✨

118 posts

✨ banner
✨

✨

@portrays

distributed systems eng

london Katılım Ekim 2013
27 Takip Edilen223 Takipçiler
✨
✨@portrays·
@redtachyon oh and it’s just cuz he’s german haha :D nothing else just an angry german
English
0
0
8
503
✨
✨@portrays·
@redtachyon i hate this cunt with a passion, what a terrible look for someone who’s an “entrepreneur” selling you a course on how to ship slop web apps. interesting he needs to sell a book (probs 100% generated by an llm) when his revenue seems to be doing so well according to bio🤔
English
1
0
19
529
✨
✨@portrays·
@strikermi91 @RealBenOwensX @RupertLowe10 @zarahsultana larping as centre-right civic nationalist while your only contribution to the debate is emoji mockery with no substance the second someone distinguishes between a well-integrated british citizen and open borders
English
0
0
0
23
✨
✨@portrays·
@Femi_sorry not to mention the fact that your reaction most likely came off the back of this tweet, and rupert couldn’t have put it better
✨ tweet media
English
0
0
0
18
✨
✨@portrays·
@Femi_sorry what a strange inversion, patriotic pride in english/british success incl players of immigrant background should be normal. it’s a positive example of assimilation. you treat the english identity as racially gated which is exactly the ethno-nationalist logic you accuse others of
English
1
0
0
32
Femi
Femi@Femi_sorry·
Oh shut the fuck up you RACIST PRICK. Your spokesperson just refused to rule out deporting me because I'm black. You don't get to celebrate the success of black English people while telling us we don't belong in England. Keep the name Jude Bellingham out your Nazi mouth.
Rupert Lowe MP@RupertLowe10

Jude Bellingham.

English
2.9K
2.2K
23.4K
1.3M
✨
✨@portrays·
@EndMeta @pvncher yeah smh, he should've ignored it instead. how outrageous to call incorrect information, "misinformation" the literal definition
English
0
0
0
16
w
w@EndMeta·
@pvncher as DX, it's literally your job, do your job smh
English
1
0
0
26
eric provencher
eric provencher@pvncher·
This is misinformation. Your tokens are not being billed at a higher rate over 272k tokens with the new expanded context window with the 5.6 family of models. If you manually expand the context window beyond that however, that’s a different story.
Vincent@Vincent_AINotes

OpenAI 的规则是： 输入超过 272K tokens 后， 整次请求按以下价格计算： → 输入 ×2 → 输出 ×1.5 重点是“整次请求”。 不是只给超过 272K 的部分加价， 而是从第一个 token 开始全部重算。

English
42
38
566
148.4K
✨
✨@portrays·
@theo why would i listen to someone advising on how to not hit limits, if the article image is a screenshot with 0% remaining?
English
7
0
15
15.5K
moose
moose@moosemoosse·
moose tweet media
ZXX
1
0
10
580
✨
✨@portrays·
@scholzmx @theo @kyle_mccleary he's not calling it "useful slop" tho. @theo hit 1 bug and immediately outed it to his entire following as trash. just shitting on an oss project with his reach on x to put other maintainers down is kinda weird when u can fix it urself as code is so free these days?
English
0
0
4
148
Theo - t3.gg
Theo - t3.gg@theo·
@kyle_mccleary Oh it did that because after installing it printed the ENTIRE CHANGELOG FROM DAY 1 and hosed my terminal. I'm sorry but this is clearly slop and I will be removing it from my machine immediately.
Theo - t3.gg tweet media
English
6
0
37
47.5K
✨
✨@portrays·
@theo biggest loser as well
English
0
0
0
23
✨
✨@portrays·
@kyle_mccleary @theo yeah it can be resolved and already has been, oss is great. he can open up a github issue instead of being a fucking loser on x shitting on others with his superiority complex when he's never built anything remotely complicated
English
0
0
2
121
Kyle
Kyle@kyle_mccleary·
@theo Damn. Sorry Theo :( It's been very good for me though. Other facets feel quite polished, and I think this changelog thing can be patched.
English
2
0
7
3.8K
Theo - t3.gg
Theo - t3.gg@theo·
If you set gpt-5.6-sol to "ultra", all the subagents it spawns will also be set to ultra. IMO this is a fumble. Causes massive token burn for no good reason. At the very least, I should be able to hard-set the subagent effort level to "medium". Claude Code is far ahead here
Eidzoku@evi77ain

There's a flaw in Codex's (or should I say ChatGPT's?) subagent orchestration. The spawn_agent tool doesn't let you choose the model or reasoning effort. Therefore, every time 5.6 Sol Ultra spawns a subagent, you're getting another Sol Ultra instance. That's why your quota gets drained so fast.

English
206
51
1.9K
655.5K
aashuu ✦
aashuu ✦@warrioraashuu·
how Anthropic made the new Fable 5
English
4
0
9
545
✨
✨@portrays·
@mark_k @OpenAI god i hate slop tweeters like yourself that literally just have 0 reading comprehension. bryce said different, not worsee and he's in his own replies agreeing that slower + more persistence is probably the better profile for real research work, delete ur acc pls
English
0
0
0
116
Mark Kretschmann
Mark Kretschmann@mark_k·
Review of @OpenAI GPT-5.6 SOL by an Nvidia engineer with early access to the model! His review is not entirely positive when compared to Claude Opus. It seems to have a number of drawbacks for coding. But there are also good aspects, like simpler code and less code overall:
Mark Kretschmann tweet media
English
36
12
283
48.1K
Leon Lin
Leon Lin@LexnLin·
"5.6 plan limits will be significantly more generous" YESS
leo 🐾@synthwavedd

🚨 SCOOP: As previously reported, OpenAI plan to launch GPT-5.6 once back in office next week, with a target window of July 7-9, but want it out as early as possible within that window (so July 7th is the most likely date). This is also perfect timing to catch customers coming from Claude who have just lost their access to Fable 5 in plans, and I'm told the 5.6 plan limits will be significantly more generous. More aggressive safeguards are already being rolled out in preparation for the launch too, although they probably won't be as aggressive as Fable's. DeepMind have also tentatively set a new launch date for Gemini 3.5 Pro of July 17th. Apparently, this extra time has been spent on a new pretrain (they were planning to keep using the ancient 2.5 Pro base, lol), but it remains to be seen whether it's any good. I'm not hopeful. In other news, work is well underway on a new Nano Banana Pro model based on the new 3.5 Pro base, which I expect to be better received and compete well with GPT-Image 1.

English
18
13
1K
99.5K
✨
✨@portrays·
@TatataToddC @LexnLin 0-shot frontend ability is a weak way to evaluate a model. it seems like you're new here if you think so
English
0
0
0
13

Keşfet

@redtachyon @strikermi91 @RealBenOwensX @RupertLowe10 @zarahsultana @Femi_sorry @EndMeta @pvncher