Summer holidays = coding season.
Last term I have really enjoyed building a feedback and marking app to try and help save teachers hours of work. Now I’m finally cracking on with the other ideas sitting in my notes.
School starts again, and we’re expecting a baby, in September...
Better get building now while I have the chance...!
@petergyang It’s got better but I tend to turn it off for a week I know I’ll be hitting the limit to give a bit more breathing space. That said, having it on is a very useful and I genuinely think it has saved me tokens at times as it uses context it knew rather than me having to give it
What's the best book you have read on AI?
I've got a bit more time over the next few weeks before work starts again and I'm wanting to do a bit mroe reading before this. I've started a few books recently but even ones published 6 months ago feel outdated with the current pace of AI at the moment.
Has anyone read anything really good that stays relevant with the newest releases?
@i_mika_el I'm in the other 'half' where the office isn't for my dev work so it's all on my time at home. Hoping one day to turn it into Remote working for myself!
Finally into developing for the latest iOS and must say the new Siri app is aesthetically beautiful. Eco sites to try out and see if it is more usable now
@thsottiaux The Codex models themselves are powerful and each update has built on the success of the last and made them more usable each time. But for me the Codex desktop app hands down is the reason I keep consistently coming back
Ok, Codex is telling me this will take six to 9 engineering days.
It's a big implementation I am planning so how long do we think it will take Sol Ultra on fast mode?
Lets see...
@forgebitz This still baffles when it gives the days worth of estimates. But I think maybe AI companies are purposefully getting their models to state this to constantly remind developers how quick models can write code.
Expert doesn’t require decades of experience but just operating at a higher level than the majority. I would say there’s debate about the exact percentile cutoff, but people who’ve spent a solid chunk of every day working with LLMs and AI algorithms clearly sit well above the average user.
Relative to everyone else, that qualifies as expertise.