Posts tagged: llm

Programming Still Sucks. — Writing Sorry Peter. — I'm at a birthday party, and while most people here also work in tech, there's always a Guy with a Real Job. You know, a physical job, building some or other thing people need. And... stvn.sh [1] Absolute banger of a post, this is the time we are living in. Explain “are you afraid AI is going to take your job” to a non tech blue collar worker. Broken over promises, greed, and projects mismanaged by leadership who has no idea what the day to day work actually does and how critical it is. I’m not quite in Sara’s position, but I feel something shielded by half of this working deep inside of a non tech part of a non tech company leading a very small rag tag team with get shit done attitude. But I feel it, I see colleagues hit by these blasts.b I get clipped with shrapnel from some of the largest blasts. But nothing as significant as I see many others hit with Note This post is a thought [2]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://www.stvn.sh/writing/programming-still-sucks-fqffhyp [2]: /thoughts/

- Casey had an interesting point here. I think demitri came back with some sense of sanity that its just not how corporations look at employee cost, but I still thought it was a head scratcher. Roughly translated not quoted If the sellers of ai are telling you that your developers are going to be 10x productive, why are they only spending half their salary in tokens? Why not 9x? Note This post is a thought [1]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: /thoughts/

- I hate how he called out terminal user interfaces as shit… then proved web interfaces to be superior. Damn him. I love working from my terminal, but having ai prove itself through html [1] reports including video, image, metrics, charts, and text is goated. Rethinking yourself has the bottleneck not the orchestrator feels real. Validating the work is hard, theres a shift right now and everyone is trying to figure it out. Lucas’s technique is a little bit of be lazy and tell it to prove itself to you, so as you juggle your 15 agents you have a nice report to read. Note This post is a thought [2]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: /html/ [2]: /thoughts/

- This is a really good guide, with quite a few good nuggets. I need to try deleting my AGENTS.md and rebuilding it from scratch more often. I liked how he talked about having agents prove their work and tell them up front how they will be judged. What I didn’t care for so much was the feeling that a lot of the rules go in markdown, thats not a rule, thats a suggestion. Rules should be deterministic. They should be tests and linters that ensure they are followed. Suggestions are good, but dont trust the agents to always follow them. And don’t trust that they wont change your rules, keep them honest. Note This post is a thought [1]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: /thoughts/

Write It First, Then Let AI Drive There's a thing that happens when you start using AI coding tools seriously. You assume the best workflow is obvious: let AI generate the first draft, then... Kenneth Reitz · kennethreitz.org [1] Interesting take by Kenneth Reitz. Not quite sure how I feel about it anymore. It kinda hurts, but I’m not sure if code aesthetics matter as much as the product anymore. I cared when I was the one editing, but at this point I’m not doing a lot of edits by hand. Do these aesthetics affect the final products that users use, Not sure. AI makes me sad. Note This post is a thought [2]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://kennethreitz.org/essays/2026-04-12-write_it_first_then_let_ai_drive [2]: /thoughts/

External Link X (formerly Twitter) · x.com [1] If agents make prime a bit faster, what does that mean for the rest of us mortals? Note This post is a thought [2]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://x.com/ThePrimeagen/status/2043861800819761382 [2]: /thoughts/

External Link X (formerly Twitter) · x.com [1] I’ve gotta agree with bob on this one, the first thing I did to my biggest brownfield project I wanted to use agents on BEFORE they did work was a hardened pre-commit.yaml, ci, hardened type checking and linting. SECOND get rid of bad inconsistent patterns, let them replicate consistency, force them to pass checks. Agents will follow all of your markdown suggestions most of the time, enough for you to become complacent if you let it. They are goal seeking, if you put them to a task you thought was possible that is not given your constraints, they will try to find a way given enough tokens. I dont see this ever changing, its one thing that makes them great, it just needs to be kept in check. Note This post is a thought [2]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://x.com/unclebobmartin/status/2044065822067282396 [2]: /thoughts/

Steve Yegge Steve Yegge: I was chatting with my buddy at Google, who's been a tech director there for about 20 years, about their AI adoption. Craziest convo I've had all year. … Simon Willison’s Weblog · simonwillison.net [1] behind, yet positioned to completely dominate this race by hitting it with some sense. Making trends in what looks like longevity in the race that is not subsidising to simply get users, but to get by until they figure out how to 100x reduce the cost to a reasonable level. They feel like the guy sitting in the back with nothing big or flashy to say that is going to drop the hammer on their competition that overstretched itself taking on too much debt because it was necessary to change the game. There might be something to having a mix of hipsters, boomers, and luddites all trying to balance each other out. Note This post is a thought [2]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://simonwillison.net/2026/Apr/13/steve-yegge/#atom-everything [2]: /thoughts/

