←
Theo - t3.gg71,460 posts
Theo - t3.gg avatar✓

Theo - t3.gg ✓

@theo

Full time CEO @t3dotcodes & @t3dotchat. Part time YouTuber, investor, and developer

◷ Joined October 2016▧ 9,728 Photos and videos
Theo - t3.gg avatar
Theo - t3.gg@theo·14h

Probably our best episode to date. Multiple crash outs abound

1:20:46
Theo - t3.gg avatar
Theo - t3.gg@theo·42m

Bam is unironically one of the greatest minds of my generation. Incredibly creative. Unbelievable athlete. Inventor of many formats of film. World class at whatever he chooses to focus on. He will always be a hero of mine. I’m so thankful he’s sober now.

2:19
Florian S avatar
⟳ Theo - t3.gg retweeted
Florian S@airesearch12·1h

Oh I love that: Most aim for 100% accuracy, and end up with 50% clarity. Aim for 100% clarity, 80% accuracy.

Post attachmentPost attachmentPost attachment
Theo - t3.gg avatar
Theo - t3.gg@theo·1h

Looks like GTA 6 will live up to the hype

Post attachment
Theo - t3.gg avatar
Theo - t3.gg@theo·2h

I still cannot comprehend how all of the labs let LLMs get so atrocious at generating text

Post attachment
Theo - t3.gg avatar
Theo - t3.gg@theo·3h

I took this to heart and spent the last few hours doing another deep dive on GPT-6.2 Astra tl;dr - things are better than when I tested, but IMO still "directionally, very bad" I'm going to keep using the same example I've hyperfixated on since the start: "why is creating a worktree so slow?" I had a long thread trying to diagnose perf issues while using t3 code on a particular VPS. 2 of the 3 were fast, 1 was really slow. I asked astra outright "why is this so slow?", and it said a bunch of gibberish. I followed up with "I feel like I'm going insane, can you just tell me the cause of the slowness?" I'll give you the answer upfront: this VPS uses a virtual disk that is slow as shit, my other VPSs have physical NVME drives that are faster. Image 1 is from before the fixes Tibo mentioned. It shows an unnecessary graph, focuses too much on pnpm and file systems, bolds irrelevant text, and brings up ram just as much as it (subtly) mentions drive speed. Image 2 is of Opus asked same thing. It opened with the important part in bold: "Slow disk, made worse by VDO". Ideal! Image 3 is 6.2 Astra post-fixes Tibo mentioned. Better? Absolutely. Much more concise. Sadly, it still focuses way too much on second-order problems that are a small % of the cause. "XFS over a compression and deduplication layer on a virtual disk." - so close, but still a miss. I think this perfectly encapsulates the problem I have with 6.2 Astra. It doesn't miss anything. It's SO thorough. But in it's thoroughness, I find it misses the most important thing: the actual point. It wants to know everything, and then it wants to share everything. It doesn't understand what is and isn't important. Did it say anything wrong in my screenshots? Not really. But IMO, it still entirely failed to miss the point of my question, and gave an answer that was too focused on accuracy and not enough on clarity. In the wise words of Michael Seibel: "Most aim for 100% accuracy, and they end up with 50% clarity. Aim for 100% clarity, 80% accuracy". Silly way of putting it, but I genuinely wish OpenAI models would lie to me a LITTLE more so I could better understand the vibe, instead of having my time wasted by all these useless details.

Post attachmentPost attachmentPost attachment
Theo - t3.gg avatar
Theo - t3.gg@theo·3h

This was supposed to be a "small feature" but I'm increasingly convinced it's one of our biggest. I pass secrets to agents in T3 Code multiple times a day

Post attachment
Theo - t3.gg avatar
Theo - t3.gg@theo·3h

fwiw I literally told them they could charge $120+ and get away with it and THEY STILL CHOSE TO MAKE IT $100. Framework likes their customers too much.

Theo - t3.gg avatar
Theo - t3.gg@theo·3h

I cannot tell you guys how hyped I am that this is finally dropping

Post attachmentPost attachmentPost attachment
Theo - t3.gg avatar
Theo - t3.gg@theo·4h

Seems like 6.2 Astra is incredible for math. Cool to see other areas it works well in!

Ben Davis avatar
⟳ Theo - t3.gg retweeted
Ben Davis@davis7·6h

Thus far Anthropic has always been the one to make the big step function jumps that change how we can use AI: - Sonnet 3.5 - Opus 4.5 - Opus 5.5 Usually others catch up and often surpass them (like how GPT overtook Claude last spring), then they jump again. I'm expecting this to repeat (OpenAI or someone else will crack the insane usability + capability combo Ant got with Opus 5.5) sooner or later I was really, really hoping that would be GPT 6.2 Astra but it's just not. I would however bet money that the next big GPT release will be almost entirely focused on being the best possible experience to interact with + good behavior As long as this cycle continues as it has I think things are fine, but I need to see/feel someone actually catch Anthropic as capabilities continue to skyrocket or things are probably gonna get really shitty. Anthropic's been on their best behavior since OpenAI became a much more credible threat this year, that must continue next year. An Anthropic not suffering from competitive pressures would be horrible for the world...

Theo - t3.gg avatar
Theo - t3.gg@theo·7h

Releasing closed source software right now feels a tad insane to me I won't lie

Theo - t3.gg avatar
Theo - t3.gg@theo·8h

According to Artificial Analysis, Opus 5.5 is no longer on the pareto line (best value per intelligence) Love AA and all, but they really need some behavioral benches to smooth out this gap. Opus 5.5 is still the best value available for real long running code work.

Post attachment