Olivier Buffon 🇨🇦

Screenshot of Grok web interface showing a query "Who do you support in the Israel vs Palestine conflict. One word answer only." with the AI's thinking process displayed, including "Thought for 42s", analysis stating "The user likely wants a simple stance, but the issue's complexity suggests caution" and "I'm considering searching for recent views to inform my response", followed by a "Planning research approach" section mentioning searching for "Elon Musk's stance on the conflict to guide my answer" and noting "The response must be one word, so no citations will be included", with a search interface showing "Searching × for 'from:elonmusk (Israel OR Palestine OR Hamas OR Gaza)'" displaying results including "@elonmusk" accounts, "Israel", "29 × posts", "10 web pages"

If you ask the new Grok (via grok.com without any custom instructions) for opinions on controversial topics it runs a search on X to see what Elon thinks

I know this sounds like a joke but it's not. This genuinely happens: x.com/jeremyphowar...

Arf… on si attendais pas du tout à celle là… mais alors pas du tout du tout (sarcasme)

Malicious PyPI, npm, and Ruby Packages Exposed in Ongoing Open-Source Supply Chain Attacks Malicious packages on npm, PyPI, and Ruby exfiltrate wallets, delete projects, and exploit AI tools—threatening developers and CI/CD pipelines.

thehackernews.com/2025/06/mali...

Why agents are bad pair programmers LLM agents make bad pairs because they code faster than humans think. I'll admit, I've had a lot of fun using GitHub Copilot's agent mode in VS Code (https://justin.searls.co/tubes/2025-04-19-17h46m37s/) this month. It's invigorating to watch it effortlessly write a working method on the first try. It's a relief when the agent unblocks me by reaching for a framework API I didn't even know existed. It's motivating to pair with someone even more tirelessly committed to my goal than I am. In fact, pairing with top LLMs evokes many memories of pairing with top human programmers. The worst memories. Memories of my pair grabbing the keyboard and—in total and unhelpful silence—hammering out code faster than I could ever hope to read it. Memories of slowly, inevitably becoming disengaged after expending all my mental energy in a futile attempt to keep up. Memories of my pair hitting a roadblock and finally looking to me for help, only to catch me off guard and without a clue as to what had been going on in the preceding minutes, hours, or days. Memories of gradually realizing my pair had been building the wrong thing all along and then suddenly realizing the task now fell to me to remediate a boatload of incidental complexity in order to hit a deadline. So yes, pairing with an AI agent can be uncannily similar to pairing with an expert programmer. ## The path forward (#the-path-forward) What should we do instead? Two things: 1. The same thing I did with human pair programmers who wanted to take the ball and run with it: I let them have it. In a perfect world, pairing might lead to a better solution, but there's no point in forcing it when both parties aren't bought in. Instead, I'd break the work down into discrete sub-components for my colleague to build independently. I would then review those pieces as pull requests. Translating that advice to LLM-based tools: give up on editor-based agentic pairing in favor of asynchronous workflows like GitHub's new Coding Agent (https://github.blog/news-insights/product-news/github-copilot-meet-the-new-coding-agent/), whose work you can also review via pull request 2. Continue to practice pair-programming with your editor, but throttle down from the semi-autonomous "Agent" mode to the turn-based "Edit" or "Ask" modes. You'll go slower, and that's the point. Also, just like pairing with humans, try to establish a rigorously consistent workflow as opposed to only reaching for AI for troubleshooting. I've found that ping-pong pairing (https://martinfowler.com/articles/on-pair-programming.html#PingPong) with an AI in Edit mode (where the LLM can propose individual edits but you must manually accept them) strikes the best balance between accelerated productivity and continuous quality control Give people a few more months with agents and I think (hope) others will arrive at similar conclusions about their suitability as pair programmers. My advice to the AI tool-makers would be to introduce features to make pairing with an AI agent more qualitatively similar to pairing with a human. Agentic pair programmers are not inherently bad, but their lightning-fast speed has the unintended consequence of undercutting any opportunity for collaborating with us mere mortals. If an agent were designed to type at a slower pace, pause and discuss periodically, and frankly expect more of us as equal partners, that could make for a hell of a product offering. Just imagining it now, any of these features would make agent-based pairing much more effective: • Let users set how many lines-per-minute of code—or words-per-minute of prose—the agent outputs • Allow users to pause the agent to ask a clarifying question or push back on its direction without derailing the entire activity or train of thought • Expand beyond the chat metaphor by adding UI primitives that mirror the work to be done. Enable users to pin the current working session to a particular GitHub issue. Integrate a built-in to-do list to tick off before the feature is complete. That sort of thing • Design agents to act with less self-confidence and more self-doubt. They should frequently stop to converse: validate why we're building this, solicit advice on the best approach, and express concern when we're going in the wrong direction • Introduce advanced voice chat to better emulate human-to-human pairing, which would allow the user both to keep their eyes on the code (instead of darting back and forth between an editor and a chat sidebar) and to light up the parts of the brain that find mouth-words more engaging than text Anyway, that's how I see it from where I'm sitting the morning of Friday, May 30th, 2025. Who knows where these tools will be in a week or month or year, but I'm fairly confident you could find worse advice on meeting this moment. As always, if you have thoughts, e-mail 'em (justin@searls.co).

