Lachlan

No-code & AI Nerd | AI Product Manager @ Xano @nocodebackend

Follow me for info about building applications with and for AI.

[Lachlan @lowcodelocky]

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.

[Lachlan @lowcodelocky]

@OfficialLoganK @GoogleAIStudio Hey Logan, awesome launch - will this be coming to the Agent platform model garden soon? I can only find it in AI Studio.

[Lachlan @lowcodelocky]

@MatthewBerman I mean agree, but the bigger problem isn't them reverse engineering it, their engineers are already feeding them the source.

[Lachlan @lowcodelocky]

@elder_plinius brother they dont need to reverse engineer it, the engineers at these companies are feeding them the source..

[Lachlan @lowcodelocky]

@shawmakesmagic Yup enough years in crypto leads you to lean towards reducing risk/loss over profit.

[Lachlan @lowcodelocky]

@TAbrodi brother its 100k right?

[Lachlan @lowcodelocky]

@thsottiaux https://t.co/QHGgTH0oXQ ? with a big ass button

[Lachlan @lowcodelocky]

How cool, can't wait to explore infinite worlds in VR with my wife and daughter. VR headsets and walking / running pads - seems incredible.

[Ian Curtis @XRarchitect]

Portal jumping through gaussian splat worlds with WebGPU. real time. sound on.

[Lachlan @lowcodelocky]

@elonmusk The man wasn't lying, wtf lol.

[Lachlan @lowcodelocky]

@LimestoneHQ True that's why you should use @XanoHQ security and compliance shouldn't be an afterthought.

[Mikita Balesni @balesni]

Two other safety researchers and I were fired from OpenAI last week. We wrote this letter to leadership.

I believe we were fired for prioritizing safety over the near-term interests of OpenAI as a corporation.

[Lachlan @lowcodelocky]

@OpenAIDevs Why not share how fast it actually is in terms of tokens per second?

[Lachlan @lowcodelocky]

@AIMind_Ai Money well spent

[Lachlan @lowcodelocky]

@domsilvestre Looks to be very slow based on your results

[Lachlan @lowcodelocky]

@nutlope This is cool, surprised you didn't include Gemini models here.

[Lachlan @lowcodelocky]

@CodelessConsult Where you porting it to?

[Lachlan @lowcodelocky]

@zacharynado @synthwavedd How do we get on that preview list brother :P

[Lachlan @lowcodelocky]

@jelanifuel Pretty much just run Opus 5.5 tbh, everything else is mostly noise.

[Lachlan @lowcodelocky]

@webaddict @SemDayy @OpenAI Pretty sure $200 is 10x now..

[Lachlan @lowcodelocky]

@illyism You need a paid account for it to appear. Not quite sure why they don't upgrade all users, it feel like 3.6 must be cheaper to serve, 3.8 does love to use tokens.

[Lachlan @lowcodelocky]

@Myrfion @theo @t3dotcodes Ahh worked for me, might need to ensure your claude code is updated as well it was 5-5 for me with opus.