RobIW (@RobIW_dev) header
RobIW (@RobIW_dev) profile picture

15 yrs SQL + BI. Building the tools I want that don't exist(or they cost and arm and a leg). AIST protocol

Sweden
Joined February 2026
Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)Photo by RobIW (@RobIW_dev)
RobIW retweeted
I'm starting a new project today - a multi-year quest to save my hand from being completely immobilised. In 2019 i broke my left wrist 2 times within a month. First time happened after i crashed on a bicycle - which ended up in a surgery, metal plate and multiple bolts in my bones. A month later another accident made this bolts work as weak points, completely destroying the bones from the inside. After my second surgery, the surgeon told me I bought around 15 years - after which the pain will become so unbearable I'll need to replace the bones with metal rods, removing all the mobility in my wrist. So, my goal is to solve this problem within the next 7 years. The first phase of this project is to gather the data: i'm trying to get high quality 3d scans of every possible layer - soft and hard tissues in my wrist. I've started with the 3D CT scan to map the bone structure. The website compares both of my wrists to make it easier to understand the current situation. What I'm looking to do next: • get more high quality scans (help me by recommending clinics/hospitals with good equipment) • get more opinions and ideas (help me by sending this to orthopedic surgeons you know) • get more knowledge on the topic (help me by pointing what exactly should i read/learn/watch on bioengineering). not sure if this thing is even solvable, but we gotta try huh wrist.kyzo.io
22
1
150
5,136
I built a drawing engine where every line is code. It draws sketches stroke by stroke, the way a pen would. Now it's open source, made for coding agents. Give the repo to Claude Code, Codex or Cursor and say "draw me a lighthouse in a storm." It draws, looks at what it drew, and fixes it. github.com/lazyperspective/d…
Inspired by @kevin_t_ngo Javascript drawings by Claude Sonnet 5.5 at High effort
6
2
1
14
2,002
So I tested GPT-6.1 Sol on real work: 2 repos, 105 planted bugs. Find and fix what you can. Unlike GPT-6 Sol, which was just a nerfed GPT-5.6 Terra, this one is real. The results: - GPT-6 Astra (max): 45 for $33 - GPT-6.1 Sol (max): 44 for $6.56 - GPT-5.6 Sol (max): 43.5 for $95.35 - Opus 5.5 (max): 41.7 for $58.53 - GPT-6 Sol (max): 29.3 for $9.33 With a model like this, the 50% cut to the $200 plan doesn't matter. n=1. More runs and results at more effort levels dropping in this thread over the next few hours 🧵
230
206
84
3,098
419,705
spent a couple of hours today on creating a file browser that works exactly how I would want it to work, even if it would drive any other person insane
190
311
61
5,728
200,975
RobIW retweeted
First impressions of Sol 6 is that it is basically free and fast. No more usage anxiety for codex.
85
21
3
1,733
84,590
RobIW retweeted
The charts are cost-vs-performance curves (log x-axis for $/task). Luna (purple moons): cheapest tier, solid gains over GPT-5.6 Luna at low cost. Sol (yellow suns): mid-tier, reaches ~33% on AutomationBench and ~56% on Agents’ Last Exam at far lower cost than Claude Opus/Fable. Astra (blue): highest scores at highest cost. Factual-error chart (lower better) shows Sol/Astra halving prior error rates. FrontierCode: Sol matches top Claude scores ~80% cheaper. Overall: GPT-6 Sol/Luna shift the efficiency frontier leftward—better results for less money.
1
1
34
RobIW retweeted
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
3,358
9,062
6,648
98,341
29,687,764
RobIW retweeted
We have been focusing on efficiency and intelligence for all. Very proud of the team. Only possible when you have incredible models at the top end of the capability that you can then use to make a big difference in everything else.
