than by starving them of resources.
Who picks the missions? Scary version.
Perhaps a Tyrell origin story. Old Norse or French.
Who picks Tyrell?
What is the implicit goal?
Incidentally, early on, Minsky reportedly favored tele-presence. Others later looked at expert systems. Assuming they are not hallucinating, machines are also capable of augmented or mixed reality. How do they know the difference? How do people, in either sense? Other than biases.
Or Space Force interns go DOGE versus Delphi mode.
Backtracking through the plan, from results to analysis or methods, how do they pick better questions or problem sets?
Does self-reporting evidence subjectivity? Are there Platonic or universal prompts or are they personalized or localized? Can those be made equivalent through a dictionary? Is this another form of mimicry where the collaborating or training partner or source is then removed? Expecting Enlightenment. At least pattern affinity. Why AI?)

·arxiv.org·
Planning Anything with Rigor: General-Purpose Zero-Shot Planning...
Prompting And Prompt Engineering Facing Notable Changes Due To OpenAI Latest o1 Generative AI Model
Prompting And Prompt Engineering Facing Notable Changes Due To OpenAI Latest o1 Generative AI Model
(The old hidden constraints in new clothing. The user may go in assuming that the app thought of everything only to find out they hit a trap. This flips them to, if it has not been explicitly stated, assume it needs definition. Or a lot of testing. In this case, asking it to be verbose is considered to be against the terms of service since the vendor does not want others cloning models based on its reasoning techniques.)
·forbes.com·
Prompting And Prompt Engineering Facing Notable Changes Due To OpenAI Latest o1 Generative AI Model