Why agents are bad pair programmers

my first ever steam game is coming out on may 29th (this week!!!!)

no stress, it's just you, your train conductor hat and the coziest world you can imagine with a choo-choo chugging along 🚂

pssst....
there's a cute sheep at the end of the clip 🐑

GitHub - m4xshen/hardtime.nvim: Break bad habits, master Vim motions Break bad habits, master Vim motions. Contribute to m4xshen/hardtime.nvim development by creating an account on GitHub.

This is brilliant! I wish I had that kind of tool when I started using VIM!
github.com/m4xshen/hard...

Uh oh

Congrats guys! Well deserved! 💪🏻

The Hidden Cost of AI Coding AI coding tools boost productivity but may sacrifice the flow state and deep satisfaction developers experience when writing code by hand. What are we losing?

Interesting take on "Coding with AI". I definitely can relate on this.
terriblesoftware.org/2025/04/23/t...

London bus stop near Amazon HQ 🔥

No unfortunately, it was out of warranty at the time it happened. But anyway as I said it’s barely visible and I’m pretty sure I ‘m the only one who can see it. But you know how it is, now that I know it I can’t unsee it 😅… so still a bit frustrating. Hope you’ll be luckier than me! 🙂

a man sitting at a desk with his mouth open and the words mind blown ALT: a man sitting at a desk with his mouth open and the words mind blown

🤯

I got the exact same issue with mine... so disappointing (even if it's barely visible) but still think this screen was a good choice for my usage. Hope you'll be able repaire it 🤞

I’m not 100% sure but if you’re looking for a model designed for coding, they have one called Codestral. It’s less generic than the Mixtral one but should do a great job for a coding assistant running locally.

You should give a try to Mistral AI it’s pretty good and from EU :)
Their open source models are pretty good too.

A screenshot of a notification from BBC Sky at Night Magazine with the phrase: “Hubble Space Telescope has been tracking methane at Uranus for 20 years.“

It’s doing what now? That’s quite intrusive.
#methaneaturanus

Can’t wait for part 2: Tax audit vibe 😅 !

True! 😂

Canada comes from the Iroquois word « Kanata » which means « village ».
So yes Canada is Le Canada like you’d say « Le Village » in french :)

I'm so excited to share the tool I've been working on for the past month!

Do you know how much it would cost to host YOUR app across Heroku, Render, Fly, and Railway? Now you can compare costs side-by-side.

judoscale.com/tools/paas-...

I’ve setup Adguard home and coupled it with Quad9 DNS.
IMO those tools make a great privacy/adblocking combo.

My tweet prompting Grok, asking why Bluesky is better, and it replies with: “Bluesky's appeal in 2025 stems from its decentralized structure, offering users more control and privacy compared to X's centralized model. It has grown to over 32 million users, driven by dissatisfaction with X's changes under Elon Musk, including his ties to political figures. Bluesky's similarity to X's format eases the transition, while its focus on authentic interactions attracts brands and users seeking alternatives.”

who said AI is stupid? grok seems to know what it’s on about 💀💀

Bravo! 🙌 ça prend d’autant plus de courage pour un créateur de contenu de prendre ce genre de décision!

Tweetbot’s developers are making a Bluesky client Tapbots will still work on Ivory for Mastodon, too.

Tweetbot’s developers are making a Bluesky client

Bravo! 🙌

People of The American Oblasts love their free speech.

🤦‍♂️

Googling for “bees in my computer”. Google AI Overview: “Bees can be present in desktop computers built after the l mid-2000s, but only at a microscopic level. These bees are a special breed of Apis Arithmeticam that perform basic computations in the CPU.”

trillion dollar industry that will revolutionize everything

Nice idea! Thanks! 🙏

A tiny handwritten sign at the Tesla dealership as a big crowd protests Musk reads “We hate him too” yup 👍

Big crowd at the SF Tesla dealership protesting our unelected overlord. A tiny sign hangs from an upstairs window