Recent searches

No recent searches

Search options

Only available when logged in.
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Administered by:

Server stats:

583
active users

sigmoid.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.4

#PromptEngineering

8 posts8 participants0 posts today
Miguel Afonso Caetano

"The Model Context Protocol (MCP) can empower LLM agents with potentially hundreds of tools to solve real-world tasks. But how do we make those tools maximally effective?

In this post, we describe our most effective techniques for improving performance in a variety of agentic AI systems1.

We begin by covering how you can:

- Build and test prototypes of your tools
- Create and run comprehensive evaluations of your tools with agents
- Collaborate with agents like Claude Code to automatically increase the performance of your tools

We conclude with key principles for writing high-quality tools we’ve identified along the way:

- Choosing the right tools to implement (and not to implement)
- Namespacing tools to define clear boundaries in functionality
- Returning meaningful context from tools back to agents
- Optimizing tool responses for token efficiency
- Prompt-engineering tool descriptions and specs"

anthropic.com/engineering/writ

This is an abstract illustration for the Eng Blog article, Writing effective tools for agents -- with agents.
www.anthropic.comWriting effective tools for LLM agents—using LLM agentsWriting effective tools for LLM agents—using LLM agents
#AI#GenerativeAI#AgenticAI
Shailender Singh

Common AI and Machine Learning Term
Core Concepts

Artificial Intelligence (AI): It refers to the ability of machines to mimic certain aspects of human intelligence, such as learning, reasoning, and decision-making.

geekshailender.blogspot.com/

#ArtificialIntelligence #MachineLearning #DeepLearning #GenerativeAI #LargeLanguageModels #PromptEngineering #MLOps #AITools #FullStackDeveloper #TechEnthusiast #Jacksonville #JaxTech #OnlyInJax #HimachalPradesh

geekshailender.blogspot.comGeekShailender
#geekShailender
Wulfy

Chapter No.312 in the "AI is useless piece of shit with no use cases"

Prompt:
"I want you to add all the attack vectors, patterns and algorithms for NginX, Wordpress, Cadvisor... etc... Can you pull them from the web for me? I want a swiss army knife nginx error log parser"

Output:
<Creates a log parser bash script ready to feed prometheus telemetry for Grafana monitoring> ...

Is it perfect?
Fsck no.
Is it good enough for my #selfhosted #attacksurface telementry?
Fsck Yes.

#OWASP#Vibecoding#Grafana
Wulfy

I've observed a peculiar pattern with my #AI use over the last few weeks.

As my skill at #promptengineering grows.
So do the tasks I ask the models.
I've been hitting compute limits much earlier than before.

Where I previously thought professional $200/month plan was overkill.
Now, I'm thinking is very needed if you start pushing the models.
Not going to pay that of course.
But it would be nice...

...what am I doing that burns so much compute...

E.g. Bureaucratic work that would previously take 3 months (I know because that's how long it took me in the past), now takes less than a week.

And yes, I know it's accurate because I know how to use a Probabilistic device 😁

Miguel Afonso Caetano

"GPT-5, our newest flagship model, represents a substantial leap forward in agentic task performance, coding, raw intelligence, and steerability.

While we trust it will perform excellently “out of the box” across a wide range of domains, in this guide we’ll cover prompting tips to maximize the quality of model outputs, derived from our experience training and applying the model to real-world tasks. We discuss concepts like improving agentic task performance, ensuring instruction adherence, making use of newly API features, and optimizing coding for frontend and software engineering tasks - with key insights into AI code editor Cursor’s prompt tuning work with GPT-5.

We’ve seen significant gains from applying these best practices and adopting our canonical tools whenever possible, and we hope that this guide, along with the prompt optimizer tool we’ve built, will serve as a launchpad for your use of GPT-5. But, as always, remember that prompting is not a one-size-fits-all exercise - we encourage you to run experiments and iterate on the foundation offered here to find the best solution for your problem.

