# Posts on X before Aug 8, 2024, 12:42:01 PM UTC Canonical: https://michaelstolarz.com/x/before/1723120921000-1821527286018986423/ ## On X ### [Aug 8, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1821427045420679504) > gpt-4o is actually retarded when it comes to coding ### [Aug 8, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1821370833421447456) > all this AI hype around gpt-4.5 / gpt-5 with no release is cool the first time, eh the second time, cringe the third time, annoying the fourth time, boring the fifth time... ### [Aug 7, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1821022814863868146) > today's AI context windows are like the first 16MB flash drives back in 2000-2002. > > except we won't have to wait 10 years for orders of magnitude improvement in capacity. soon, a "context window" will be virtually limitless ### [Aug 5, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1820490185433600274) > everyone’s waiting for WW3 to drop like it’s a new model LMAO ### [Aug 5, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1820352479843721645) > been using this all day today and... yeah it's performing amazingly so far code-wise, going to stress test it even further. it's so super safe though, that's the only downside Quoted post by Ruben Hassid: ### [Aug 4, 2024 — @rubenhassid](https://x.com/rubenhassid/status/1820111720431468653) > gemini 1.5-pro-exp outperforms gpt-4o. > > Some say it's the end of OpenAI reign. > > So I ran my own tests: > test \#1 → write a viral twitter thread [Attached image](/x/media/4d2e8166b4a7dcccb09ad1f0eb2d41a4826f5804a34ff84818b0a82c41ed5481.jpg) ### [Aug 5, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1820303368968905161) > yeah a lot of people seem to forget that gpt-4o is any in, any out Quoted post by Jimmy Apples 🍎/acc: ### [Aug 5, 2024 — @apples_jimmy](https://x.com/apples_jimmy/status/1820259947059479007) > Hot take, I want the promised 4o image capabilities more than voice. > > Something magic about the prompt accuracy and working in tandem with an alien ai to create. > > “Art is the highest form of hope. What we are doing here is hope work.“ [x.com/gdb/status/179…]() ### [Aug 4, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1820073529200550303) > It’s been months since I’ve used OpenAI anything for something. It’s all Sonnet 3.5. ### [Aug 2, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1819364084548317256) > small tiny eensy weensy puny little chance that this also drops an upgraded OpenAI model. but... the chance is NOT non-existent\! Quoted post by Brett Adcock: ### [Aug 1, 2024 — @adcock_brett](https://x.com/adcock_brett/status/1819091030496735348) > fyi, Figure has some very special announcements coming > > The engineering team has been working their assess off the last four months > > Tomorrow, you'll see the beginning of something that is nothing short of magical 🎩 ### [Aug 2, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1819363191190966608) > unpopular opinion: if this is how you react when you spend your money on something like a PS5, the last thing you need in your life is a PS5. [Quoted post unavailable](https://x.com/i/status/1819205234725457947) ### [Aug 2, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1819263571668426885) > mind blowing how cheap intelligence is becoming. soon $1/$3 will be deemed too expensive for SOTA. Quoted post by Legit: ### [Aug 1, 2024 — @legit_api](https://x.com/legit_api/status/1819161144881217885) > Gemini 1.5 Flash is going to have significant price cuts on August 12th in Vertex AI > > Input cost: $0.0375 per 1M characters > Output cost: $0.15 per 1M characters > > HALF THOSE PRICES FOR \< 128K CHARS [Attached image](/x/media/71f74ce88871a25c9513bd93c8c0c397f783cf65b27a35db9c4f031719c7e1b2.jpg) ### [Aug 2, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1819177640613630361) > so... idk why no one is talking about this but... i replaced my daily $10 API bill by just replacing gpt-4o with gpt-4o-mini... now I'm paying $0.04? a day? hello? without loss of quality? ### [Jul 28, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1817608228899094990) > i support trans people converting > into Christianity ### [Jul 28, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1817468542935347467) > light mode is actually goated ### [Jul 27, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1817211697960042575) > this looks like a google killer, I wonder how it does with more obscure searches that are common among developers, like what happens when you paste in a large debug error from console? or ask a documentation question? or ask for api specifics on some obscure package? Quoted post by kes: ### [Jul 27, 2024 — @yoimnotkesku](https://x.com/yoimnotkesku/status/1817192241548468546) > SearchGPT widgets look nice > > It tends to focus on the results strongly, so sometimes I need to tell it exactly what I want it to do rather than what I want from the web [Video on X](/x/media/1e029c28f893573a4a859aad4505b22334d5bcad7523040dd54833fc29cbb737.jpg) ### [Jul 27, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1817169475994550557) > QuickTime? More like WasteOfTime. > > I've just wasted all day because for some damn reason QuickTime doesn't play audio on certain MP4s. Not until I opened it with IINA because I thought, hey, you know what, why not? Maybe this is one of those codec issues. > > Boom, it works. ### [Jul 27, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1817163711812976952) > i wonder how people pronounce [@yacineMTB]() (kache) - I pronounce it "KA-chey", almost like "catchy" but the a is like the "a" in "alone" > > or maybe it's more like "KA-shey"? instead of chey? or... what if it's like cache? "KA-sh"? literally cash? do I just call him cash? money? help ### [Jul 26, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1816828046449447186) > warp isn't that bad actually ### [Jul 25, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1816499562049368413) > holy moly\! not one, but TWO blog posts today\! woah\! ### [Jul 25, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1816379052925612246) > llama 3/3.1 and mistral large v2 are both trash compared to sonnet 3.5, there you go I just saved you loads of testing time that I did these past 2-3 days ### [Jul 23, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815784894859272464) > sonnet 3.5 is still best SOTA coder though, you can tell right away ### [Jul 23, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815779155017171059) > $3 input, $3 output. beta sonnet $3 / $15 [Attached image](/x/media/4c7fff2991292756bd147877e108cbf397a6604c39f91bf201c963e1a5c4dc97.jpg) ### [Jul 23, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815770129604731384) > Groq's max tokens (output) for the new 3.1 models seems to be 8000 ### [Jul 23, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815765997435109627) > Already in the Groq API :) useable with SystemSculpt AI for Obsidian right now\! [Attached image](/x/media/1a535b90b6d9fb469b8cc5bb66ec4db9d1694454032f5ff7c6807c65d9b92777.png) ### [Jul 23, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815707975622746580) > holy fuck how boring would life be if I was mentally deficient enough to be a 🤢 decel 🤢 and had to not use any type of AI on purpose "out of principle". or if I was an AI art hater, I couldn't use midjourney and such, wow what a miserable life in today's abundant world ### [Jul 22, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815329605735137775) > gpt-4o-mini is goated for quick back-and-forth brainstorming with huge context attached to it, amazing. ### [Jul 21, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815018257071689788) > gpt-4o-mini really feels like a SOTA \<10b model. ### [Jul 21, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815013577721536673) > I wonder if Opus 3.5 is waiting for GPT-5, or if GPT-5 is waiting for Opus 3.5 🤔 which will drop first to have the other respond-drop? ### [Jul 21, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1815011827056615582) > you don't see kache's 17 fever-dream posts every morning anymore Quoted post by kache: ### [Jul 21, 2024 — @yacineMTB](https://x.com/yacineMTB/status/1815009618247987531) > you don't see politicians kissing babies anymore ### [Jul 21, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1814910713808494668) > airpods are remarkable. i accidently left them in my pants, ran them through the washing machine - I put them in a really dry towel to pull the moisture out and 1 day later, they're completely fine as if nothing ever happened. amazing ### [Jul 19, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1814241691249033529) > honestly i don't care how expensive gpt-5 is going to be at this point, it can be $25/$75 / mil and I'll still use it, just release it already smh ### [Jul 19, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1814151128290070773) > he... he just fixed it and... and pushed it to prod [Attached image](/x/media/4c5150343c00ed6095c9e6a64b84db327b3f79b4d9014d7b77d4947a98532e92.png) Quoted post by kache: ### [Jul 18, 2024 — @yacineMTB](https://x.com/yacineMTB/status/1814049055292428671) > [@dysmemic]() fixed on web ### [Jul 19, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1814147419350983162) > yeah so gpt-4o-mini is useless for coding other than maybe diffs commits ### [Jul 18, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1813992655652843784) > first