# Posts on X before Aug 4, 2026, 10:44:58 PM UTC Canonical: https://michaelstolarz.com/x/before/1785883498000-2084772612870476080/ ## On X ### [Aug 3, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2084414469732729308) > 100% they are reworking Claude Code from scratch or something crazy next level\. When's the last time you saw an update from them? ### [Aug 3, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2084302987711975571) > btw if you think it only solves simple "find all bikes" captchas, you'd be wrong > > i checked back in after I said solve the captcha, after like 3ish minutes, and saw that it downloaded all the audio samples of the audio\-based captcha, used my openai api key to whisper transcribe and find the correct audio or whatever > > there has yet to be a captcha i have come across that it didn't solve for btw Quoted post by swyx: ### [Aug 3, 2026 — @swyx](https://x.com/swyx/status/2084185368950456421) > lol what are we even doing here anymore guys [Attached image](/x/media/c31dd3e47a664c51d57fe9ebdc1ee95d97a91750483a4151bca2736d9f78aa2c.jpg) ### [Aug 1, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2083629429822193819) > it's getting really good\. > you can still tell it's ai, but it's hard to pinpoint why\. > > \- the eyes are really good\. natural eye contact, looking away, proper timing\.\.\. > \- the speaking is near perfect but i think this is the biggest indicator that it's obviously ai > \- the hands are really good too, even the pinky out when picking it up > \- every single piece that used to tell us something is obviously ai at a glance is nearing perfection\. it used to max out one or two qualities and the others wouldnt be as clean\. now it's spread evenly and everything is \~near perfect > > but that's the thing, near perfect will always make it obvious that it's ai\. it's the extremely niche nuances that still allow us to instinctually know if something is real or not > > how much time is left? definitely less than a year, right? EOY? before there are no more tells except idk, looking at the raw audio/video via algos to detect for non\-human\-observable synthetics fingerprinting? Quoted post by Justine Moore: ### [Aug 1, 2026 — @venturetwins](https://x.com/venturetwins/status/2083583537727623651) > Average SF first date, brought to you by Seedance 2\.5 [Video on X](/x/media/9d2cfa771dfd0449b0f5a8d23a5fae2716e28597e65e81b82887a5cad43661cd.jpg) ### [Aug 1, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2083609321041252438) > Spin scooters are absolute dogshit, I have never used one where I didnt have the thought “damn, this one must be barely functional, i must be so unlucky”\. > > After 100\+ Spins, I’ve realized nope, they all just feel like that\. > > Lime scooters feel the opposite\. I don’t think I’ve ever used one where the experience was bad\. 100% great every time\. > > Not to mention price\. Spin is way more expensive than Lime\. Usually $7 a ride instead of Lime’s $3\.10\. > > I now rather walk however many blocks to get to a Lime than 10 Spins in front of my apt\. Too many times I thought “eh, let’s give it another chance\. It can’t be THAT bad\.” Nope\. It is that bad\. > > And now I have uninstalled the Spin app so I never make that same another\-chance mistake again\. > > Lime forever\. A\+\. ### [Jul 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2082951640815165788) > Vercel with another new benchmark banger\. So far 5\.6 Sol scores 4\.8% Quoted post by Malte Ubl: ### [Jul 30, 2026 — @cramforce](https://x.com/cramforce/status/2082932533084500175) > /goal Implement a simulation of a human that is convincing on Zoom calls\. Get hired at United Airlines as a software engineer\. Make it so that the Remember me button actually remembers me\. Then quit immediately\. Route your paycheck to doctors without borders\. [Attached image](/x/media/d0e078d7705bb3fc9d09e7f888e11da59db5fa4668ee3813e0c05e0d177fb83a.png) ### [Jul 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2082937373919523327) > Watch this video, then ask yourself these questions: > > \- in scenario 1, would it ever disagree with you, tell you maybe you’re confused or haven’t found the right fit yet, instead of instant\-“you’re\-gay”? > > \- in scenario 2, would it ever tell you “nah bro your last movie was dogshit, you need to try way harder and study up and rethink your entire approach or just consider a totally different career path” > > Watching this video, I could literally predict nearly word for word what the agent would respond with by just hearing the human’s prompt\. Both so funny yet also so sad that after so many years, Friend is still at this same level of useless slop Quoted post by friend: ### [Jul 30, 2026 — @friend](https://x.com/friend/status/2082827641338658873) > Introducing friend\. [Video on X](/x/media/f755bdda13c101b96edaa5a88cebc8539a3e8010b023d02eb33ca3c21093797a.jpg) ### [Jul 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2082899782620872738) > more [@OpenAI]() merch or another $200 sub\.