Lachlan

One of my favourite ways to get a vibe for AI models coding ability (particularly it's ui preference) is via @lmarena_ai they have their WebDev arena which pits two AI's against each other, blindly and you pick which result you like the most. You begin to learn the styles that particular AI uses, it helps you understand why people generally prefer Anthropic outputs. Both their 3.5 models, Sonnet & Haiku share a similar design style which is more aesthetically pleasing for sure. I was also impressed with some of the new Gemini 2.0 Pro outputs, and Qwen Max, these are definitely a leap up compared to previous gen models also. But still just behind sonnet 3.5 overall, generally* I was generally underwhelmed by the O3 mini high outputs, (particularly UI). *It's a very useful exercise to show you that there isn't one "best" model, even though it's easy to say "Claude is the best" - Each prompt is different and getting opinions from other models is very useful.

Going to be a fun week of launches : )

These benchmarks look a lil too good to be true, interested to hear how it performs under real-world usage.

@joshwoodward @OfficialLoganK Why are you only able to revert / edit your most recent prompt / message in the gemini app? You also aren't able to roll the conversation back to a previous point. Seems like an easy win to give users more control. Like in AI Studio.

New @opencode plugin incoming. Your safety is our mission.

@ptsi @claudeai Yeah only appears to work in the terminal - would be awesome to get support for it in the extension too!

@claudeai It seems like Claude-in-Chrome MCP is on by default in CLI but not VS Extension. So it still isn’t accessible or has to be configured manually somehow? Unless I’m missing something? 🙏

The VS Code extension for Claude Code is now generally available. It’s now much closer to the CLI experience: @-mention files for context, use familiar slash commands (/model, /mcp, /context), and more. Download it here: marketplace.visualstudio.com/items?itemName…

@codewithantonio @opencode I moved when claude-code had a bug with their compact feature and made the model stupid - haven't gone back as opencode is doing the trick.

for those of you who moved from claude code to @opencode , what was the main reason?

@OpenAI Please update your docs and in-app experience regarding building apps with a free vs paid account. There's no mention a paid account is required, developer mode can be enabled on a free account and building one in app presents no error, it simply just doesn't create a new app. Please throw an error letting the user to know they need to upgrade and mention it in the docs - wasted enough time!

use code "FEEDBACK" for 3 months free on greptile valid until sunday DMs open

@MoonDevOnYT The bait is strong with this one

if you are spending more than $20 per month on claude code, openai or any ai you literally hate money there is this service called ollama it allows you to run ai on your computer buy one of these acer laptops for $210 (probably can get it for under $200 for holidays) download ollama and install your favorite ai free ai for life you're welcome bonus - use a credit card and get the payment on the laptop to under $20/mo

@MoonDevOnYT Mac Studio not mini

@MoonDevOnYT More likely you’d be wanting two of these at least (this is AUD not USD) but you’d be well above 1K USD a month to start handling the bigger models with larger contexts

Before you pay $200/month for another month of Claude code... What about just allocating that $200/month to Apple with a 0% APR? Running a local model in a local agentic coding thing like CC Ironic that the most souped-up m4 Mac Mini comes out to almost exactly $200/month, which is the same price as the Unlimited (Limited) Claude Code. The only questions pending are, what model would you run, and what Agentic coding thing comes close to Claude Code?

@opencode I really hate the way you have conversations setup in the mac app - such a frustrating experience using it tbh.

@scaling01 I'm enjoying it at the moment, i've got more confidence with opus 4.5, but so far for micro adjustments / refining things it's been very solid. The quick iterations keeps you in the flow.

Gemini 3 Flash scores higher than GPT-5.2, Opus 4.5 and Gemini 3 Pro on SWE-Bench Verified ???

@skirano Nice! Any chance you can extend this to other languages like Angular?

It’s absolutely insane how well Gemini 3 Flash works with our Chrome extension, you can design and prototype your REAL product in minutes now. Feels like a paradigm shift.

I think there's still the issue of maintainable code, and working in large codebases. I'd wonder what the purpose of these vibecoders are for, if considered a traditional developer I think they're setup to fail. But on the product side, being able to rapidly prototype and iterate through ideas is where the value lies currently. Every time I vibe code a feature for our product i dread having to pass it to an engineer and them validate my code. Simple changes aren't so bad but working on more complex items leads to a dev sinking their time into debugging and reviewing. If they are to work in the eng teams directly I'd say it'd only be suited to teams that are adopting AI by their eng team also - those who have spent the time setting up their apps and documentation to make it clear how AI should approach tasks. From what I can see a lot of orgs aren't geared like this just yet.

Trend I'm following: Top AI companies hiring professional "vibe coders." Non-technical people who are top 1% at using Lovable/Replit/Bolt/v0/Cursor.

@theo Prompt king.. naht

Gemini 3 Flash is definitely still a small model lol

@VictorTaelin Yeah you need to restart a task. For complex items always best to break it down into .md files and have it work through them individually updating a log with status updates.

I mean not literally useless but you should probably just pause it, understand what it is currently doing, and write a fresh new prompt yourself so it can continue doing useful work, otherwise it will often get lost. I don't get what's so hard about it but seems like it is

Claude Code's compaction is *terrible*. Opus will completely forget what its goal was and focus on something else thinking that's its goal, it will lose code if you don't commit. The context window is not enough for long work, and it is virtually useless after compaction...

@jasonbosco @AnthropicAI Are you sure there’s nerfing happening? My experience has been pretty consistent tbh.

The previous round of unannounced nerfing that @AnthropicAI did (accompanied by regular denials publicly), left such a bad taste in my mouth, that I canceled my $200/mo max plan. When Opus 4.5 launched I saw rave reviews, but from past experience, I figured the nerfing was just a few weeks away, so I didn't even bother to resubscribe and try it. And sure enough... Anthropic - if you're reading this, silent rug pulls like this is how you lose trust, that will then take years to reverse, irrespective of model quality. Please don't do this.

Here we go again! pumped for the new flash model.

AI agents shouldn’t be a black box. Xano now supports OpenTelemetry for AI agents → trace every request, decision, and tool call in LangSmith, Langfuse, or Braintrust. Zero setup. Instant visibility. 🔗 go.xano.co/48N7nTL