321–330 of 363 posts
Earlier quoted context omitted.
Their chat was called "Le Chat" - it's just their style. And while it may miss the HN crowd, one of the main selling-points of AI coding is the ease and playfulness.
It's still called "Le Chat" (which means The Cat in French), hence the occasional pun with a cat icon in various places on their website.
Thanks :)
Earlier quoted context omitted.
I really do not want those things in Claude COde - I much prefer choosing my own diff tools etc. and running them in a separate terminal. If they start stuffing too much into the TUI they'd ruin it - if you want all that stuff built in, they have the VS Code integration.
Mind elaborating a bit on the diff tool / flow you’re using? Trying to follow along better with what CC is doing
Trying to follow along better is exactly the opposite of what I'd advocate - it's a waste of time especially with Claude, as Claude tends to favour trying lots of things, seeing what works, and revising its approach multiple times for complex tasks. If you follow along every step, you'll be tearing your hair out over stupid choices that it'll undo within seconds if you just let it work.
Earlier quoted context omitted.
I ran ollama first because it was easy, but now download source and build llama.cpp on the machine. I don't bother saving a file system between runs on the rented machine, I build llama.cpp every time I start up. I am usually just running gpt-oss-120b or one of the qwen models. Sometimes gemma? These are mostly "medium" sized in terms of memory requirements - I'm usually trying unquantized models that will easily run…
I know you say you don't use the paid apis, but renting a gpu is something I've been thinking about and I'd be really interested in knowing how this compares with paying by the token. I think gpt-oss-120b is 0.10/input 0.60/output per million tokens in azure. In my head this could go a long way but I haven't used gpt oss agentically long enough to really understand usage. Just wondering if you know/be willing to shar…
Look interesting, eager to play around with it! Devstral was a neat model when it released and one of the better ones to run locally for agentic coding. Nowadays I mostly use GPT-OSS-120b for this, so gonna be interesting to see if Devstral 2 can replace it. I'm a bit saddened by the name of the CLI tool, which to me implies the intended usage. "Vibe-coding" is a fun exercise to realize where models go wrong, but for…
Earlier quoted context omitted.
Mind elaborating a bit on the diff tool / flow you’re using? Trying to follow along better with what CC is doing
I don't want/use anything fancy - I just use git diff in a separate terminal. I don't care about the individual changes Claude is making during a unit of work. I'll review a final change. Sometimes not even that - if the tests pass I may way until it's committed a bunch of changes, and review them as a whole. Trying to follow along better is exactly the opposite of what I'd advocate - it's a waste of time especially…
Earlier quoted context omitted.
I wrote about that possibility here: https://simonwillison.net/2025/Nov/13/training-for-pelicans-...
Aiden is perhaps misinformed. From a Bing search performed just now. > Yes, I am familiar with the "pelican riding a bicycle" SVG generation test. It is a benchmark for evaluating the ability of AI models, particularly large language models (LLMs) and multi-modal systems, to generate original, high-quality SVG vector graphics based on a deliberately unusual and complex prompt. The benchmark was popularized by Simon W…
I gave Devstral 2 in their CLI a shot and let it run over one of my smaller private projects, about 500 KB of code. I asked it to review the codebase, understand the application's functionality, identify issues, and fix them. It spent about half an hour, correctly identified what the program did, found two small bugs, fixed them, made some minor improvements, and added two new, small but nice features. It introduced…
I gave Devstral 2 in their CLI a shot and let it run over one of my smaller private projects, about 500 KB of code. I asked it to review the codebase, understand the application's functionality, identify issues, and fix them. It spent about half an hour, correctly identified what the program did, found two small bugs, fixed them, made some minor improvements, and added two new, small but nice features. It introduced…
Also tried it on a small project, it did ok finding issues but completely failed doing rather basic edits, like it lost closing brackets or used wrong syntax and couldn't recover. The CLI was easy to setup and use though.
Back when Devstral 1 released, this was made very noticeable to me because the ones who used the smaller quantizations were unable to actually properly format the code, just as you noticed, that's why this sounded so similar to what I've seen before.
Earlier quoted context omitted.
Hi Simon! Love your work! Our of curiosity - how many pelican-cycling samples do you produce. Curious about the variance here. Thanks!
I've lost count, but there are 85 posts with that tag here: https://simonwillison.net/tags/pelican-riding-a-bicycle/ I need to extract them all into a formal collection.
Look interesting, eager to play around with it! Devstral was a neat model when it released and one of the better ones to run locally for agentic coding. Nowadays I mostly use GPT-OSS-120b for this, so gonna be interesting to see if Devstral 2 can replace it. I'm a bit saddened by the name of the CLI tool, which to me implies the intended usage. "Vibe-coding" is a fun exercise to realize where models go wrong, but for…
>vibe-coding A surprising amount of programming is building cardboard services or apps that only need to last six months to a year and then thrown away when temporary business needs change. Execs are constantly clamoring for semi-persistent dashboards and ETL visualized data that lasts just long enough to rein in the problem and move on to the next fire. Agentic coding is good enough for cardboard services that colla…
"There is nothing more permanent than a temporary demo"