Daniel Royal

[J.B. @VibeMarketer_]

call me crazy but the first AI agent most companies should build is an autonomous analyst.

you can build one using Kimi K3.

it watches your competitors while you sleep, remembers every move, and wakes your team with the launches, pricing changes, and positioning shifts they need to act on.

don't bookmark this if it crosses your timeline.

paste the full article into Kimi and tell it to build the first version for your market.

[Daniel Royal @DanielRoyalhere]

@MarathonTheGame Pls do more PVE and more Lore contracts, I want to solve all mysteries.

[Marathon @MarathonTheGame]

Vault Breaker is Marathon's first experimental PvE mode, set in Cryo Archive. Play as a crew, duo, or solo—no enemy players. Power up across runs with roguelite progression to overcome UESC hordes, vault security measures.... and even the Compiler.

Available July 21 - August 4.

[Daniel Royal @DanielRoyalhere]

@BungieStore Nice, pls do more T-shirts also.
Awesome plush

[Bungie Store @BungieStore]

Marathon Collection [001] WEAVEworm Plush is back in stock on the Bungie Store!

🪱https://t.co/oAKnphKMo3

[CyrilXBT @cyrilXBT]

The man who BUILT Claude Code just sat down and showed how he actually uses it.

Not a tutorial creator.

Not a vibe coder with 3 months of experience.

The CREATOR.

30 minutes of watching him work will restructure how your brain thinks about building with AI.

Most people are using Claude Code like a smarter autocomplete.

He uses it like a second engineering team.

The gap between those two mental models is the gap between shipping toys and shipping products people pay for.

Bookmark this.

Watch it twice.

The second watch hits different once you understand what he is actually doing.

Follow @cyrilXBT for more Claude Code breakdowns the moment they drop.

[Min Choi @minchoi]

3D game dev is about to change forever.

Claude can now talk directly to Unity / Unreal / Blender... so you can build crazy 3D scenes + game with just prompts.

3 MCPs to try this weekend. Bookmark this.

1. Blender MCP

[Marathon @MarathonTheGame]

//MARATHON ALPHA TEST//

Join Senior Design Lead Lars Bakken, as he runs Tau Ceti with @bearki and @HiddenXperia.

RUN 🏃‍♂️

//ACCESS_POINT_1: https://t.co/R0uqdUj08i
//ACCESS_POINT_2: https://t.co/U3qqa8si6h

[Andrew Ng @AndrewYNg]

Tool use, in which an LLM is given functions it can request to call for gathering information, taking action, or manipulating data, is a key design pattern of AI agentic workflows. You may be familiar with LLM-based systems that can perform a web search or execute code. Some of the large, consumer-facing LLMs already incorporate these features. But tool use goes well beyond these examples.

If you prompt an online LLM-based chat system, “What is the best coffee maker according to reviewers?”, it might decide to carry out a web search and download one or more web pages to gain context. Early on, LLM developers realized that relying only on a pre-trained transformer to generate output tokens is limiting, and that giving an LLM a tool for web search lets it do much more. With such a tool, an LLM is either fine-tuned or prompted (perhaps with few-shot prompting) to generate a special string like {tool: web-search, query: "coffee maker reviews"} to request calling a search engine. (The exact format of the string depends on the implementation.) A post-processing step then looks for strings like these, calls the web search function with the relevant parameters when it finds one, and passes the result back to the LLM as additional input context for further processing.

Similarly, if you ask, “If I invest $100 at compound 7% interest for 12 years, what do I have at the end?”, rather than trying to generate the answer directly using a transformer network — which is unlikely to result in the right answer — the LLM might use a code execution tool to run a Python command to compute 100 * (1+0.07)**12 to get the right answer. The LLM might generate a string like this: {tool: python-interpreter, code: "100 * (1+0.07)**12"}.

But tool use in agentic workflows now goes much further. Developers are using functions to search different sources (web, Wikipedia, arXiv, etc.), to interface with productivity tools (send email, read/write calendar entries, etc.), generate or interpret images, and much more. We can prompt an LLM using context that gives detailed descriptions of many functions. These descriptions might include a text description of what the function does plus details of what arguments the function expects. And we’d expect the LLM to automatically choose the right function to call to do a job.

