cagz

Exactly. As a software developer, AI has given me more time to tackle higher-order problems. The actual architecture, optimisation, and user experience.

Mathematicians could:

- Continue working on philosophical aspects of the solution and not bothered by whether the solution is known or not. It is not a movie that gets spoiled when the ending is known.

- Or better, demand from AI labs, how they would like to see AI helping them on philosophical aspects.

The article starts interestingly; I like the analogy between cold reading and LLM responses (well, the ones we were getting three years ago). Then it goes on to generalise to the tune of "This new era of tech seems to be built on superstition and pseudoscience" which I think was a conclusion better left to the reader.

We are used to articles, blogs that stayed relevant for years. It is hardly the case with AI, the speed of change is so high that an observation can become stale in a year. This makes it very important for articles to state that the ideas are based on the technology in year X, rather than generalising them as universal truths.

The title feels clickbaity. Direct API, CLI and MCP all have their uses.

Direct access (Curl/own small function): This requires agent to have full understanding of the API spec. Yes, context can be protected using progressive disclosure, but this essentially means agent needing to understand the API again and again, before every use. Also, a typical API spec may or may not be agent-friendly. If there are nuances when calling an endpoint, where do we put these? Into OAS description? Works, but clunky.

CLI: It works beautifully, especially when a 3rd party CLI already exists for a complex backend. Assumes a well documented, agent friendly CLI, most CLIs are designed for human or CI/CD consumption. Talking about MCP taking up too much context, think about agent starting with my_cli --help, and going down through the switches and parameters one at a time to figure out how the CLI should be called. Less of a problem when calling a well know CLI (e.g. aws), but anything more niche (or custom) requires multiple turns to compose the final CLI command.

MCP: Has its issues, but offers an agent-native solution. Everything agent needs to know about a tool becomes available at once. In an enterprise environment MCPs can be served through an MCP Gateway, providing governance and permission management, this is quite contrast against running a CLI that requires agent to have execute permissions in its shell.

A very poor, word-by-word copy of https://mathandai.org

I wish this were a document that clearly described how mathematicians expect AI to behave, rather than how it is misaligned. I can kind of decipher the expectation from the declaration, but it still sounds a bit like "it would be better if AI didn't meddle with mathematics", instead of "we want AI to approach problems like this and that way".

Yes, quite a few uses in prod, main use case being abstracting API access for agents. In our case these are mostly in-house MCP servers, purpose built for the given agent.

Why MCP instead of CLI or agent accessing API directly?

Direct access (Curl/own small function): This requires agent to have full understanding of the API spec. Yes, context can be protected using progressive disclosure, but this essentially means agent needing to understand the API again and again, before every use in that context. Also, a typical API spec may or may not be agent-friendly. If there are nuances when calling an endpoint, where do we put these? Into OAS description? Works, but clunky.

CLI: It works beautifully, especially when a 3rd party CLI already exists for a complex backend. Assumes a well documented, agent friendly CLI, most CLIs are designed for human or CI/CD consumption. Talking about MCP taking up too much context, think about agent starting with my_cli --help, and going down through the switches and parameters one at a time to figure out how the CLI should be called. Less of a problem when calling a well know CLI (e.g. aws), but anything more niche (or custom) requires multiple turns to compose the final CLI command.

MCP: Has its issues, but offers an agent-native solution. Everything agent needs to know about a tool becomes available at once. In an enterprise environment MCPs can be served through an MCP Gateway, providing governance and permission management, this is quite contrast against running a CLI that requires agent to have execute permissions in its shell.

I must mention that we also utilise lazy-loading of MCPs. In use cases where 10s of tools needs to be loaded, only the most common ones are pre-loaded, then agent kernel connects the others as an when needed, and release them after a timeout (in case of long running sessions). This keeps the context lean.

It is BTP, not London Underground, they are not the same thing.

Outages happen. What concerned me most was the time taken for the full resolution (almost 12 hours). I am hoping that root cause analysis promised will look into this as well and how it can be improved.

Is the 1/10+ reduction in memory usage applicable to larger models, i.e. would be possible to run a 200Gb model, by using 20Gb of memory?

I couldn't help noticing on the screenshot that user having direct access to a production database from their laptop :)

My workflow is: - Write the test first, confirm it fails - Write the minimum code to make that test pass - Confirm it is green

Would be nice to see the actual % token/time saving across end-to-end coding sessions over these time periods https://github.com/MinishLab/semble#savings

My observation is that greps and the processing of grep outputs account for only a small portion of overall consumption; I haven't measured this scientifically though.

I like how far mature adulthood goes :) One never gets old.

Getting frustrated by not having RAG solutions able to answer schematic questions such as "how many X are there", I've created DuoRAG: https://github.com/cagriy/duo-rag

It maintains a vector store and a SQL database. While vector store supports usual RAG operations, the ones that require counting, summation, selection are routed to the SQL database.

There is an option to start with an initial schema, or let it discover the schema itself. Then on the day to day use, if a user query cannot be responded, a candidate schema entry is created to be populated on the next backfill run.

So in actual use, user asks the question such as "Give me the list of people who are scientists". If it is not in the schema, LLM suggest checking it later. Backfill runs at night. Next day it can answer the same question without issues.

Nice tech read, but without information about which companies, doing what, just feels way too click-baity.

I found the idea very interesting but put off a little bit by the various details such as face normals etc (have limited knowledge of the topic). Here are few ideas to increase adoption:

- Sample files

- A video of end-to-end process of creating a basic model (perhaps something more complex than a cube) from 3d design to finished artefact.