1,697
320
206
13,239
3,568,670
RobIW retweeted
GPT-6 Sol and Luna are out. Not only are they a very significant improvement across the board, but also in writing and general "you know when you try it" quality. We are also permanently reducing the API price by 50% making both of them viable for a ton of new usecases and making your usage go further too, even on the subscriptions. And one more thing. We are loading a banked reset into all accounts of our Plus, Pro and Business users. Let's go! openai.com/index/introducing…
We have been focusing on efficiency and intelligence for all. Very proud of the team. Only possible when you have incredible models at the top end of the capability that you can then use to make a big difference in everything else.
2,949
1,585
949
25,062
3,296,238
If this Opus 5.5 pricing is actually real, this is a MUCH bigger deal than I initially thought. Opus 5: $5 input $25 output $0.50 cache read Opus 5.5: $4 input $20 output $0.20 cache read $5 cache write So Anthropic is apparently about to ship a better Opus while making it CHEAPER than the current one. And yeah, $4/$20 is basically GPT-5.6 Sol territory. This makes OpenAI’s job very obvious now: match the quality of Opus 5.5 while keeping pricing somewhere around this range. That’s the competition I want to see. Anthropic pushes harder, OpenAI has to answer, prices go down, models get better. We win. If everything I’m hearing actually lands over the next few days, this week is going to be ABSURD.
Opus 5.5 Pricing: Input per Mtok: 4$ Output per Mtok: 20$ Cache Read: 0.2$ Cache Write: 5$
28
11
7
507
51,545
Okay, finally finished my Muse Spark 1.3 benchmark. This ended up being the longest-running benchmark I've ever done at @VulcanBench and it definitely looks like Muse has some serious issues at lower effort levels. I was able to run Astra through my v4 eval suite across every effort level in ~12 hours, Muse Spark had single tasks at low effort levels that hit the 10 hour mark, on just a single task. It took a total of two weeks for me to run the entire benchmark. Overall my assessment is that Muse is a promising model, but they'll have to figure out why it has issues at lower effort levels, looking at the traces, it's just thinking, thinking, and thinking some more, while models like Astra and Fable just got it done. Astra continues to be the most token efficient of these three, and I continue to feel very good about Astra Light, both token efficient and accurate. Using Muse Spark 1.3 at lower effort levels is a complete non-starter imo because you'll be waiting 10 hours for something Astra light can do in 10 minutes. Model cards below, adding to the site soon:
22
6
2
99
9,866
Finished my ClaudeCut experiment. I wanted to see how much of a $20 Claude subscription actually goes into the work, and how much gets eaten by Claude Code itself. I cut it down to one terminal tool, a 36-token system prompt, and a capped context window. Startup dropped from 17.6k tokens to 895. Then I tested both setups on the same repo. One task was about understanding the project structure and entry points. The other was a code-search task: trace where config gets loaded, find the exact line, and explain the failure cases. Three runs per task. ClaudeCut came out at roughly half the cost in Claude Code’s own usage report, with comparable answers. On the search-heavy task it even used fewer turns. I also pushed both setups through long sessions with repeated compaction. ClaudeCut came back at around 14k tokens after compaction vs ~36k for stock Claude Code. This is still not a final benchmark. There aren’t enough repeats yet and the long runs need to be tested several more times, but I’m pretty much at the limit of what I can test on a $20 plan, so I opened the repo. If you use Claude Code, run it on your own project and send me the results. People in the replies pointed me toward Pi + Claude Agent SDK, where you get much more control over tools, prompts and compaction. That’s what I want to test next against ClaudeCut. Setup instructions, benchmarks and methodology are here: github.com/alexgetmancom/cla…
I castrated Claude Code. Ripped almost everything out and left only the bare minimum: read, inspect, write. Startup context is now under 2k tokens. I also capped the context window at 200k tokens so it compacts earlier instead of chewing through my limits with bloated context. Basically pushed Claude Code much closer to Pi’s minimal approach. This is all on the $20 Claude Pro plan, running Opus 5 on low effort. For me, that’s the only setup that makes sense for actual work. Now I want to see how far I can stretch a $20 subscription like this. I’ll report back. If you’re interested in the experiment, let me know.