Further, systems are being built in which the LLM has access to hundreds of tools. In such settings, there might be too many functions at your disposal to put all of them into the LLM context, so you might use heuristics to pick the most relevant subset to include in the LLM context at the current step of processing. This technique, which is described in the Gorilla paper cited below, is reminiscent of how, if there is too much text to include as context, retrieval augmented generation (RAG) systems offer heuristics for picking a subset of the text to include.

Early in the history of LLMs, before widespread availability of large multimodal models (LMMs) like LLaVa, GPT-4V, and Gemini, LLMs could not process images directly, so a lot of work on tool use was carried out by the computer vision community. At that time, the only way for an LLM-based system to manipulate an image was by calling a function to, say, carry out object recognition or some other function on it. Since then, practices for tool use have exploded. GPT-4’s function calling capability, released in the middle of last year, was a significant step toward general-purpose tool use. Since then, more and more LLMs are being developed to similarly be facile with tool use.

If you’re interested in learning more about tool use, I recommend:
- Gorilla: Large Language Model Connected with Massive APIs, Patil et al. (2023)
- MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action, Yang et al. (2023)
- Efficient Tool Use with Chain-of-Abstraction Reasoning, Gao et al. (2024)

Both Tool Use and Reflection, which I posted about last week, are design patterns that I can get to work fairly reliably on my applications — both are capabilities well worth learning about. In the future, I’ll describe the Planning and Multi-agent collaboration design patterns. They allow AI agents to do much more but are less mature, less predictable — albeit very exciting — technologies.

[Original text: https://t.co/gHCOYSsKQO ]

[KLOUD @weareKLOUD]

DISCIPLE EP
APRIL 5
Are you in?

[Destiny 2 @DestinyTheGame]

It's been an intense Guardian Games All-Stars, with the results coming right down to the wire. And the winner is... 🥁

🏹 Congratulations Hunters for winning Guardian Games All-Stars!

[LUCKYY10P @LUCKYY10P]

HUNTERS have won Guardian Games 2024

[Daniel Royal @DanielRoyalhere]

@PaulTassi Ok, then try Alan Wake II

[Daniel Royal @DanielRoyalhere]

@thegameawards Alan Wake II

[NVIDIA GeForce @NVIDIAGeForce]

Enter the Dark Place for a chance to win🔦🌃

To celebrate Alan Wake 2 and its official release w/ full ray tracing + NVIDIA DLSS 3.5 w/ Ray Reconstruction, we're giving away a NVIDIA GeForce RTX 4090 with a custom @AlanWake backplate.

To enter:
🟢 Like
🟢 Comment #RTXON

[Mr. Money Lesson @mrmoneylesson]

SUCCESS REQUIRES REPLACEMENT:

Alcohol —> Water
Netflix —> Reading
Overthinking—> Action
Scrolling —> Exercise
Complaining —> Gratitude
Toxic Friends —> Mentors
All-nighters —> Sleep
Blame —> Accountability
Fast food —> Homemade food

[Dolby Games @DolbyGameDev]

We’re excited to officially announce we are working with Audiokinetic to create a deeper integration of #DolbyAtmos into the Wwise pipeline, making workflows easier for developers to add new dimensions to their games.
https://t.co/qbehJFDHBS

[PlayStation @PlayStation]

Announcing the PlayStation Plus Game Catalog lineup for March, which includes:

➕ Tchia
➕ Uncharted: Legacy of Thieves Collection
➕ Ghostwire Tokyo
➕ Tom Clancy’s Rainbow Six Extraction
➕ Immortals Fenyx Rising

…and many more. The full lineup: https://t.co/cgFSSiPVbV

[Paul Tassi @PaulTassi]

DRIFTER: A “Veil”? Been haulin’ this thing around all this time and never thought of a fancy name for it. Why, you need a spare?

[Destiny 2 @DestinyTheGame]

Get locked, shocked, and loaded. ⚡

Brand new Arc-themed armor ornaments are available right now at the Eververse.