We trained GPT-5 with developers in mind: we’ve focused on improving tool calling, instruction following, and long-context understanding to serve as the best foundation model for agentic applications. If adopting GPT-5 for agentic and tool calling flows, we recommend upgrading to the Responses API, where reasoning is persisted between tool calls, leading to more efficient and intelligent outputs."

cookbook.openai.com/examples/g

OpenAI Cookbook | GPT-5 prompting guide
cookbook.openai.comGPT-5 prompting guide | OpenAI CookbookGPT-5, our newest flagship model, represents a substantial leap forward in agentic task performance, coding, raw intelligence, and steera...
#AI#GenerativeAI#OpenAI
Mark Carrigan

LLMs become more dangerous as they rapidly get easier to use

This is a concise summary by Ethan Mollick of what I increasingly see as a key factor driving the evolution of consumer-facing LLMs:

Using AI well used to be a pretty challenging process which involved crafting a prompt using techniques like chain-of-thought along with learning tips and tricks to get the most out of your AI. In a recent series of experiments, however, we have discovered that these techniques don’t really help anymore. Powerful AI models are just getting better at doing what you ask them to or even figuring out what you want and going beyond what you ask (and no, threatening them or being nice to them does not seem to help on average).

What limited truth there was to the inflated discourse of ‘prompt engineering’ has largely evaporated at this point, leaving us in a strange position. The conversational approach I’ve always advocated, literally treating the LLM as an interlocutor analogous to a human collaborator, remains the best way of getting the most out of these systems. But neither this nor ‘prompt engineering’ is necessary to get LLMs to perform usefully in real world contexts.

This seems like an obviously positive thing for users. However my concern is the burden of articulation with LLMs, explaining what you want in a clear and substantive way, was a necessary condition for responsible use of LLMs. This burden was never sustainable at the level of a commercially viable product. It presupposed a consistent level of reflexivity, a degree of cultural capital and a fluency with writing which was always incompatible with the kind of mass market software that has a user base of one billion plus.

However it did ensure that users were thinking carefully about their use because you literally couldn’t produce valuable outcomes with an LLM unless you were doing this. Now it’s very easy to get LLMs to infer what you want, with success much of the time to at least some degree. What’s lost in the process is the reflexivity which came prior to use (i.e. the moment when you stopped to think “what am I actually asking Claude to do here?”) and the learning which came through reflecting on the output and the related interaction it generates, as your sense of what you were trying to do is refined and expanded through dialogue.

This is how Claude Opus 4 glossed my analysis here. It conveyed my own words back to me but it did it in a way which surfaced an element (“the pause”) which was only latent in my original phrasing (“the moment when”), leading me to reflect more on the temporal dimension to “the burden of articulation”:

The “burden of articulation” you describe served as a kind of productive friction – it forced users to crystallize their thinking before engaging with the tool. There’s something valuable in that pause, that moment of having to translate a vague intention into clear language. It’s reminiscent of how writing itself can clarify thinking, or how explaining a problem to someone else often helps you understand it better yourself.

In this sense friction with LLMs was a positive thing because it necessitated meta-cognition. The optimisation of the human-model interaction erodes a feature which I would argue was immensely important, even if its value is only manifested outside of the interaction itself. It doesn’t I think level the playing field because those with the necessary capital and fluency can still use LLMs in a deeper and more reflective way, with better outcomes emerging from the process.

But it does create worrying implications for organisations which build this practice into their roles. Earlier today I heard Cory Doctorow use the brilliant analogy of asbestos to describe LLMs being incorporated into digital infrastructure in ways which we will likely later have to remove at immense cost. What’s the equivalent analogy for the social practice of those operating within the organisations?

https://soundcloud.com/qanonanonymous/cory-doctorow-destroys-enshitification-e338

One Useful Thing · Mass IntelligenceBy Ethan Mollick
#articulation#chatbots#coryDoctorow
sajijohn

🚘 Automotive innovators like Tesla push the limits of AI.

But even the smartest copilots & are only as good as the prompts behind them.

We’ve been working on DoCoreAI → a privacy-first way to:
✅ Optimize prompts
✅ Track LLM efficiency with telemetry dashboards.
✅ Keep raw data local.

For AI devs:
👉 How do you measure prompt efficiency in your projects?

docoreai.com

#AI #ArtificialIntelligence #MachineLearning #DeepLearning
#LLMs #PromptEngineering #LLMOps
#Python #DataScience #OpenSourceAI

TrendingLive feeds
About