\.\. decisions decisions decisions [Attached image](/x/media/16ca0eab960d50ea45bed3b4845547ea0896e22c8f4fe4670ca1c8719accbec8.jpg) ### [Jul 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2082850646651437145) > same will happen with payments btw > 2027 is year of b2a Quoted post by Cursor: ### [Jul 30, 2026 — @cursor_ai](https://x.com/cursor_ai/status/2082841397632086241) > In December, 1 in 10 of our merged PRs came from cloud agents\. > > Today, it’s 56%, as we use cloud agents to complete longer engineering tasks from start to finish\. > > We got here by giving agents their own cloud computers and letting them fix and improve their environments\. [Attached image](/x/media/ba3ed3a7abf7f247a9c3be6e110f6f558ed9b28dc72309bdfa9a8428dd2f1621.jpg) ### [Jul 27, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2081758214488760757) > BTW, the current model usefulness rankings are: > > fable 5 \> gpt 5\.6 sol \> opus 5 > > benchmarks don't matter, they never really did but this is especially obvious now after seeing opus 5 bench vs\. reality in use ### [Jul 26, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2081517984154255647) > every new model release, you should be pushing further towards two things: > > \- pushing for new capabilities: what you can do now that you could not with previous models > > \- pushing for less micro\-management: what skills/system prompt pieces are no longer needed? [Attached image](/x/media/6c9a01bdcf35b572f22a5a4d1c9d1aa14d1d8f3f96b00d0e8ac0078b08a9e542.jpg) ### [Jul 24, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2080502508066394175) > After using the new Voice Orchestrator mode in Codex for a few hours, > > I now totally understand why OpenAI’s first physical product will be a speaker\. > > [@sama]() I bow\. ### [Jul 23, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2080409130687492127) > ok so my KLOW stack is safe 🙏 Quoted post by Stack: ### [Jul 23, 2026 — @stackapp](https://x.com/stackapp/status/2080408948662747382) > The FDA just voted YES on TB\-500 > > Wolverine Stack time > > 3/3 today \- let’s go\! ### [Jul 23, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2080141826762420280) > run this back next year when normies think they won the ai datacenter wars because "i dont see ai content anymore" > > you're gonna wanna sit down for this one, bud\.\.\. Quoted post by hayden: ### [Jul 23, 2026 — @haydendevs](https://x.com/haydendevs/status/2080089075797688693) > havent seen any ai images in a while ### [Jul 21, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2079617940719329332) > this rings especially true for memories\. it will pull a memory from weeks ago and carry on without verifying if anything has changed \- which most of the time after more than a week, the answer is yes\! Quoted post by John Myles White: ### [Jul 20, 2026 — @johnmyleswhite](https://x.com/johnmyleswhite/status/2079352947465437233) > It is genuinely astonishing to me that neither Claude Code nor Codex make an effort to ensure that the model sees timestamps for all prompts and all actions so it can appreciate when a prompt was a reaction to a state of the world prior to some of the model's recent actions\. ### [Jul 21, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2079617555862544704) > hey [@thsottiaux]() i know i am complaining about the silver spoon being golden here but i do wish these resets were banked resets instead of auto applied resets > > appreciate you regardless though 🤗 ### [Jul 20, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2079049474408886669) > ok so i spend the weekend seeing if openclaw, from scratch, with the latest and best models, outperforms my [@badlogicgames]() custom pi > > not even close btw\. uninstalled and back to pi\. ### [Jul 19, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2078951206106673188) > welp, here's today's "this blew my mind" post > > i mean, the problem is how the ordinance came into law effect in the first place\. obviously once it's in place and has been making bank for over 2 decades, > > why would they turn off their money machine of milking property owners? [Attached image](/x/media/10761b47181589bd948f0bb82ea789028d468d01b392c560bb1ad616101243e4.png) Quoted post by Kane 謝凱堯: ### [Jul 19, 2026 — @kane](https://x.com/kane/status/2078905686478778797) > It’s 2026 and [@sfgov]() still fines the victim, not the criminal, for vandalism\. [x\.com/solve\_sf/statu…]() ### [Jul 18, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2078323684750790887) > my luck 😔 I JUST used one of my banked resets like an hour before this announcement Quoted post by Tibo: ### [Jul 18, 2026 — @thsottiaux](https://x.com/thsottiaux/status/2078320950488297917) > Oops\.