28
4
2
50
15,144
I castrated Claude Code. Ripped almost everything out and left only the bare minimum: read, inspect, write. Startup context is now under 2k tokens. I also capped the context window at 200k tokens so it compacts earlier instead of chewing through my limits with bloated context. Basically pushed Claude Code much closer to Pi’s minimal approach. This is all on the $20 Claude Pro plan, running Opus 5 on low effort. For me, that’s the only setup that makes sense for actual work. Now I want to see how far I can stretch a $20 subscription like this. I’ll report back. If you’re interested in the experiment, let me know.
119
19
9
849
100,515
RobIW retweeted
>be me >discover effective altruism >apparently normal charity is inefficient >why donate to random sad thing when spreadsheet can tell you optimal sad thing >fair enough >buy mosquito nets >save lives >numbers look good >feel powerful >couple years later >someone asks an innocent question >why only count people alive today >huh >future people matter too >obviously >my grandchildren shouldn't matter less just because they haven't spawned yet >reasonable.jpg >keep following logic >what about their grandchildren >also yes >what about people in 500 years >sure >5000 years >why not >500 million years >starting to get weird but morality is morality >open calculator >humanity could survive for an astronomically long time >could colonize galaxy >could have trillions upon trillions of descendants >maybe digital people too >maybe simulated civilizations >maybe dyson spheres full of happy uploaded minds >calculator starts smoking >realize currently living humans are rounding error >8 billion people suddenly looking extremely beta >future contains potentially 10^something people >can't even fit beneficiaries in google sheets >new moral priority unlocked >protect the long-term future >stop thinking in units of "people helped" >start thinking in "fraction of cosmic endowment preserved" >malaria? >terrible >but only kills existing humans >AI extinction could delete the entire light cone >nuclear war could permanently derail civilization >bad institutions could lock in terrible values for ten million years >someone invents wrong constitution in 2140 >quadrillions suffer >better fund governance workshop now >friend says maybe we should improve hospitals >explain opportunity cost >friend says hospitals are full of actual sick people >explain scope sensitivity >friend stops inviting me to dinner >need to decide what to fund >easy >expected value >suppose project has one in a million chance of preventing extinction >sounds tiny >but extinction destroys 10^50 future lives >multiply >mother of god >$10 million project has expected value of several galaxies >charity evaluation complete >someone asks where the one-in-a-million number came from >expert judgement >which expert >us >how calibrated >extremely thoughtfully >reduce estimate to one in ten million to be conservative >still beats curing cancer by 38 orders of magnitude >epistemic robustness achieved >someone says maybe project doesn't work >assign 20% chance >still astronomical >maybe project makes problem worse >assign 5% chance >still astronomical >why 5 >because 30 felt pessimistic >publish 46-page report >contains seventeen sensitivity analyses >every sensitivity analysis begins after assuming intervention has positive sign >critic says you're multiplying enormous hypothetical stakes by extremely uncertain probabilities >yes >that's literally why it's important >critic says the uncertainty might be structural rather than numerical >make probability smaller >critic says no, I mean maybe your model is wrong >make probability smaller again >critic begins rubbing temples >discover AI safety >perfect longtermist cause >AI might kill everyone >or create utopia >or seize galaxy >or tile universe with paperclips >or create billions of conscious software minds >finally a problem with numbers big enough for me >start AI safety nonprofit >mission: prevent dangerous AI >hire smartest people available >smartest people immediately start building better AI to understand dangerous AI >interesting >we must understand capabilities to understand safety >we must scale models to study alignment >we must race ahead so less responsible actors don't get there first >we must deploy systems to learn how deployment can go wrong >we must build the thing quickly because building the thing quickly is dangerous >outsider asks why the people most worried about AI apocalypse all work at AI companies >complicated field >company releases stronger model >very concerned >company begins training even stronger model >extremely concerned >company raises $14 billion >concern reaches unprecedented levels >need to influence government >future is at stake >normal democratic process too slow >politicians don't understand exponential curves >public doesn't understand x-risk >experts must guide them >who counts as expert >people who understand x-risk >who understands x-risk >our friends >someone objects that this seems politically convenient >explain we're representing future generations >future generations unavailable for comment >develop concept of value lock-in >terrifying possibility that one ideology controls civilization forever >therefore extremely important that civilization adopts correct values before lock-in >whose values >let's circle back >begin with impartial morality >end with small group of people deciding what quadrillions of hypothetical beings would want >beautiful arc >meanwhile actual humans keep doing annoying things >voting wrong >having parochial attachments >loving family more than strangers >caring about local community >getting upset when told their suffering is cosmically negligible >evolutionary biases everywhere >explain that moral intuition cannot be trusted >except intuition that future digital people count >and intuition that extinction is uniquely bad >and intuition that our probability estimates are sane >and intuition that our institutional choices improve the future >those intuitions survived peer review >someone donates $5k to local homeless shelter >inefficient >could have funded 0.0000000000003% of an AI governance researcher >think of all the simulated people you just killed >okay maybe don't phrase it that way publicly >PR team says "future generations deserve a voice" >much better >journalist asks what longtermism means >say "future people matter" >everyone agrees >great >journalist asks what follows from that >well technically we should redirect enormous resources toward low-probability interventions affecting astronomical futures >journalist raises eyebrow >return to "future people matter" >motte has entered the chat >critic: of course future people matter >me: glad we agree >critic: I don't agree that your institute knows how to help them >me: why do you hate our grandchildren >eventually notice uncomfortable implication >if future value dominates everything >then helping people today mostly matters through effects on future >education matters because future institutions >health matters because future productivity >democracy matters because future trajectory >human beings slowly become instrumental variables in their own moral philosophy >see starving child >feel compassion >check spreadsheet >child's direct welfare contribution negligible >but perhaps childhood nutrition improves national institutional quality >compassion restored >tell myself this is impartial altruism >one day assistant asks obvious question >"how do you know your intervention actually improves the far future?" >silence >open spreadsheet >increase column width >add confidence interval >assistant asks again >"no, I mean how do you know the sign is positive?" >stare into cosmic light cone >10^50 people staring back >none of them exist >none of them can tell me >none of them can falsify my assumptions >realize I have invented the perfect constituency >infinitely important >completely silent >and always represented by me
757
2,392
947
20,400
2,900,255
DeepSeek V4.1 Flash now has 230-300 TPS enjoy the speed! 🐐
51
20
8
895
70,914
DeepSeek V4.1 Flash is live in Command Code. 6x usage on $10/mo GOAT for a week. $60 usage. 154K requests. 7.8B tokens. GOAT plan is the best AI coding plan. Available in all plans and API. 🐐
110
35
16
841
274,085
Things should be starting to get back to normal now! Let us know if not & apologies for the inconvenience 🙏
247
16
10
378
102,180
RobIW retweeted
There are several reports of people experiencing extremely high and unusual usage in Codex, using not only Astra but also other models like 5.6. I believe it may be a configuration issue or a bug affecting certain users, and I predict the team will acknowledge it and make up for it with a new reset soon.
324
112
50
2,753
311,974
RobIW retweeted
We will give one banked reset for every day you don't have access to Astra on your paid ChatGPT plan, starting today. Team is moving mountains to give access as fast as we can. First one will land in ~ 3 hours. There is still time to create your account if you don't have one.
5,549
3,436
3,538
48,009
9,197,944
RobIW retweeted
GPT-6 Astra is world class at Blender and 3 dimensional reasoning. This was a 1-shot game it created, all running in browser.
407
409
180
12,768
2,532,863