The "Confident Idiot" Problem  ## Metadata - Author: [[The Changelog: Software Development, Open Source]] - Full Title: The "Confident Idiot" Problem - Category: #podcasts - URL: https://share.snipd.com/episode/3ce014c6-bd4f-4b13-87af-4d4de6493ddb ## Document Notes ## Highlights - **Probability Can't Fix Probability** - Relying on one LLM to check another creates circular validation and fails when models share biases. - Treat agents as software with rules and interception, notacles of vague 'vibe' checks. Transcript: Jerod Sant The confident idiot problem, or why AI needs hard rules, not vibe checks. If you've been following the how do we actually use AI in production conversation stream, you've probably heard people propose a strategy where one LLM checks another LLM's results. But will that work? Quote, we are told to ask GPT-40 to grade GPT-3 We are told to fix the vibes, but this creates a dangerous circular dependency. If the underlying models suffer from sycophancy, which is agreeing with the user, or hallucination, a judge model often hallucinates a passing grade. We are trying to fix probability with more probability. That is a losing game. End quote. One possible way of dealing with these confident idiots we've introduced into our software stacks the last few years is to stop treating agents like magic boxes and start treating Them like software. Hence, the Steer SDK was created. Quote, Steer is an open source Python library that intercepts agent failures such as hallucinations, bad JSON, PII leaks, et cetera, and allows you to inject fixes via a local dashboard Without changing your code. ([Time 0:00:34](https://share.snipd.com/snip/c6ec897e-8bc0-495b-be76-bc2cdab6f912)) - **Bun Team Joins Anthropic** - Anthropic acquired the Bun team despite Bun being open source, highlighting the value of engineering talent. - Jerod suggests Anthropic wanted the Bun team's expertise more than the code itself. Transcript: Jerod Sant Bunn is joining Anthropic. The company behind Bunn, which is the open source runtime for CloudCode, is joining Anthropic. We discussed the big acquisition slash aqua hire on last week's Friends episode, but at the time, I hadn't quite considered this move and how contrary it is to Anthropik's party line That AI agents are replacing software engineers. From Anthropik's announcement, quote, we've been a close partner of Bun for many months. Our collaboration has been central to the rapid execution of the CloudCode team, and it directly drove the recent launch of CloudCode's native installer. We know the Bun team is building from the same vantage point that we do at Anthropic, with a focus on rethinking the developer experience and building innovative, useful products. End quote. Bun is open source. Why not just fork it and have a Cloud Code-powered engineer make all the necessary changes and upgrades to the runtime that Anthropic needs. Perhaps because there's no getting there from here. At least not yet. Jared Sumner and the Bun team's expertise is what's so valuable. ([Time 0:01:55](https://share.snipd.com/snip/233039cf-26e5-4396-898e-5751d4a28f7d)) - **Claude Can't Recreate Space Jam** - Jonah Glover tried to recreate the 1996 Space Jam site with Claude Code and repeatedly failed. - The experiment showed the model anchored to its own outputs and confidently produced wrong layouts. Transcript: Jerod Sant Claude can't recreate classic Space Jam site. Jonah Glover tried to recreate everyone's favorite 1996 website by giving Claude Code, which is running Opus 4.1, a screenshot of the site and all the associated assets. It failed repeatedly in all the ways I would expect from my own front-end and design attempts with the tool. Jonah's finding, which is quite relatable, quote, once Claude's version existed, every grid overlay, every comparison step, every precise adjustment was anchored to his layout, Not the real one. At the end of all of this, I'm left with the irritating fact that, like many engineers, he's wrong and he thinks he's right. What this teaches me is that Claude is actually kind of a liar, or at least Claude is confused. However, for the drama, I'll assume Claude is a liar, end quote. I've been giving Claude Code a lot of props lately, but I've also been giving it a lot of tasks that it can't quite accomplish. This process starts off as fun and interesting, but each time it ends in failure, I am perplexed by all the possible failure paths. Was it me and my prompting? Was it the agent? Was it the model? Or perhaps I'm asking for things that aren't easily accomplished with today's tech. I can be quite demanding. ([Time 0:03:00](https://share.snipd.com/snip/2c683b83-0fe5-45a9-a1ef-c2eb67ab7856)) - **Google Unkills JPEG XL** - Chromium reversed its earlier decision and will support JPEG XL in Blink, which may push the format toward ubiquity. - Browser vendor choices still strongly influence web standards adoption. Transcript: Jerod Sant Google unkills JPEG XL. Quote, in a dramatic turn of events, the Chromium team has reversed its obsolete tag and has decided to support the format in Blink, which is the engine behind Chrome, Chromium, and Edge. Given Chrome's position in the browser market share, I predict the format will become a de facto standard for images in the near future. ([Time 0:05:25](https://share.snipd.com/snip/d2267503-6afa-4784-b564-d07e1ddb9461)) - **Gaming Drives Linux Momentum** - Linux gaming is growing, with Steam on Linux usage and distros focused on gamers gaining traction. - Bazite tailors Fedora for gaming with Steam preinstalled and tweaks for HDR, VRR, and streaming. Transcript: Jerod Sant If the mythical year of the Linux desktop is ever to materialize, it will first be preceded by a sea change in gaming options for the venerable open source OS. The gaming sea change appears to be in full swing with Steam on Linux hitting an all-time high of over 3% usage last month. Enter Bazite, a Fedora-based Linux distro that's hyper-focused on making gaming awesome. Quote, Bazite is designed for Linux newcomers and enthusiasts alike with Steam pre-installed, HDR and VRR support, improved CPU schedulers for responsive gameplay, and numerous Community-developed tools and tweaks to streamline your gaming and streaming experience. End quote. The project began back in 2023, but it appears to be maturing and aiming at sustainability by setting up ways to donate with its latest update. Quote, as Bazite matures, we begin to tackle more ambitious projects such as proper secure boot, support for more handheld devices, and conference attendance, which means more costs For us. And we would gladly appreciate the help in covering them. ([Time 0:06:04](https://share.snipd.com/snip/8a86b624-3c79-406e-b091-c12c02435eab))