An ai model created by Anthropic was announced as a closed preview on April 7, 2026 for critical security research and evaluation with its close partners with critical software such as operating systems and browsers. Anthropic claims that mythos is able to reason through so much more context that any model ever before. This enables it to find bugs that are 25 years old in the BSD, considered one of the most secure operating systems we have. Once it finds these zero day bugs never discovered before its able to use them together in malicious ways never expected. In ways the world is not ready for. At the time of writing these are claims without proof. It remains scary to know the potential this has and that there is only a few companies with this potential that will gatekeep who gets access.

- 5 star video, if you are going to watch one video to understand how harnesses and agents work, this is it. This really had my gears spinning on what tools do for agents and how big of a difference they make in their ability to manage context efficiently and accurately create changes. It’s crazy how good bash works, and that gives the agents the ability to do just about everything, but it could be better. Note This post is a thought [1]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: /thoughts/

- A really interesting long form interview with @simonwillison.net. If you follow him closely most of it is probably not new, but I found some interesting nuggets. Simon is writing most of his code from his phone these days using anthropic hosted platform. He mentioned that a lot of security risks go away when you don’t put secrets on the platform and you let them take the risk of running ai written code with ai chosen supply chain. He talked about the Pelican Riding a Bike benchmark for quite awhile. He was surprised at how well of a proxy it is for how capable a model is at just about everything. He also said that when he runs the benchmark he also runs half a dozen others that he’s never talked about so that He could see if they were to train a model specific to his benchmark he could catch them, but it seems they had caught on and if they were they seem that they would already be doing it on all of his others anyways. TDD is incredibly boring for humans, it strips so much creativity and joy from the process. Who cares if agents are bored they do better when doing TDD. Note This post is a thought [1]. It’s a short note that I make about someone else’s content online #th...

Laurie Voss (@seldo.com) Project Glasswing is a glimpse at an oncoming future in which agents do things humans could never have accomplished and the results are handled by other agents faster than humans could react and we... Bluesky Social · bsky.app [1] Is Glasswing the next inflection point [2] Note This post is a thought [3]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://bsky.app/profile/seldo.com/post/3miybjol76p2r [2]: https://dropper.waylonwalker.com/file/00bc13be-32bd-4410-b0c4-2ecc0f2f6b95.webp [3]: /thoughts/

What Happens When AI Stops Being Artificially Cheap The subsidy era is ending. Here danielmiessler.com [1] I’ve been thinking about this for awhile and Daniel makes some great arguments here. Interestingly keeping inference cheap removes the incentives to make our tools better, help us choose the right model, lean on local models, open weight models. The frontier models are so affordable through subsidized subscription models why would you deal with anything less intelligent at this point. The tooling we use is not optimized for it, and why should it be. Note This post is a thought [2]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://danielmiessler.com/blog/ai-stops-being-artificially-cheap [2]: /thoughts/

External Link X (formerly Twitter) · x.com [1] Everyone look away, nothing to see here. [2] Note This post is a thought [3]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://x.com/ThePrimeagen/status/2038978962089492631 [2]: https://dropper.waylonwalker.com/file/090f03b2-e6f5-4ede-a814-bfbb4e237b54.webp [3]: /thoughts/

External Link X (formerly Twitter) · x.com [1] Anthropic safewords are the talk of the town today. [2] Note This post is a thought [3]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://x.com/metedata/status/2038924041453441422 [2]: https://dropper.waylonwalker.com/file/c097c6dc-4b10-4fab-a9f9-1d4181422285.webp [3]: /thoughts/

External Link X (formerly Twitter) · x.com [1] The claude code source code leaked today and the tweets are great, maybe twitter is back. Did you know you can replace the spinning verbs in Claude Code. I’m having fun with it. [2] Note This post is a thought [3]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://x.com/joshmedeski/status/2039010741039120417 [2]: https://dropper.waylonwalker.com/file/8cf5cf65-40e1-4f40-8d09-b596a97dd51d.webp [3]: /thoughts/

Nick Nisi (@nicknisi.com) Y'all, I think I'm a convert to pi Bluesky Social · bsky.app [1] I’m about to be pi pilled. Note This post is a thought [2]. It’s a short note that I make about someone else’s content online #thoughts References: [1]: https://bsky.app/profile/nicknisi.com/post/3mhgcbpm4ds2p [2]: /thoughts/