impressions of gpt-4o-mini: super fast. succinct. ### [Jul 18, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1813949063718699484) > it doesn't matter who we are. what matters is our bit. no one knew who i was til I started doing the bit. [https://t.co/W636GCae60]() [Attached image](/x/media/b6d223098ef83e2bf36b950e7932d0c522124b77144fef317683ea27164aff56.png) [Quoted post unavailable](https://x.com/i/status/1813948338481627490) ### [Jul 18, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1813943521310863454) > so it seems like a new model is dropping today, gpt-4o-mini, possibly a full replacement for gpt-3.5-turbo. it's supposed to be "the smartest + cheapest" or something along those lines - hopefully it's available through API right away so we can test it ### [Jul 18, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1813854655031730448) > it's been over 2 months since openai has done anything cool lmao ### [Jul 18, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1813836334219616709) > remember, they masquerade their terrible brain rot opinions as you "not being inclusive enough to understand". > > you're right. there's no room for debauchery, hedonism, addiction - no matter what excuse you think fits -in my household. ### [Jul 17, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1813576839279059452) > the amazing thing about open source that I don't think the first movers of the movement thought about was not that open source is something amazing for humans, which of course it is, but that it's actually a boon for ai. imagine how useless today's ai would be without github lmao ### [Jul 17, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1813430932277457031) > should i rewrite my entire typescript-based plugin in javascript just to see if I still got it ### [Jul 16, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1813138659719455188) > imagine if context length of new llama 3 405b is like 8K or 16K LMAO ### [Jul 15, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1812838750495420691) > ya\! :D [Attached image](/x/media/e2cb71d11322e25ab8c4fe3bcf89607819255f5b278959b3efedc54604c25833.jpg) ### [Jul 13, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1812089184016118252) > i wish they didn't upload all these new models to lmsys, just inject it right into my veins via an API please ### [Jul 13, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1812019743307759787) > everyone's playing the B2C game, fancy people play the B2B game, meanwhile OpenAI is playing the B2G game ### [Jul 12, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1811837062708101289) > I wonder how my website looks on twitter: [systemsculpt.com]() ### [Jul 12, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1811796308598096080) > i always get confused which one is which, their pfp looks near identical (from afar / small ofc) [@linaqruf\_]() [@anpaure]() twins irl or moots or wat? [Attached image](/x/media/56ebe32b1a7620a58b785f61018b194e522b6d1bcff4d8dc5e0d1a7bf65b0ed9.png) [Attached image](/x/media/4027b0df7325b5e9fb66b102ab7eff297d61341fad9f1087b6a5bd2e90a8d366.jpg) ### [Jul 12, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1811795188287000994) > sometimes i tweet a banger, > sometimes i tweet a retard ### [Jul 12, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1811793779759939632) > quote this with an image that ages you [Attached image](/x/media/1cf5f22de3029259e98eaafafdef05ae0c75a7e4477b860dd696c59bbb0e3cca.png) Quoted post by kache: ### [Jul 12, 2024 — @yacineMTB](https://x.com/yacineMTB/status/1811786846092886474) · Edited > quote this with an image that ages you [Attached image](/x/media/a0b7687df59c0ca4308c92053a70b28ca616e0cb9a004ef00a5b26ec1f6e6105.png) ### [Jul 12, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1811738900597244298) > it's so cool to take an old script/niche program made by gpt 4/gpt 4o and rewrite it entirely with claude sonnet 3.5. the difference in quality - code wise, design wise, architecture wise - is leagues above. ### [Jul 12, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1811724237163381119) > and this is why u have to say frfr, not just fr Quoted post by ScottFive: ### [Jul 11, 2024 — @5cottFive](https://x.com/5cottFive/status/1811502331609120920) > [@netcapgirl]() Every time I see "fr" my brain happily and unapologetically goes "hey, that's the two-letter abbreviation for "France\!" ### [Jul 9, 2024 — @MichaelStolarz](https://x.com/MichaelStolarz/status/1810690478846706113) > deepseek coder v2 is heavily slept on, even by tpot [Older posts](/x/before/1720537225000-1810690478846706113/index.md) [More from @michaelstolarz](https://x.com/michaelstolarz) Saved from X: 2026-09-07T03:59:41.765Z