- Support for STL

- Built-in option to adjust (reduce) face counts

I am a big fan of MAUI, but I'd really wish they fixed existing issues instead of extending it further. 3.9k open issues and counting. I've got 5 open, verified bugs, some from 2023 :(

It is perhaps my eyes, but when I zoom in enough to make it readable, it gets blurry. A higher-res image would be much appreciated. Great idea otherwise.

> No one is formally verifying the result

This might be the case for a hobby project or a start-up MVP being created in a rush, but in reality, there are a few points we may want to take into account:

1. Software teams I work with are maintaining the usual review practices. Even if a feature is completely created by AI. It goes through the usual PR review process. The dev may choose "Accept All", although I am not saying this is a good practice, the change still gets reviewed by a human.

2. From my experience, sub-agents intended for code and security review do a good job. It is even possible to use another model to review the code, which can provide a different perspective.

3. A year ago, code written by AI was failing to run the first time, requiring a painful joint troubleshooting effort. Now it works 95% of the time, but perhaps it is not optimal. Given the speed at which it is improving, it is safe to expect that in 6-9 months' time, it will not only work but will also be written to a good quality.

I understand the argument, and there are some really good points.

My biggest concern would be that adopting the CLI method would require LLM to have permission to execute binaries on the filesystem. This is a non-issue in an openclaw-type scenario where permission is there by design, but it would be more difficult to adopt in an enterprise setting. There are ways to limit LLMs to a directory tree where only allowed CLIs live, but there will still be hacks to break out of it. Not to mention, LLM would use an MCP or another local tool to execute CLI commands, making it a two-step process.

I am a supporter of human tools for humans and AI tools for AI. The best example is something like WebMCP vs the current method of screenshotting webpages and trying to find buttons inputboxes etc.

If we keep them separate, we can allow them to evolve to fully support each use case. Otherwise, the CLIs would soon start to include LLM-specific switches and arguments, e.g., to provide information in JSON.

Tools like awscli are good examples of there LLM can use a CLI. But then we need to remember that these are partly, if not mostly, intended for machine use, so CI/CD pipelines can do things.

I think their intention is not mining your data (easily opt-outable) or hoping that you maintain the subscription after 6 months. It is rather making large open source project maintainers give AI a proper go.

Believe it or not, there are still a large amount of great tech professionals out there who are sceptical about AI. Many tried AI a year ago and has the impression that "It was alright but had limitations". AI came a long way since then, and it is going to improve even faster over the next 6 months. So this is Anthropics invite for you to join that journey.

In turn, of course this fuels the adoption by superstars (maintainers) endorsing the models.

The use of data for model training is a simple toggle, very easy to opt out of during the initial setup.

Also, the end product is open source anyway, so there is no case of IP being leaked into training data. What remains is that they can use, with your permission, the overall coding practices of a great programmer to fine-tune Claude's code and models. As in, how one approaches planning or troubleshooting. Is this a bad thing? Perhaps every maintainer should decide for themselves whether they want to contribute back or not.

Assuming they've got reasonable programming skills. They can simply find an open-source project they are passionate about. Spend time understanding the overall structure. Then pick up an issue raised by the community and prepare a fix as a pull request.

The first PR is unlikely to be merged the next day; however, it sparks lots of productive discussions with the rest of the community, allowing your kid to build a mental model of the project's best practices and sensitivities.

The more he contributes, the more integral he becomes to the community. After gaining enough experience through small issues, they can even consider working on a new feature.

As a byproduct, a great addition to the CV if they are also looking to go commercial.

I don't think this is an AI issue. It is about the terms of use: they don't allow a second account, even if it's intended for ad management. The recommended way is to use Meta Business Manager via the existing account.

Low-quality AI-created PRs that are submitted to open-source repositories are prompted by humans. And those are the same humans who fails to review AI's output properly before submitting (or letting AI submit) as PRs. Let's not blame the tools instead of bad workmanship.

A smaller number of PRs generated by OpenClaw-type bots are also doing so based on their owner's direct or implied instructions. I mean, someone is giving them GitHub credentials and letting them loose.

AI is also allowing the creation of many new open-source projects, led by responsible developers.

Given the exponential speed at which AI is progressing, surely the quality of such PRs is going to improve. But there are also opportunities for the open-source community to improve their response. It will sound controversial, but AI can be used to perform an initial review of PRs, suggest improvements, and, in extreme cases, reject them.

Does the article have a strong marketing vibe? Absolutely Does the research performed move the needle, however small, in theoretical physics? Yes Could we have expected this to happen a year ago? Not really.

My personal opinion is that things will only accelerate from here.

I use the underground frequently. It doesn't really feel like half of it is covered. Where it is available, it works amazingly. I might have been using the other half by sheer luck.

Good idea, after trying it a number of times, it has some downsides. Most calendar applications cannot clearly display 5 minutes past, and the meeting appears to start on the hour visually. One of the attendees ends up dialling in at the hour, and then everyone gets a notification that the meeting has started.

Half of the people who get the notification click "join" without checking. This ends up with a half-populated meeting room. The issue becomes obvious, and somebody says, "Let's dial back in 5 mins", and drops off. Half of the people like the idea and drop off, while the rest decide to stay and chat.

Meanwhile, some of those who dropped off see this as a great opportunity to grab a brew. That inadvertently triggers some water-cooler, kettle-corner chats, and they end up running late for the 5-past. The rest usually get engaged in something else to make use of 5 minutes, and miss 5-past since no new notifications are issued due to the people already chatting in the meeting :)

Great article on reminding the risks of browser extensions. They literally have access to everything within the browser window, from usernames and passwords to bank account details.

Funnily I always tempted by extensions that offer dark more for webpages but never dared to install one.

I do use extensions, but only if they are from well known, respected organisations.

The author was lucky that it was only few compromised social media accounts. It could easily be an empty bank account or stolen identity instead.