Raiko (@barndooor) header
Raiko (@barndooor) profile picture

https://nitter.cf/t.co/PbPwrUQdt5 → turn any pdf into a study plan that peaks your knowledge on exam day

☦️
Joined June 2023
Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)Photo by Raiko (@barndooor)
Jensen as nepohire to AMD
Replying to @TravisMWhitaker
What if Jensen makes his own company, or joins AMD? He'd be completely wasted working for elon etc, he still cares about the average consumer as we can see from them not totally withdrawing from consumer cards
58
latest tts model seems abandoned/forgotten by oai?
1
1
56
luna >> haiku on my benchmarks seems to be 50% less accurate than luna while being more expensive
74
Dario: there no amount of financing that could save us Also Dario:
Per Reuters, Anthropic has $252 billion in non-cancelable compute obligations across Microsoft, Google and Amazon, and $161.2 billion in Broadcom TPU lease obligations that are "largely non-cancelable". Truly insane. reuters.com/business/anthrop…
2
187
I have yet to see someone put some respek on dayz (arma)
4
7
239
logged more hours on one of these than the rest of them combined
1
20
chonky
2
5
147
is there an image-jev that's accurate and actually on API right now?
1
128
The .5 jump feels well deserved and honestly an understatement. Underhyped on twitter for far a sub takes you now which is crazy given the terrible mileage on both fable models
so opus 5.5 did substantially better than fable 5.1 on all my prompts. Anthropic says it is "as good as Fable 5.1" but, in my experience, that does no justice to it now, before you call me a paid shill, remember Anthropic is actively training on my domain. this is easy to verify. ask Opus 5.5 to write the grammar and rules of the Interaction Calculus. it will nail them, to small details (see it on VictorTaelin/Interaction-Calculus), while GPT models barely know it. so I think I might be experiencing Claude's jumps more profoundly than most, and that explains my preference needless to say, I'm having a fields day and feeling an enormous urge to lock in and (finally) write Bend in itself. that'd unlock so many incredible things. but I have PRs and a raise to handle :| (if you're from Anthropic, I'm very thankful you guys are doing that and I hope you keep it up...)
1
4
205
Opus 5.5 is an incredible model I hope they use it to fix this memory leak
3
140
hell yeah goodbye openrouter
2
122
Does this work without ruining cache
This is actually insane. This uses @typesafeai Jev model, as a plugin in Claude to review all the un-nesseasary tool calls, and it takes 1s to run! Like, literally, 1 second to take my Claude session from nearly 1M to ... 86K tokens! 😮 Ask your claude to install it and be amazed Use this prompt ``` Install, and configure : github.com/tamaratran/fast-j… ```
1
234
computer use, but drop the most useful part, it's cleaner
127
pi or fx?
1
119
ok just added a replay feature to herdr-story im watching a day in the life of my SaaS unfold: - Codex/claude tackling tasks at their desks - Every Stripe payment turns into a customer walking in and buying my product - Receptionists and agents celebrating the wins love gamifying my saas
2
1
9
331
we live in a utopia
149
i've been an oai UI/UX hater until today... can confirm this works shockingly well with astra and arguably better than fable
I can confirm this actually works!? For divergent design explorations
1
1
285
Astra is powerful but still suffers from insane sprawl on code it should never have to touch Benchmarks like frontiercode measure how human it is but don’t do a good job of negatively grading sprawl as much as they should be. In an AGI world this is the only metric that matters
Replying to @tmuxvim @reach_vb
That's actually exactly what I did, it still went and slopped it up
2
235
you can't make this up. this is for a document editor btw
182