AiAnyTool - Best AI Tools Directory and Artificial Intelligence Software Hub Logo
Loading theme toggle
Real-Time Coverage

AI News Today

Live

4945 stories from 30+ sources, refreshed continuously.

Hacker News LLMLLMs

Hacking Salesforce Sites with an LLM Agent

Article URL: https://www.reco.ai/blog/hacking-salesforce-sites-with-an-llm-agent Comments URL: https://news.ycombinator.com/item?id=48524937 Points: 2 # Comments: 1

Read source article
Hacker News LLMLLMs

Introduction to (Multimodal) LLM-as-a-Judge

Article URL: https://yinghonglan.substack.com/p/introduction-to-multimodal-llm-as Comments URL: https://news.ycombinator.com/item?id=48524584 Points: 5 # Comments: 0

Read source article
Simon WillisonLLMs

Publishing WASM wheels to PyPI for use with Pyodide

The Pyodide 314.0 release announcement (via Hacker News ) includes news I've been looking forward to for a long time: You can now publish Python packages built for Pyodide (or any Python runtime compatible with the PyEmscripten platform defined in PEP 783 ) directly to PyPI and install them at r

Read source article
Hacker News LLMLLMs

Llama.cpp – Run LLM Inference in C/C++

Article URL: https://llama-cpp.com/ Comments URL: https://news.ycombinator.com/item?id=48522662 Points: 2 # Comments: 0

Read source article
Simon WillisonLLMs

luau-wasm 0.1a0

Release: luau-wasm 0.1a0 See Publishing WASM wheels to PyPI for use with Pyodide for details. Tags: lua , webassembly , pyodide

Read source article
Simon WillisonLLMs

Mapping SQLite result columns back to their source `table.column`

Research: Mapping SQLite result columns back to their source `table.column` It would be neat if arbitrary SQL queries in Datasette could be rendered with additional information based on which columns from which tables were included in the results. To build that, we would need to be able to look at a SQL query like select users.name

Read source article
Hacker News LLMLLMs

LLM Token Price Index

Article URL: https://tokenpriceindex.com Comments URL: https://news.ycombinator.com/item?id=48522130 Points: 3 # Comments: 1

Read source article
Simon WillisonLLMs

Statement on the US government directive to suspend access to Fable 5 and Mythos 5

Statement on the US government directive to suspend access to Fable 5 and Mythos 5 Well this is nuts : The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, in

Read source article
Simon WillisonLLMs

OpenAI WebRTC Audio Session, now with document context

OpenAI WebRTC Audio Session, now with document context I built the first version of this tool in December 2024 to try out the then-new OpenAI WebRTC API for interacting with their realtime audio models. Last month OpenAI <a href="https://openai.com/index/advancing-voice-intellig

Read source article
Hacker News LLMLLMs

What Is an LLM Control Plane?

Article URL: https://blog.mozilla.ai/what-is-an-llm-control-plane/ Comments URL: https://news.ycombinator.com/item?id=48508913 Points: 3 # Comments: 0

Read source article
Simon WillisonLLMs

Quoting Andrew Singleton

Jenny owns a crematorium. John’s propane company gives her a $20 billion investment in return for 5 percent of her operation. Jenny throws $10 billion into the incinerator, then pays John $10 billion to buy propane to burn that money to ashes. John reports that his AI investments have generated $10 billion in revenue this quarter and that he owns 5 percent of a $100 billion business. A reporter from &l

Read source article
Hacker News LLMLLMs

Ask HN: Favorite prompts for improving LLM output?

I use Claude Code a lot and GPT 5.5 as well, and find that they are simultaneously extremely useful and also fall into common poor-performance basins. For example, writing performance -- perhaps my biggest issue with them is writing style -- such as well documented stylistic tics (em-dash, it's not x it's y), less commented stylistic tics ("the honest framing", "the earned XYZ"), cryptic and coined jargon, overabbreviation and sentences replaces by arrow constructions (this -> that -> this other

Read source article
Hacker News LLMLLMs

LLM suppliers should offer PR scoped ephemeral keys

LLMs make PRs cheaper to create than to review (many to one relationship).In my case, as a repo maintainer, I usually run my prompts and workflow to review a lot of the code that comes in, and I end up paying for every unsolicited PR.I was wondering: why don't LLM suppliers support ephemeral, PR-scoped usage keys funded by the contributor? Like a review bond.For example: usable only by the maintainer, only for this repo/PR, hard capped at a low $ amount or N tokens, with a short expiry. Enough t

Read source article
Hacker News LLMLLMs

How to Grep Like an LLM

Article URL: https://marcusmichaels.com/notes/grep-like-an-llm/ Comments URL: https://news.ycombinator.com/item?id=48502159 Points: 2 # Comments: 3

Read source article
Hacker News LLMLLMs

Personal Guardian Angel with LLM

Article URL: https://gwern.net/guardian-angel Comments URL: https://news.ycombinator.com/item?id=48501715 Points: 2 # Comments: 0

Read source article
Hacker News LLMLLMs

LLM for the ESP32-S3

Article URL: https://github.com/harmansingh4163-ai/ESP-32-s3-Story-maker-LLM Comments URL: https://news.ycombinator.com/item?id=48500424 Points: 1 # Comments: 0

Read source article
Hacker News LLMLLMs

Chaining LLM and web bugs to Admin

Article URL: https://blog.quarkslab.com/from-prompt-to-pwned-chaining-llm-and-web-bugs-to-admin.html Comments URL: https://news.ycombinator.com/item?id=48498943 Points: 1 # Comments: 0

Read source article
Hacker News LLMLLMs

Don't let the LLM speak, just probe it

Article URL: https://blog.j11y.io/2026-06-10_hidden-state-probes/ Comments URL: https://news.ycombinator.com/item?id=48498283 Points: 41 # Comments: 3

Read source article
Hacker News LLMLLMs

Our workplace LLM mass delusion

Article URL: https://blog.avas.space/llm-circus/ Comments URL: https://news.ycombinator.com/item?id=48498252 Points: 21 # Comments: 2

Read source article
Simon WillisonLLMs

Claude Fable is relentlessly proactive

After two days of experience with Claude Fable 5 I think the best way to describe it is relentlessly proactive . It knows a whole lot of tricks and it will deploy pretty much any of them to get to its goal. I'll illustrate this with an example. I was hacking on Datasette Agent today when I noticed a glitch: a

Read source article
Hacker News LLMLLMs

Every LLM Tool Call Needs an Output Budget

Article URL: https://www.axamy.com/blog/tool-budget Comments URL: https://news.ycombinator.com/item?id=48496230 Points: 2 # Comments: 0

Read source article
Hacker News LLMLLMs

Superficial Beliefs in LLM Decision-Making

Article URL: https://arxiv.org/abs/2606.11016 Comments URL: https://news.ycombinator.com/item?id=48496180 Points: 3 # Comments: 0

Read source article
Hacker News LLMLLMs

Ask HN: What's the best LLM model that on a 24 GB VRAM GPU?

What’s the best model right now that outperforms Qwopus3.6-27B-v2-MTP-GGUF 8-bit on a 24 GB VRAM GPU? Looking for real reviews. I found 4 bit not usable in production. Comments URL: https://news.ycombinator.com/item?id=48494377 Points: 3 # Comments: 3

Read source article
Simon WillisonLLMs

datasette 1.0a33

Release: datasette 1.0a33 This alpha is a significant step on the road to a stable 1.0, finally extending the ?_extra= pattern I introduced in Datasette 1.0a3 to cover queries and rows in addition to tables. That pattern is also <a hre

Read source article