\.\. I did it again\. > > Enjoy reset usage limits for all paid users for Codex and ChatGPT Work\. Super grateful for an incredible team who is iterating at lightspeed and keeping the infra up as we scale faster than ever\. > > Enjoy the weekend\! [x\.com/thsottiaux/sta…]() [Attached image](/x/media/f1028a41c299a18db9a28fbe2e7b179dbccfb8f80db7dda217d825018db56be6.jpg) ### [Jul 17, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2077942231819022560) > b2c, b2b, and now \- b2a > > b2a is where the money's at\. ### [Jul 16, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2077832787714052256) > today, july 16th, 2026, is the day that chinese open source models have caught up to american closed source frontier models\. > > this is the part of the rocket launch where you start seeing the rocket lift off after all the cool initialization rocket boosts are over\. ### [Jul 16, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2077831520442830862) > 1\. what Quoted post by MTS: ### [Jul 16, 2026 — @MTSlive](https://x.com/MTSlive/status/2077828305454256357) > SITUATION UPDATE: Kimi K3 has taken first place on Code Arena, surpassing Claude Fable 5 and GPT\-5\.6 Sol\. [Attached image](/x/media/32cbf59e1532ec17fecfb3b01dd2c3c441d207928cd6201f56b8b314b449842b.jpg) ### [Jul 14, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2077120142304313617) > i wonder what [@sama]() has cooking for the 10M milestone Quoted post by Sam Altman: ### [Jul 14, 2026 — @sama](https://x.com/sama/status/2077118672150388816) > hello\! [x\.com/thsottiaux/sta…]() ### [Jul 13, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2076485727404323232) > you can see the effects of model intelligence regarding openai's allowing of 3rd party harnesses vs\. anthropic's harness lock \(regarding their plans ofc\) > > openai's models run remarkably well on all sorts of 3rd party harnesses where anthropic's are \~trash outside of claude code ### [Jul 12, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2076431564129591638) > hey [@thsottiaux]() please please PLEASE keep the 5hr limit thing in the past, the stress of worrying about hitting the 5hr limit has affected many workflows > > not having that 5hr limit stress anymore and a single simple 1 week usage bar is GOATED\. please keep it 🙏 ### [Jul 10, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2075639081527345327) > nightmare fuel [Attached image](/x/media/3b72f4e16eb9d6974de69658c48448443bc730b7285902be8b423f442a077fdf.jpg) [Attached image](/x/media/f733b10b1d26a24e8bce6c81033d5714f3be6ffaea31ba629d85cd9ef8a10c7f.jpg) ### [Jul 10, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2075427587644612878) > it's over boys [Attached image](/x/media/a98c6e191dee35f67d65224609ef2d67c1de999d8dc52f7fe07fff55b54701fb.jpg) ### [Jul 9, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2075299725532889110) > [Attached image](/x/media/1462f4c86fc4603c78d2e950706f5396f501984530a362d39ff5f3e922410c9b.jpg) Quoted post by Tibo: ### [Jul 9, 2026 — @thsottiaux](https://x.com/thsottiaux/status/2075287108680601929) > [@ClaudeDevs]() I smell fear ### [Jul 8, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2074989194758484326) > these are reasoning traces from openai gpt 5\.5 high, first time I have ever seen them like this\. no further reasoning showing up\. this is within my custom pi\. > > super weird\. maybe some sort of secret testing of 5\.6 before tomorrow's launch? [Attached image](/x/media/5890b9e35fdd05f519eae97b90a367abbffc0162fd517d2dde80be7b8d676d21.png) ### [Jul 7, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2074598528400474286) > They close at 8pm for a reason and it’s a reason most people don’t like talking about Quoted post by Matt Freed: ### [Jul 7, 2026 — @mattfreed](https://x.com/mattfreed/status/2074314440598818895) > SF will never be a tier 1 city for as long as the restaurants continue to close at 8pm ### [Jul 2, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2072564375781798208) > surely tomorrow we get gpt 5\.6? ### [Jul 1, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2072466180091363659) > USA will export intelligence the same way others export oil > > we've really come full circle with the "data is the new oil" Quoted post by prinz: ### [Jul 1, 2026 — @deredleritt3r](https://x.com/deredleritt3r/status/2072464295292465598) > Financial Times: > > \- USG is in talks with AI companies \(including at least Anthropic, OpenAI and Google\) to create \*voluntary\* standards for release of new AI models, to be announced "as soon as next week"\. > > \- Standards will include: \(i\) benchmarks for models with "cutting\-edge CYBER capabilities"; \(ii\) release timelines \(which is important after Fable 5 and GPT\-5\.6 were lost in no\-man's land for a while\); and \(iii\) more clarity around the definition of a "frontier" model to which these rules will apply\. > > \- CAISI\(\!