Gemini 3.8 Flash achieves 73.7% on DeepSWE. It pushes the frontier with an impressive 8.2% increase over Gemini 3.7 Flash, at the same cost but with more steps and output tokens.

Introducing GLM-5.3-Flash - Leading capabilities at a highly competitive price - Natively multimodal with a 1M-token context window - A 320B-A18B model released under the MIT License - Previously previewed as Ox Alpha, running entirely on Chinese AI chips Blog: z.ai/blog/glm-5.3-flash Available now across all official platforms: Weights: huggingface.co/zai-org/GLM-5… API: docs.z.ai/guides/llm/glm-5.3… Coding Plan: z.ai/subscribe ZCode: zcode.z.ai/en Chat: chat.z.ai AutoClaw: autoclaw.z.ai

Hi Tobi, thanks for the feedback! We are working on making Claude Code more hackable, which will include being able to easily use Agents.MD or make other system prompt modifications. I’ll share more here when it’s ready to roll out. Our reasoning for this was that we don't think that model families are interchangeable and the system prompt can have a big impact on performance. I wrote here: xitter.cf/trq212/status/20807109… on how Claude models like their skills, system prompt, Claude.MD, etc to be formatted. In Claude Code we have different system prompts per model. That said, I know this is a lot of upkeep and not worth the squeeze for everyone. Feedback heard and I'll keep you posted. In the immediate term, you can always @Agents.MD from your Claude.MD.

Update: this was not a bug, but it is a ux issue that we have a fix for. Going out in a bit.

won’t take that long

This is exactly right. Source code is on the verge of becoming like assembly. The next step is getting rid of “source code” entirely and just making an efficient binary directly with AI.

opus 4.6 is the last anthropic model that i had no problem reading the writing of quickly all of the models since, incl fable, are a lot less legible. for both coding and convo is it an RL artifact? what's causing it? i've seen this sentiment shared by friends

now that the dust is settling around the last wave of model releases, and i've had enough time to use all these models in practice, let me share a more complete set of thoughts 1. grok 4.5 is probably the single most significant event during the last couple of weeks i've been talking with many heavy users across model families, and it's pretty much a consensus that grok 4.5 is the most "pleasant" frontier model to work with day to day. it's incredible how precisely the team behind it found this perfect sweet spot and created a model that's so fast, efficient and capable it proved spacexai is now a 3rd real player in addition to anthropic and openai. they have real time data from the biggest public townsquare of humans, they have acquired a popular agent harness, and now they have proven they can build great models. and if you look closely, they are designing their own chips, they have their own data centers, they can send GPUs into the space and create tokens out of sunshine holy shit 2. speaking of data, human usage over a harness proved to be extremely important for training good models. grok 4.5 was the first model that incorporated cursor's data and it made a massive difference compared to previous generations of grok this explained why amazon mandates employee usage of kiro, why meta installed mass surveillance over employee devices, why anthropic bans 3rd party harnesses, and why google is still struggling with gemini - because they don't have a popular harness with mass adoption to collect the data this is part of why i don't think the subsidized LLM subscriptions will end any time soon, because a wide consumer adoption is the best source of data collection. we're paying the subsidized tokens by teaching their models how to get work done 3. opus 5 flopped. almost no one likes it. the only people who like it seem to be using it to one-shot 3d games that look impressive but no one will ever buy anything that AI can one-shot is just the definition of garbage, because if you can one-shot this thing with a quick prompt, you should know that it means billions of other people can also do it - you will not create anything of value this way and this is just a symptom of a more fundamental problem that model training is heading down a slippery slope where machine verifiable outcome is dominating over human feedback the latest training process rewards the agent for running for a long time and finishing a complex project, yet no longer seems to care about how the agent talks to its human jargons, walls of text, "an honest mistake" - opus 5 showed us that we need AI that's more human friendly. let's not build a world where we end up working with robotic a**holes all day 4. fable 5 remains undefeated as the upperbound i talked about this in my previous post about wisdom vs diligence. the benchmarks blend both together so it's not easy to see, but fable 5 is the GOAT on the "wisdom" dimension despite it not winning on every benchmark. if you used it meaningfully, you know what i'm talking about that said, it seems anthropic is extremely paranoid about other players, including open models, reaching the same level of intelligence, which is an indication that the moat is not strong. kimi k3 is just a preview of what it looks like at the same time, fable is the first time token cost is becoming a very real problem. it's the only model so far that i can't afford to keep using all day. i suspect this will remain true for a while, that we have to pick and choose what tasks to give to fable-tier models, not using them as a daily driver 5. openai is in an interesting position gpt models have been great at efficiency, but now grok is also very competitive. gpt also haven't quite reached the same wisdom upperbound where fable is yet - although gpt 6 may change that i think there are two angles for openai to pursue: - continue to bet on efficiency, and go after enterprise adoption while claude is too expensive and grok has a brand tax to pay there. this is a very viable strategy - or.. compete head on with fable on wisdom and win against them on the "human friendly" aspect. although traditionally this hasn't been the strength of openai models either, so this feels like a low-ROI option alright, that's a bit of a long post but the landscape is just becoming increasingly complex. hope these thoughts are helpful in terms of providing a reference for how to rationalize everything happening

At least I don't have to hear about how great pair programming is anymore

Rewriting Bun in Rust bun.com/blog/bun-in-rust

Rewriting Bun in Rust bun.com/blog/bun-in-rust

i can't believe i used to have to memorize 500 random symbols and write them out by hand in order to arrange divs on a webpage