Would be more and more useful to have terminal CLI utilities like running a given prompt or agent over a folder. I'd use that for auditing legal compliance for some projects.
I had this idea to rent roofs to install solar panels, building a kind of decentralized power plants. I live in the sunny southern France where summer are starting to become unbearably hot, but at least this comes with a lot of sunpower. There are plenty roofs but sadly we install solar plants in spaces that compete with forest/fertile soil. I am not an energy engineer so that's not a realistic project for me, but are there similar projects around?
I can't agree more, downloading OpenAPI doc for an API and parse it is more than enough to implement the core of MCP. But sadly the buzzword completely took of and for instance all participants to my trainings will ask for MCP, systematically.
The LLM doesn't intervene much actually, it just tells what tool to call. It's your MCP implementation that does the heavy lifting. So yeah you can always shove a key somewhere in your app context and pass it to the tool call. But I think the point of other comments is that the MCP protocol is kinda clueless about how to standardize that within the protocol itself.
My understanding is that it can upgrade to an SSE connection so a persistent stream. Also for interprocess communication you usually prefer a persistent connection. All that to reduce communication overheads. The rationale also is that an AI agent may trigger more fine-grained calls than a normal program or a UI, as it needs to collect information to observe the situation and decide next move (lot more get requests than usual for instance).
Just use a normal static analysis tool and shove the result to an LLM. I believe Anthropic properly figured that agents are the key, in addition to models, contrary to OpenAI that is run by a psycho that only believes in training the bigger model.
I'd say metadata not content so good title and abstract, consistent with book content. Nothing new compared to usual book marketing, AI is a new channel but not that disruptive.
I would tolerate some js to implement dark mode with a class rather than a media query. It allows more control with a toggle if user wants some site dark some light.
Edit: it's covered in the article actually.
It's a relatively new feature, also people need actual professional training to become true LLM developers using them to their fullest and not just developers that happen to call an LLM API here and there. Takes a lot of time and effort.
Talk to engineers, they just fear research papers. It's important to have alternate ways of consuming research. Then maybe some engineers will jump the fence and start taking the habit of reading papers.
LLM running tools in a loop is the core idea of ReAct agents, and is indeed one of the most effective way to extract value from a generative AI. Ironically, it's not about generation at all, we use the models classification skills to pick tools and text processing skills to take the context into account.
That's a problem discussed in the industry. Currently LLM frameworks don't give enough structure when it comes to the agent authorization, sadly. But it will come.
What always bothered me when trying to "feel" Fourier transforms is that to compute the oscillations, you need to wait some time. Mathematically, the transformation includes computing integrals.
So it's tricky to understand how you compute the Fourier decomposition for a stream.
Illustrations always show the whole signal over time but in real life you get the signal progressively.
I'd be eager to read more on this.
"Businesses produced and maintained quality content, Google rewarded the businesses with visitors while diverting some to their ads" that's idealistic, I am happy to see Google algorithm losing its monopoly, even if AI seach ends up being a bubble. When search engines will stop reducing website sorting to some stupid algorithm picked because of scalability while neglecting quality, I will start pity them. By the way this is, again, a low quality short opinion article about AI going to HN front page while not deserving it, it's really an annoying trend.
Yes that's my point, there is a shared budget so at least in some indirect way, the money a Romanian professional makes in another country may end up contributing to Romania's development and growth. I don't have number or what but this has to be taken into account.
Agreed but what I mean is that 15 years ago you wouldn't have thought about studying medicine in East Europe, or building startups etc. And now people study in Romania, Warsaw is perceived as a great place for entrepreneurs and so on. It's just my personal biased impression but it feels good.
"Because Romania is a member state of the European Union, the people the country has put great effort into training and credentialing are easily able to leave the country and acquire jobs elsewhere"
and
"free movement of talent between countries, Romania ends up subsidizing talent discovery for other countries with less apt educational systems"
Are pretty negative stances.
UE is a union, so it's a pretty different situation than students leaving eg third world country to come to Europe. And the migration exists in the other direction, you'll be amazed by how many French dentists are studying in Romania. I hope such phenomenon progressively average the situation between UE countries and closes the gaps that may currently exist.
I think LLM vendors papers entertain such confusions, the lack of peer reviewing tends to favour grandiose but barely defined wording as such. At least author seems to have checked a few papers that do some empirical validation (which is still different from establishing any kind of theory of prompt engineering, there is no other way than cutting the model up to do that).
I don't buy the arguments made here. You can't call it attention optimized without opening the LLM brain and assessing what happens in the attention layers. Does the quoted paper did some of that? I know Anthropic is advanced in this area but I haven't seen that many results elsewhere yet. I mean the fact that optimizing for attention makes better prompt is a solid hypothesis, but I don't read a proof here.
Good read. I just want to pinpoint that LLMs seems to write better React code, but as an experienced frontend developers my opinion is that it's also bad at React. Its approach is outdated as it doesn't follow the latest guidelines. It writes React as I would have written it in 2020. So as usual, you need to feed the right context to get proper results.
An llm on your computer is a fun hobby, an llm in your SME for 10 people is a business idea. There are not enough resources on this topic at all and the need is growing extremely fast. Local LLMs are needed for many use cases and business where cloud is not possible.
Some are asking that yeah but I haven't run an install yet, I am documenting the process. This is a last resort, hosting on European cloud is more efficient but some companies don't even want to hear about cloud hosting.
Yeah I mean you'd want to take a look at the plan to get a bigger picture, it reflects a specific set of values which are not universally shared. This should led to the development of European models, but it feels inefficient to duplicate the work in each country/region just because open source models are planned to be used as trojan horses for values.
"Encourage Open-Source and Open-Weight AI" is the part just after "Ensure that Frontier AI Protects Free Speech and American Values" in America's AI Action Plan. I know this is not rational but OpenAI OSS models kinda give me chills as I am reading the Plan in parallel.
Anyway I like seeing oss model providers talking about hardware, because that's a limiting point for most developers that are not familiar with this layer.
SMEs are starting to want local LLMs and it's a nightmare to figure what hardware would work for what models. I am asking devs in my hometown to literally visit their installs to figure combos that work.