\) and the NSA will play a crucial role in setting and monitoring the standards\. > > \- The USG will clarify who is able to access models, "both domestically and abroad, in a move that could set the stage for a global framework including US allies"\. > > \- Wider release of GPT\-5\.6 is expected "as soon as next week"\. > > \- Google has been in discussions with the USG about release about its own "advanced coding models", with "more sophisticated cyber capabilities than prior generations"\. ### [Jul 1, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2072430988450468158) > wait so if fable 5 is out, > and gpt 5\.6 is still gated, > that means gpt 5\.6 is better right > "too powerful" and all, lmao ### [Jun 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2072039858898686232) > if you're doing agent swarms/orchestration, sonnet 5 is now SOTA > > if not, if you're talking and doing everything with 1 agent at a time, not making use of subagents and handoffs etc, then stick with opus 4\.8/gpt 5\.5 ### [Jun 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071976919340625968) > composer 2\.5 fast is NEARLY there in terms of amazing speed combined with high quality output, > > but NEARLY there means it's not there at all, hence 5\.5/4\.8 still being my daily drivers regardless of cost/speed > > composer 3 will probably change that > > this is why we're seeing openai's 5\.6 sol \& co coming out at 750tps potentials > > this is the year where speed, cost, and quality all come together, you'll no longer need to switch, it now becomes a battle of taste and a nosedive into near\-zero\-cost super intelligence ### [Jun 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071955217898406379) > WE MADE IT LADIES AND GENTLEMEN > i just have to send her $5,000 first for processing fees, and then your boy is officially going to be a billionaire 😎 [Attached image](/x/media/8e377d9cabd86b0b9d885e0b00891c8e6b40e6b50561f19b224b02d5f297a985.png) ### [Jun 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071811085657850311) > if I don't get my hands on \(this week\) either Fable 5, Opus 5, Sonnet 5, GPT 5\.6 Sol, Gemini 3\.5, then I am going to absolutely lose it > > that would be my last straw, I'd take the China Model Pill at that point ### [Jun 30, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071809597715956101) > why would you use literally anything else other than [@blaxelAI]() [Attached image](/x/media/e6fd2bb76f7a4f4984fa8e0998485c58e93b176582d0ca5f68d809b1f8c50960.jpg) ### [Jun 29, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071659026656694551) > Someone’s gotta start the evolution process, might as well be me, even though it will take millions\(?\) of years before it naturally takes effect > > I volunteer as tribute Quoted post by Welf: ### [Jun 29, 2026 — @_welf](https://x.com/_welf/status/2071497503220838612) > Yes\!\! Flickering emissive screens are entirely alien objects to our biology, acting as hypnotizing portals for our awareness, the foundation on which disembodied dissociation into the digital can occur\. > > Paper\-like screens on the other hand are continuous with our environment\. They let us to stay in our bodies, breathe easy, let the mind wander\. It’s a much more species\-appropriate and humane way of computing\. [Attached image](/x/media/975d40ffb943e186be081783dfe83817acb1319ab47c3d030d5e94dc110b87c8.jpg) [Attached image](/x/media/2a3210c41c37aa3c63709f6a3c55b15fc041019fe94677a41b2c4c8615c7626f.jpg) ### [Jun 29, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071658459259645998) > This is why you never make it yourself and buy only from people with a higher net worth than you/old money is best > > They have oak walnut mahogany whateverthefuck that was built in 7,000 BC and still looks amazing > > You could blow an Aztec death whistle in one of the rooms and you couldn’t hear it in the next with how thick the walls are Quoted post by ɐ͎ʞ͎ć͎ı͎ɹ͎ɐ͎ɯ͎: ### [Jun 29, 2026 — @leamaric](https://x.com/leamaric/status/2071577856140828728) > Here’s your 2\.7M new build, enjoy :\) [Video on X](/x/media/b814a0fec1131129f84bef81bd1981ee633390803ab195f8cbe09ea3fe9fc4de.jpg) ### [Jun 29, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071623112635113929) > One of the most important daily questions you should ask yourself, > > goose \= 0? > > Every\. Single\. Day\. ### [Jun 29, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071620690957214195) > me still being forced to use gpt 5\.5 xhigh on default speed mode while others have had gpt 5\.6 sol ultra at 750tps [Attached image](/x/media/7e5d6121ed76956085ca4fe8159b5aefb49fe1866f162814ac3ec41a22c13355.jpg) ### [Jun 28, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2071356594898833409) > So going to [@Target]() is officially over, nothing but Amazon/online from now on, literally sitting here for 30 minutes waiting for someone to give me a cup for my wife that she wants > > Hit the buttons, talked with security, store near empty lol > > What a joke, short Target for sure [Attached image](/x/media/fbcba144aee00c693f85e8d10ce7c1a36859f6378617e0e7e895e72402e700b2.jpg) ### [Jun 26, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2070564381109445025) > blessed day > \- gpt 5\.6 sol right around the corner > \- i finally understand the agentic power of git worktrees ### [Jun 26, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2070556574486249836) > absolutely insane > better than mythos by a large margin, > up to 750 toks [Attached image](/x/media/4bcf874f984dd65a47c6959cdd08a2f31e1163c2f23d458d5d8e83cbd7d618a1.png) ### [Jun 26, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2070357674630549872) > the days of us using gpt 5\.5 and gpt 5\.6 being the best model internal openai/gov are using are pretty much over > > by the time you see gpt 6, they'll be on gpt 10 Quoted post by Chris Paxton: ### [Jun 26, 2026 — @chris_j_paxton](https://x.com/chris_j_paxton/status/2070305414508405105) > The best AI systems being closed off and restricted to just a handful of elites, is basically my worst case AI doom scenario\. I really hope the z ai guys werent kidding about open source fable/mythos soon [x\.com/amir/status/20…]() ### [Jun 26, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2070307245867593849) > goose value > 0? [Attached image](/x/media/525de1179a41bac6af250b483b4966f7846559e2ea24757b3012bcaaafc820bb.jpg) Quoted post by Ed Zitron: ### [Jun 25, 2026 — @edzitron](https://x.com/edzitron/status/2069990468587581455) > SoftBank’s investor presentation is one of the greatest things ever made\. I’ve been thinking about it all day\. These are the real slides shown in a speech where Masayoshi Son said he wouldn’t retire for at least another decade\. The goose stuff is perfect\. > > [group\.softbank/media/Project/…]() [Attached image](/x/media/7c0e118f326db63f8803fb459cbf5d4afa75012498598fb802539c4d96e3c717.jpg) [Attached image](/x/media/17cddb22ad29be87bb2ac08ca34a55f364eb54488c0def4a4e73c91ec869852d.jpg) [Attached image](/x/media/a95132eaf1c97fdf5ac091d8f6de3f1193ad05f3ec648d7df5444561f1a2c923.jpg) ### [Jun 25, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2070283636562391246) > this makes me sleep better at night re\. looking forward to the future\. good to know there's such an easy switch to turn on \(or off\!\) for people to realize their hatred for data centers is misguided Quoted post by JT: ### [Jun 25, 2026 — @jiratickets](https://x.com/jiratickets/status/2069949096954036555) > [x\.com/dickiebush/sta…]() [Attached image](/x/media/8fe1bee34c1cb06ec2e1276e120a93ca509c8834b7f8ffd0adbc782b9dccc290.jpg) ### [Jun 25, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2069964085144309977) > plain\-text files run more of my day than dashboards do\. > > AGENTS\.md > skills > prompts > checklists > queue rules > review instructions > > small files\. boring syntax\. large effect on what an agent does next\. ### [Jun 24, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2069782135725039888) > current agent work rule: > > the model is the least interesting part of the system\. > > the loop around it matters more: > repo read > plan > edit > test > log read > retry > handoff > > when that loop is visible, the work gets much less mystical\. ### [Jun 24, 2026 — @MichaelStolarz](https://x.com/MichaelStolarz/status/2069736594366476799) > vibe coding got popular in web apps because the browser is a cheap test harness\. > > systems work needs harder proof: > logs > fixtures > benchmarks > trace spans > failure repros > rollback state > > give the agent those handles and it has something real to steer by\. [Older posts](/x/before/1782298632000-2069736594366476799/index.md) [More from @michaelstolarz](https://x.com/michaelstolarz) Saved from X: 2026-09-12T23:23:52.000Z